Artificial Intelligence in Healthcare

Topic Information

Dear Colleagues,

The complexity and rise of data in healthcare mean that artificial intelligence (AI) and related technologies will increasingly be applied in the field. This topic seeks to not only present solutions that combine state-of-the-art devices, computer software, model-based approaches for exploiting the huge health and bio data, and the Internet of Things resources available (while ensuring that these systems are explainable to domain experts), but also new methods that more generally describe the successful application of emerging technologies and spectra, and science and engineering to issues such as disease, cancer, databases, sensor device and user interfaces, software design, and system implementation in healthcare, as well as the medical domain, biology, and wellbeing domains. The main idea is to cover the applications of artificial intelligence (AI) and related technologies and engineering issues addressing all facets of solutions in the real world from databases, disease, and human health technology from a wellbeing and healthy life perspective. This topic welcomes the submission of technical, experimental, methodological, and data analytical, developing and implementing contributions focused on real-world problems and systems, as well as on general applications of AI, data mining, and data analytic methodologies in emerging technology solutions and real world applications related to life, disease, cancer, healthcare, and hospitals that can help human beings to lead heathy lives, including, but not limited to, the following topics:

• Data mining in healthcare

• Machine and deep learning approaches for disease, and health data

• Decision support systems for healthcare and wellbeing

• Regression and forecasting for medical and/or biomedical signals

• Healthcare and wellness information systems

• Medical signal and image processing and techniques

• Applications of AI techniques in healthcare and wellbeing systems

• Intelligent computing and platforms in medicine and healthcare

• Biomedical applications

• Biomedical text mining

• Deep learning and methods to explain disease prediction

• Big data frameworks and architectures for applied medical and health data

• Visualization and interactive interfaces related to healthcare systems

• Recommending and decision-making models and systems based on AI and data mining technologies

• Machine learning and deep learning applications for life, disease, cancer, healthcare, and hospitals

• Querying and filtering on heterogeneous, multi-source streaming life and health data

• Internet of things and data management for human life

• Data and applications for human life; data and applications for technology improvement

• Emerging technologies and applications of data, database, big data, and data mining, AI, models

Prof. Dr. Keun Ho Ryu
Prof. Dr. Nipon Theera-Umpon
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Applied Sciences applsci	2.7	4.5	2011	16.9 Days	CHF 2400
Diagnostics diagnostics	3.6	3.6	2011	20.7 Days	CHF 2600
Healthcare healthcare	2.8	2.7	2013	19.5 Days	CHF 2700
International Journal of Environmental Research and Public Health ijerph	-	5.4	2004	29.6 Days	CHF 2500

MDPI Topics is cooperating with Preprints.org and has built a direct connection between MDPI journals and Preprints.org. Authors are encouraged to enjoy the benefits by posting a preprint at Preprints.org prior to publication:

1. Immediately share your ideas ahead of publication and establish your research priority;
2. Protect your idea from being stolen with this time-stamped preprint article;
3. Enhance the exposure and impact of your research;
4. Receive feedback from your peers in advance;
5. Have it indexed in Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (71 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Applied Sciences Diagnostics Healthcare IJERPH

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

16 pages, 566 KiB  

Open AccessReview

Towards the Use of Big Data in Healthcare: A Literature Review

by Grazia Dicuonzo, Graziana Galeone, Matilda Shini and Antonella Massari

Healthcare 2022, 10(7), 1232; https://doi.org/10.3390/healthcare10071232 - 01 Jul 2022

Cited by 7 | Viewed by 3920

Abstract

The interest in new and more advanced technological solutions is paving the way for the diffusion of innovative and revolutionary applications in healthcare organizations. The application of an artificial intelligence system to medical research has the potential to move toward highly advanced e-Health. [...] Read more.

The interest in new and more advanced technological solutions is paving the way for the diffusion of innovative and revolutionary applications in healthcare organizations. The application of an artificial intelligence system to medical research has the potential to move toward highly advanced e-Health. This analysis aims to explore the main areas of application of big data in healthcare, as well as the restructuring of the technological infrastructure and the integration of traditional data analytical tools and techniques with an elaborate computational technology that is able to enhance and extract useful information for decision-making. We conducted a literature review using the Scopus database over the period 2010–2020. The article selection process involved five steps: the planning and identification of studies, the evaluation of articles, the extraction of results, the summary, and the dissemination of the audit results. We included 93 documents. Our results suggest that effective and patient-centered care cannot disregard the acquisition, management, and analysis of a huge volume and variety of health data. In this way, an immediate and more effective diagnosis could be possible while maximizing healthcare resources. Deriving the benefits associated with digitization and technological innovation, however, requires the restructuring of traditional operational and strategic processes, and the acquisition of new skills. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 768 KiB)

29 pages, 2079 KiB  

Open AccessArticle

A Hybrid Feature Selection Approach to Screen a Novel Set of Blood Biomarkers for Early COVID-19 Mortality Prediction

by Asif Hassan Syed, Tabrej Khan and Nashwan Alromema

Diagnostics 2022, 12(7), 1604; https://doi.org/10.3390/diagnostics12071604 - 30 Jun 2022

Cited by 5 | Viewed by 1966

Abstract

The increase in coronavirus disease 2019 (COVID-19) infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has placed pressure on healthcare services worldwide. Therefore, it is crucial to identify critical factors for the assessment of the severity of COVID-19 infection and the [...] Read more.

The increase in coronavirus disease 2019 (COVID-19) infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has placed pressure on healthcare services worldwide. Therefore, it is crucial to identify critical factors for the assessment of the severity of COVID-19 infection and the optimization of an individual treatment strategy. In this regard, the present study leverages a dataset of blood samples from 485 COVID-19 individuals in the region of Wuhan, China to identify essential blood biomarkers that predict the mortality of COVID-19 individuals. For this purpose, a hybrid of filter, statistical, and heuristic-based feature selection approach was used to select the best subset of informative features. As a result, minimum redundancy maximum relevance (mRMR), a two-tailed unpaired t-test, and whale optimization algorithm (WOA) were eventually selected as the three most informative blood biomarkers: International normalized ratio (INR), platelet large cell ratio (P-LCR), and D-dimer. In addition, various machine learning (ML) algorithms (random forest (RF), support vector machine (SVM), extreme gradient boosting (EGB), naïve Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN)) were trained. The performance of the trained models was compared to determine the model that assist in predicting the mortality of COVID-19 individuals with higher accuracy, F1 score, and area under the curve (AUC) values. In this paper, the best performing RF-based model built using the three most informative blood parameters predicts the mortality of COVID-19 individuals with an accuracy of 0.96 ± 0.062, F1 score of 0.96 ± 0.099, and AUC value of 0.98 ± 0.024, respectively on the independent test data. Furthermore, the performance of our proposed RF-based model in terms of accuracy, F1 score, and AUC was significantly better than the known blood biomarkers-based ML models built using the Pre_Surv_COVID_19 data. Therefore, the present study provides a novel hybrid approach to screen the most informative blood biomarkers to develop an RF-based model, which accurately and reliably predicts in-hospital mortality of confirmed COVID-19 individuals, during surge periods. An application based on our proposed model was implemented and deployed at Heroku. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

11 pages, 9351 KiB  

Open AccessArticle

Rapid Prediction of Retina Stress and Strain Patterns in Soccer-Related Ocular Injury: Integrating Finite Element Analysis with Machine Learning Approach

by Yasin Shokrollahi, Pengfei Dong, Mehmet Kaya, Donny W. Suh and Linxia Gu

Diagnostics 2022, 12(7), 1530; https://doi.org/10.3390/diagnostics12071530 - 23 Jun 2022

Cited by 4 | Viewed by 2170

Abstract

Soccer-related ocular injuries, especially retinal injuries, have attracted increasing attention. The mechanics of a flying soccer ball have induced abnormally higher retinal stresses and strains, and their correlation with retinal injuries has been characterized using the finite element (FE) method. However, FE simulations [...] Read more.

Soccer-related ocular injuries, especially retinal injuries, have attracted increasing attention. The mechanics of a flying soccer ball have induced abnormally higher retinal stresses and strains, and their correlation with retinal injuries has been characterized using the finite element (FE) method. However, FE simulations demand solid mechanical expertise and extensive computational time, both of which are difficult to adopt in clinical settings. This study proposes a framework that combines FE analysis with a machine learning (ML) approach for the fast prediction of retina mechanics. Different impact scenarios were simulated using the FE method to obtain the von Mises stress map and the maximum principal strain map in the posterior retina. These stress and strain patterns, along with their input parameters, were used to train and test a partial least squares regression (PLSR) model to predict the soccer-induced retina stress and strain in terms of distributions and peak magnitudes. The peak von Mises stress and maximum principal strain prediction errors were 3.03% and 9.94% for the frontal impact and were 9.08% and 16.40% for the diagonal impact, respectively. The average prediction error of von Mises stress and the maximum principal strain were 15.62% and 21.15% for frontal impacts and were 10.77% and 21.78% for diagonal impacts, respectively. This work provides a surrogate model of FE analysis for the fast prediction of the dynamic mechanics of the retina in response to the soccer impact, which could be further utilized for developing a diagnostic tool for soccer-related ocular trauma. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 246 KiB)

14 pages, 1181 KiB  

Open AccessArticle

Machine Learning Coronary Artery Disease Prediction Based on Imaging and Non-Imaging Data

by Vassiliki I. Kigka, Eleni Georga, Vassilis Tsakanikas, Savvas Kyriakidis, Panagiota Tsompou, Panagiotis Siogkas, Lampros K. Michalis, Katerina K. Naka, Danilo Neglia, Silvia Rocchiccioli, Gualtiero Pelosi, Dimitrios I. Fotiadis and Antonis Sakellarios

Diagnostics 2022, 12(6), 1466; https://doi.org/10.3390/diagnostics12061466 - 14 Jun 2022

Cited by 2 | Viewed by 2077

Abstract

The prediction of obstructive atherosclerotic disease has significant clinical meaning for the decision making. In this study, a machine learning predictive model based on gradient boosting classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD [...] Read more.

The prediction of obstructive atherosclerotic disease has significant clinical meaning for the decision making. In this study, a machine learning predictive model based on gradient boosting classifier is presented, aiming to identify the patients of high CAD risk and those of low CAD risk. The machine learning methodology includes five steps: the preprocessing of the input data, the class imbalance handling applying the Easy Ensemble algorithm, the recursive feature elimination technique implementation, the implementation of gradient boosting classifier, and finally the model evaluation, while the fine tuning of the presented model was implemented through a randomized search optimization of the model’s hyper-parameters over an internal 3-fold cross-validation. In total, 187 participants with suspicion of CAD previously underwent CTCA during EVINCI and ARTreat clinical studies and were prospectively included to undergo follow-up CTCA. The predictive model was trained using imaging data (geometrical and blood flow based) and non-imaging data. The overall predictive accuracy of the model was 0.81, using both imaging and non-imaging data. The innovative aspect of the proposed study is the combination of imaging-based data with the typical CAD risk factors to provide an integrated CAD risk-predictive model. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 1758 KiB  

Open AccessArticle

Transfer Learning Analysis for Subvisible Particle Flow Imaging of Pharmaceutical Formulations

by Xiangan Long, Chongjun Ma, Han Sheng, Liwen Chen, Yiyan Fei, Lan Mi, Dongmei Han and Jiong Ma

Appl. Sci. 2022, 12(12), 5843; https://doi.org/10.3390/app12125843 - 08 Jun 2022

Cited by 8 | Viewed by 2043

Abstract

Subvisible particles are an ongoing problem in biotherapeutic injectable pharmaceutical formulations, and their identification is an important prerequisite for tracing them back to their source and optimizing the process. Flow imaging microscopy (FIM) is a favored imaging technique, mainly because of its ability [...] Read more.

Subvisible particles are an ongoing problem in biotherapeutic injectable pharmaceutical formulations, and their identification is an important prerequisite for tracing them back to their source and optimizing the process. Flow imaging microscopy (FIM) is a favored imaging technique, mainly because of its ability to achieve rapid batch imaging of subvisible particles in solution with excellent imaging quality. This study used VGG16 after transfer learning to identify subvisible particle images acquired using FlowCam. We manually prepared standards for seven classes of particles, acquired the image information through FlowCam, and fed the images over 5 µm into VGG16 consisting of a convolutional base of VGG16 pre-trained with ImageNet data and a custom classifier for training. An accuracy of 97.51% was obtained for the test set data. The study also demonstrated that the recognition method using transfer learning outperforms machine learning methods based on morphological parameters in terms of accuracy, and has a significant training speed advantage over scratch-trained CNN. The combination of transfer learning and FIM images is expected to provide a general and accurate data-analysis method for identifying subvisible particles. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 713 KiB)

18 pages, 3711 KiB  

Open AccessArticle

Predicting CT-Based Coronary Artery Disease Using Vascular Biomarkers Derived from Fundus Photographs with a Graph Convolutional Neural Network

by Fan Huang, Jie Lian, Kei-Shing Ng, Kendrick Shih and Varut Vardhanabhuti

Diagnostics 2022, 12(6), 1390; https://doi.org/10.3390/diagnostics12061390 - 04 Jun 2022

Cited by 6 | Viewed by 2162

Abstract

The study population contains 145 patients who were prospectively recruited for coronary CT angiography (CCTA) and fundoscopy. This study first examined the association between retinal vascular changes and the Coronary Artery Disease Reporting and Data System (CAD-RADS) as assessed on CCTA. Then, we [...] Read more.

The study population contains 145 patients who were prospectively recruited for coronary CT angiography (CCTA) and fundoscopy. This study first examined the association between retinal vascular changes and the Coronary Artery Disease Reporting and Data System (CAD-RADS) as assessed on CCTA. Then, we developed a graph neural network (GNN) model for predicting the CAD-RADS as a proxy for coronary artery disease. The CCTA scans were stratified by CAD-RADS scores by expert readers, and the vascular biomarkers were extracted from their fundus images. Association analyses of CAD-RADS scores were performed with patient characteristics, retinal diseases, and quantitative vascular biomarkers. Finally, a GNN model was constructed for the task of predicting the CAD-RADS score compared to traditional machine learning (ML) models. The experimental results showed that a few retinal vascular biomarkers were significantly associated with adverse CAD-RADS scores, which were mainly pertaining to arterial width, arterial angle, venous angle, and fractal dimensions. Additionally, the GNN model achieved a sensitivity, specificity, accuracy and area under the curve of 0.711, 0.697, 0.704 and 0.739, respectively. This performance outperformed the same evaluation metrics obtained from the traditional ML models (p < 0.05). The data suggested that retinal vasculature could be a potential biomarker for atherosclerosis in the coronary artery and that the GNN model could be utilized for accurate prediction. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

23 pages, 40786 KiB  

Open AccessArticle

Classifying Breast Density from Mammogram with Pretrained CNNs and Weighted Average Ensembles

by Eman Justaniah, Ghadah Aldabbagh, Areej Alhothali and Nesreen Abourokbah

Appl. Sci. 2022, 12(11), 5599; https://doi.org/10.3390/app12115599 - 31 May 2022

Cited by 2 | Viewed by 2520

Abstract

We are currently experiencing a revolution in data production and artificial intelligence (AI) applications. Data are produced much faster than they can be consumed. Thus, there is an urgent need to develop AI algorithms for all aspects of modern life. Furthermore, the medical [...] Read more.

We are currently experiencing a revolution in data production and artificial intelligence (AI) applications. Data are produced much faster than they can be consumed. Thus, there is an urgent need to develop AI algorithms for all aspects of modern life. Furthermore, the medical field is a fertile field in which to apply AI techniques. Breast cancer is one of the most common cancers and a leading cause of death around the world. Early detection is critical to treating the disease effectively. Breast density plays a significant role in determining the likelihood and risk of breast cancer. Breast density describes the amount of fibrous and glandular tissue compared with the amount of fatty tissue in the breast. Breast density is categorized using a system called the ACR BI-RADS. The ACR assigns breast density to one of four classes. In class A, breasts are almost entirely fatty. In class B, scattered areas of fibroglandular density appear in the breasts. In class C, the breasts are heterogeneously dense. In class D, the breasts are extremely dense. This paper applies pre-trained Convolutional Neural Network (CNN) on a local mammogram dataset to classify breast density. Several transfer learning models were tested on a dataset consisting of more than 800 mammogram screenings from King Abdulaziz Medical City (KAMC). Inception V3, EfficientNet 2B0, and Xception gave the highest accuracy for both four- and two-class classification. To enhance the accuracy of density classification, we applied weighted average ensembles, and performance was visibly improved. The overall accuracy of ACR classification with weighted average ensembles was 78.11%. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

19 pages, 2484 KiB  

Open AccessArticle

Exploring Usability and Patient Attitude towards a Smart Hospital Service with the Technology Acceptance Model

by Jui-Che Tu, Shi Chen Luo, Yi-Lin Lee, Ming-Feng Shih and Shu-Ping Chiu

Int. J. Environ. Res. Public Health 2022, 19(10), 6059; https://doi.org/10.3390/ijerph19106059 - 16 May 2022

Cited by 4 | Viewed by 2614

Abstract

The demand for health care has increased with the development of global technology and the rise of public health awareness, and smart service systems have also been introduced to medical care to relieve the pressure on hospital staff. However, the survey found that [...] Read more.

The demand for health care has increased with the development of global technology and the rise of public health awareness, and smart service systems have also been introduced to medical care to relieve the pressure on hospital staff. However, the survey found that patients’ willingness to use smart services at the time of consultation has not improved. The main research purpose of this study was to understand the willingness of patients from various groups to use smart medical service systems and to explore the influencing factors on patients’ use of smart service systems in hospitals through the technology acceptance model. This study distributed questionnaires in the outpatient area of National Taiwan University Hospital Yunlin Branch, and a total of 202 valid questionnaires were obtained. After related research and regression analysis, it was found that patients paid more attention to the benefits and convenience brought by smart services. If patients believed that smart services were trustworthy and beneficial to themselves, their usage intention and attitude would be positive. The results of this study are summarized by the following four points: (1) Designed according to the cultural conditions of different regions; (2) think about design from the patient’s perspective; (3) strengthen the explanation and promotion of smart services; and (4) add humanized care and design. This study could be used as a reference for hospitals to improve their service quality and systems in the future. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

20 pages, 2057 KiB  

Open AccessArticle

Construction of Talent Competency Model for Senior Care Professionals in Intelligent Institutions

by Yu Song, Dongphil Chun, Peng Xiong and Xinyuan Wang

Healthcare 2022, 10(5), 914; https://doi.org/10.3390/healthcare10050914 - 13 May 2022

Cited by 3 | Viewed by 2259

Abstract

As the problem of the aging population becomes more and more serious, building an intelligent senior care service model and optimizing the senior care service industry become key to the development of the senior care service industry. The key to developing intelligent senior [...] Read more.

As the problem of the aging population becomes more and more serious, building an intelligent senior care service model and optimizing the senior care service industry become key to the development of the senior care service industry. The key to developing intelligent senior care services is to improve the overall senior care personnel quality and construct a competency model of intelligent institutional senior care professionals. This study used literature research and interviews to establish 31 relevant institutional senior care professional talent competency elements. We proposed six research propositions, prepared questionnaires for empirical analysis, and took caregivers of senior care institutions implementing intelligent management in some cities in Hebei Province, China as samples. This study established and validated 28 competency quality index models of senior care professionals in intelligent institutions in four dimensions: nursing knowledge, professional ability, personal quality, and professional attitude through exploratory factor analysis and confirmatory factor analysis. Based on the index system, this study suggests three aspects: improving the talent recruitment and selection mechanism, talent training and development mechanism, and assessment and incentive mechanism. The traditional talent competency model only focuses on fundamental aspects, such as competence. This study comprehensively establishes an evaluation model from four aspects, providing theoretical and practical significance for selecting and developing talents in intelligent institutions. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 2579 KiB  

Open AccessArticle

Cluster-Based Ensemble Learning Model for Aortic Dissection Screening

by Yan Gao, Min Wang, Guogang Zhang, Lingjun Zhou, Jingming Luo and Lijue Liu

Int. J. Environ. Res. Public Health 2022, 19(9), 5657; https://doi.org/10.3390/ijerph19095657 - 06 May 2022

Cited by 1 | Viewed by 1510

Abstract

Aortic dissection (AD) is a rare and high-risk cardiovascular disease with high mortality. Due to its complex and changeable clinical manifestations, it is easily missed or misdiagnosed. In this paper, we proposed an ensemble learning model based on clustering: Cluster Random under-sampling Smote–Tomek [...] Read more.

Aortic dissection (AD) is a rare and high-risk cardiovascular disease with high mortality. Due to its complex and changeable clinical manifestations, it is easily missed or misdiagnosed. In this paper, we proposed an ensemble learning model based on clustering: Cluster Random under-sampling Smote–Tomek Bagging (CRST-Bagging) to help clinicians screen for AD patients in the early phase to save their lives. In this model, we propose the CRST method, which combines the advantages of Kmeans++ and the Smote–Tomek sampling method, to overcome an extremely imbalanced AD dataset. Then we used the Bagging algorithm to predict the AD patients. We collected AD patients’ and other cardiovascular patients’ routine examination data from Xiangya Hospital to build the AD dataset. The effectiveness of the CRST method in resampling was verified by experiments on the original AD dataset. Our model was compared with RUSBoost and SMOTEBagging on the original dataset and a test dataset. The results show that our model performed better. On the test dataset, our model’s precision and recall rates were 83.6% and 80.7%, respectively. Our model’s F1-score was 82.1%, which is 4.8% and 1.6% higher than that of RUSBoost and SMOTEBagging, which demonstrates our model’s effectiveness in AD screening. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

26 pages, 4306 KiB  

Open AccessArticle

Investigating the Performance of FixMatch for COVID-19 Detection in Chest X-rays

by Ali Reza Sajun, Imran Zualkernan and Donthi Sankalpa

Appl. Sci. 2022, 12(9), 4694; https://doi.org/10.3390/app12094694 - 06 May 2022

Cited by 5 | Viewed by 1929

Abstract

The advent of the COVID-19 pandemic has resulted in medical resources being stretched to their limits. Chest X-rays are one method of diagnosing COVID-19; they are used due to their high efficacy. However, detecting COVID-19 manually by using these images is time-consuming and [...] Read more.

The advent of the COVID-19 pandemic has resulted in medical resources being stretched to their limits. Chest X-rays are one method of diagnosing COVID-19; they are used due to their high efficacy. However, detecting COVID-19 manually by using these images is time-consuming and expensive. While neural networks can be trained to detect COVID-19, doing so requires large amounts of labeled data, which are expensive to collect and code. One approach is to use semi-supervised neural networks to detect COVID-19 based on a very small number of labeled images. This paper explores how well such an approach could work. The FixMatch algorithm, which is a state-of-the-art semi-supervised classification algorithm, was trained on chest X-rays to detect COVID-19, Viral Pneumonia, Bacterial Pneumonia and Lung Opacity. The model was trained with decreasing levels of labeled data and compared with the best supervised CNN models, using transfer learning. FixMatch was able to achieve a COVID F1-score of 0.94 with only 80 labeled samples per class and an overall macro-average F1-score of 0.68 with only 20 labeled samples per class. Furthermore, an exploratory analysis was conducted to determine the performance of FixMatch to detect COVID-19 when trained with imbalanced data. The results show a predictable drop in performance as compared to training with uniform data; however, a statistical analysis suggests that FixMatch may be somewhat robust to data imbalance, as in many cases, and the same types of mistakes are made when the amount of labeled data is decreased. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 4510 KiB  

Open AccessArticle

Earth Mover’s Distance-Based Tool for Rapid Screening of Cervical Cancer Using Cervigrams

by Kumar Dron Shrivastav, Priyadarshini Arambam, Shelly Batra, Vandana Bhatia, Harpreet Singh, Vinita Kumar Jaggi, Priya Ranjan, Eyad H. Abed and Rajiv Janardhanan

Appl. Sci. 2022, 12(9), 4661; https://doi.org/10.3390/app12094661 - 06 May 2022

Cited by 4 | Viewed by 2914

Abstract

Cervical cancer is a major public health challenge that can be cured with early diagnosis and timely treatment. This challenge formed the rationale behind our design and development of an intelligent and robust image analysis and diagnostic tool/scale, namely “OM—The OncoMeter”, for which [...] Read more.

Cervical cancer is a major public health challenge that can be cured with early diagnosis and timely treatment. This challenge formed the rationale behind our design and development of an intelligent and robust image analysis and diagnostic tool/scale, namely “OM—The OncoMeter”, for which we used R (version-3.6.3) and Linux (Ubuntu-20.04) to tag and triage patients in order of their disease severity. The socio-demographic profiles and cervigrams of 398 patients evaluated at OPDs of Batra Hospital & Medical Research Centre, New Delhi, India, and Delhi State Cancer Institute (East), New Delhi, India, were acquired during the course of this study. Tested on 398 India-specific women’s cervigrams, the scale yielded significant achievements, with 80.15% accuracy, a sensitivity of 84.79%, and a specificity of 66.66%. The statistical analysis of sociodemographic profiles showed significant associations of age, education, annual income, occupation, and menstrual health with the health of the cervix, where a p-value less than (<) 0.05 was considered statistically significant. The deployment of cervical cancer screening tools such as “OM—The OncoMeter” in live clinical settings of resource-limited healthcare infrastructure will facilitate early diagnosis in a non-invasive manner, leading to a timely clinical intervention for infected patients upon detection even during primary healthcare (PHC). Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

15 pages, 4161 KiB  

Open AccessArticle

CAttSleepNet: Automatic End-to-End Sleep Staging Using Attention-Based Deep Neural Networks on Single-Channel EEG

by Tingting Li, Bofeng Zhang, Hehe Lv, Shengxiang Hu, Zhikang Xu and Yierxiati Tuergong

Int. J. Environ. Res. Public Health 2022, 19(9), 5199; https://doi.org/10.3390/ijerph19095199 - 25 Apr 2022

Cited by 9 | Viewed by 2156

Abstract

Accurate sleep staging results can be used to measure sleep quality, providing a reliable basis for the prevention and diagnosis of sleep-related diseases. The key to sleep staging is the feature representation of EEG signals. Existing approaches rarely consider local features in feature [...] Read more.

Accurate sleep staging results can be used to measure sleep quality, providing a reliable basis for the prevention and diagnosis of sleep-related diseases. The key to sleep staging is the feature representation of EEG signals. Existing approaches rarely consider local features in feature extraction, and fail to distinguish the importance of critical and non-critical local features. We propose an innovative model for automatic sleep staging with single-channel EEG, named CAttSleepNet. We add an attention module to the convolutional neural network (CNN) that can learn the weights of local sequences of EEG signals by exploiting intra-epoch contextual information. Then, a two-layer bidirectional-Long Short-Term Memory (Bi-LSTM) is used to encode the global correlations of successive epochs. Therefore, the feature representations of EEG signals are enhanced by both local and global context correlation. Experimental results achieved on two real-world sleep datasets indicate that the CAttSleepNet model outperforms existing models. Moreover, ablation experiments demonstrate the validity of our proposed attention module. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

23 pages, 2346 KiB  

Open AccessArticle

Pneumonia Recognition by Deep Learning: A Comparative Investigation

by Yuting Yang and Gang Mei

Appl. Sci. 2022, 12(9), 4334; https://doi.org/10.3390/app12094334 - 25 Apr 2022

Cited by 5 | Viewed by 1730

Abstract

Pneumonia is a common infectious disease. Currently, the most common method of pneumonia identification is manual diagnosis by professional doctors, but the accuracy and identification efficiency of this method is not satisfactory, and computer-aided diagnosis technology has emerged. With the development of artificial [...] Read more.

Pneumonia is a common infectious disease. Currently, the most common method of pneumonia identification is manual diagnosis by professional doctors, but the accuracy and identification efficiency of this method is not satisfactory, and computer-aided diagnosis technology has emerged. With the development of artificial intelligence, deep learning has also been applied to pneumonia diagnosis and can achieve high accuracy. In this paper, we compare five deep learning models in different situations for pneumonia recognition. The objective was to employ five deep learning models to identify pneumonia X-ray images and to compare and analyze them in different cases, thus screening out the optimal model for each type of case to improve the efficiency of pneumonia recognition and further apply it to the computer-aided diagnosis of pneumonia species. In the proposed framework: (1) datasets are collected and processed, (2) five deep learning models for pneumonia recognition are built, (3) the five models are compared, and the optimal model for each case is selected. The results show that the LeNet5 and AlexNet models achieved better pneumonia recognition for small datasets, while the MobileNet and ResNet18 models were more suitable for pneumonia recognition for large datasets. The comparative analysis of each model under different situations can provide a deeper understanding of the efficiency of each model in identifying pneumonia, thus making the practical application and selection of deep learning models for pneumonia recognition more convenient. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 1912 KiB  

Open AccessArticle

Detection of Sleep Apnea from Electrocardiogram and Pulse Oximetry Signals Using Random Forest

by Jianming Zhu, Aojie Zhou, Qiong Gong, Yu Zhou, Junxiang Huang and Zhencheng Chen

Appl. Sci. 2022, 12(9), 4218; https://doi.org/10.3390/app12094218 - 22 Apr 2022

Cited by 10 | Viewed by 3463

Abstract

Sleep apnea (SA) is a common sleep disorder which could impair the human physiological system. Therefore, early diagnosis of SA is of great interest. The traditional method of diagnosing SA is an overnight polysomnography (PSG) evaluation. When PSG has limited availability, automatic SA [...] Read more.

Sleep apnea (SA) is a common sleep disorder which could impair the human physiological system. Therefore, early diagnosis of SA is of great interest. The traditional method of diagnosing SA is an overnight polysomnography (PSG) evaluation. When PSG has limited availability, automatic SA screening with a fewer number of signals should be considered. The primary purpose of this study is to develop and evaluate a SA detection model based on electrocardiogram (ECG) and blood oxygen saturation (SpO2). We adopted a multimodal approach to fuse ECG and SpO2 signals at the feature level. Then, feature selection was conducted using the recursive feature elimination with cross-validation (RFECV) algorithm and random forest (RF) classifier used to discriminate between apnea and normal events. Experiments were conducted on the Apnea-ECG database. The introduced algorithm obtained an accuracy of 97.5%, a sensitivity of 95.9%, a specificity of 98.4% and an AUC of 0.992 in per-segment classification, and outperformed previous works. The results showed that ECG and SpO2 are complementary in detecting SA, and that the combination of ECG and SpO2 enhances the ability to diagnose SA. Therefore, the proposed method has the potential to be an alternative to conventional detection methods. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

16 pages, 4502 KiB  

Open AccessArticle

Identification of Smartwatch-Collected Lifelog Variables Affecting Body Mass Index in Middle-Aged People Using Regression Machine Learning Algorithms and SHapley Additive Explanations

by Jiyong Kim, Jiyoung Lee and Minseo Park

Appl. Sci. 2022, 12(8), 3819; https://doi.org/10.3390/app12083819 - 10 Apr 2022

Cited by 8 | Viewed by 2224

Abstract

Body mass index (BMI) plays a vital role in determining the health of middle-aged people, and a high BMI is associated with various chronic diseases. This study aims to identify important lifelog factors related to BMI. The sleep, gait, and body data of [...] Read more.

Body mass index (BMI) plays a vital role in determining the health of middle-aged people, and a high BMI is associated with various chronic diseases. This study aims to identify important lifelog factors related to BMI. The sleep, gait, and body data of 47 middle-aged women and 71 middle-aged men were collected using smartwatches. Variables were derived to examine the relationships between these factors and BMI. The data were divided into groups according to height based on the definition of BMI as the most influential variable. The data were analyzed using regression and tree-based models: Ridge Regression, eXtreme Gradient Boosting (XGBoost), and Category Boosting (CatBoost). Moreover, the importance of the BMI variables was visualized and examined using the SHapley Additive Explanations Technique (SHAP). The results showed that total sleep time, average morning gait speed, and sleep efficiency significantly affected BMI. However, the variables with the most substantial effects differed among the height groups. This indicates that the factors most profoundly affecting BMI differ according to body characteristics, suggesting the possibility of developing efficient methods for personalized healthcare. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

16 pages, 2077 KiB  

Open AccessArticle

Optimal Disease Diagnosis in Internet of Things (IoT) Based Healthcare System Using Energy Efficient Clustering

by Majid Alotaibi and Saud S. Alotaibi

Appl. Sci. 2022, 12(8), 3804; https://doi.org/10.3390/app12083804 - 09 Apr 2022

Cited by 2 | Viewed by 1545

Abstract

This paper aims to introduce a novel approach that includes three steps, namely Energy efficient clustering, Disease diagnosis, and an Alert system. Initially, energy-efficient clustering of nodes was conducted, and to render the clustering more optimal, its centroid was optimally selected by a [...] Read more.

This paper aims to introduce a novel approach that includes three steps, namely Energy efficient clustering, Disease diagnosis, and an Alert system. Initially, energy-efficient clustering of nodes was conducted, and to render the clustering more optimal, its centroid was optimally selected by a new hybrid algorithm. In addition, this cluster formation was conducted based on constraints such as distance and energy. Further, the disease diagnosis in IoT was performed under two phases namely, “feature extraction and classification”. During feature extraction, the statistical and higher-order features were extracted. These extracted features were then classified via Optimized Deep Convolutional Neural Network (DCNN). To make the classification more precise, the weights of the DCNN were optimally tuned by a new hybrid algorithm referred to as Hybrid Elephant and Moth Flame with Adaptive Learning (HEM-AL). Finally, an alert system was enabled via proposed severity level estimation, which determined the severity of the disease, suggesting patients to visit the hospital. Lastly, the supremacy of the developed approach was examined via evaluation over the other extant techniques. Accordingly, the proposed model attained an accuracy of 0.99 for test case 1, and was 7.41%, 17.34%, and 13.41% better than traditional NN, CNN, and DCNN models. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

19 pages, 2670 KiB  

Open AccessArticle

Boamente: A Natural Language Processing-Based Digital Phenotyping Tool for Smart Monitoring of Suicidal Ideation

by Evandro J. S. Diniz, José E. Fontenele, Adonias C. de Oliveira, Victor H. Bastos, Silmar Teixeira, Ricardo L. Rabêlo, Dario B. Calçada, Renato M. dos Santos, Ana K. de Oliveira and Ariel S. Teles

Healthcare 2022, 10(4), 698; https://doi.org/10.3390/healthcare10040698 - 08 Apr 2022

Cited by 12 | Viewed by 3993

Abstract

People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason, suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be monitored in a manner capable of identifying if and when [...] Read more.

People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason, suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be monitored in a manner capable of identifying if and when they have a suicidal ideation, enabling professionals to perform timely interventions. This study aimed to develop the Boamente tool, a solution that collects textual data from users’ smartphones and identifies the existence of suicidal ideation. The solution has a virtual keyboard mobile application that passively collects user texts and sends them to a web platform to be processed. The platform classifies texts using natural language processing and a deep learning model to recognize suicidal ideation, and the results are presented to mental health professionals in dashboards. Text classification for sentiment analysis was implemented with different machine/deep learning algorithms. A validation study was conducted to identify the model with the best performance results. The BERTimbau Large model performed better, reaching a recall of 0.953 (accuracy: 0.955; precision: 0.961; F-score: 0.954; AUC: 0.954). The proposed tool demonstrated an ability to identify suicidal ideation from user texts, which enabled it to be experimented with in studies with professionals and their patients. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 3146 KiB  

Open AccessArticle

Deep Learning Algorithm for Heart Valve Diseases Assisted Diagnosis

by Santiago Isaac Flores-Alonso, Blanca Tovar-Corona and René Luna-García

Appl. Sci. 2022, 12(8), 3780; https://doi.org/10.3390/app12083780 - 08 Apr 2022

Cited by 6 | Viewed by 1764

Abstract

Heart sounds are mainly the expressions of the opening and closing of the heart valves. Some sounds are produced by the interruption of laminar blood flow as it turns into turbulent flow, which is explained by abnormal functioning of the valves. The analysis [...] Read more.

Heart sounds are mainly the expressions of the opening and closing of the heart valves. Some sounds are produced by the interruption of laminar blood flow as it turns into turbulent flow, which is explained by abnormal functioning of the valves. The analysis of the phonocardiographic signals has made it possible to indicate that the normal and pathological records differ from each other concerning both temporal and spectral features. The present work describes the design and implementation based on deep neural networks and deep learning for the binary and multiclass classification of four common valvular pathologies and normal heart sounds. For feature extraction, three different techniques were considered: Discrete Wavelet Transform, Continuous Wavelet Transform and Mel Frequency Cepstral Coefficients. The performance of both approaches reached F1 scores higher than 98% and specificities in the “Normal” class of up to 99%, which considers the cases that can be misclassified as normal. These results place the present work as a highly competitive proposal for the generation of systems for assisted diagnosis. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 3724 KiB)

19 pages, 3920 KiB  

Open AccessArticle

Deep Learning Applied to Chest Radiograph Classification—A COVID-19 Pneumonia Experience

by Adhvan Furtado, Leandro Andrade, Diego Frias, Thiago Maia, Roberto Badaró and Erick G. Sperandio Nascimento

Appl. Sci. 2022, 12(8), 3712; https://doi.org/10.3390/app12083712 - 07 Apr 2022

Cited by 7 | Viewed by 2539

Abstract

Due to the recent COVID-19 pandemic, a large number of reports present deep learning algorithms that support the detection of pneumonia caused by COVID-19 in chest radiographs. Few studies have provided the complete source code, limiting testing and reproducibility on different datasets. This [...] Read more.

Due to the recent COVID-19 pandemic, a large number of reports present deep learning algorithms that support the detection of pneumonia caused by COVID-19 in chest radiographs. Few studies have provided the complete source code, limiting testing and reproducibility on different datasets. This work presents Cimatec_XCOV19, a novel deep learning system inspired by the Inception-V3 architecture that is able to (i) support the identification of abnormal chest radiographs and (ii) classify the abnormal radiographs as suggestive of COVID-19. The training dataset has 44,031 images with 2917 COVID-19 cases, one of the largest datasets in recent literature. We organized and published an external validation dataset of 1158 chest radiographs from a Brazilian hospital. Two experienced radiologists independently evaluated the radiographs. The Cimatec_XCOV19 algorithm obtained a sensitivity of 0.85, specificity of 0.82, and AUC ROC of 0.93. We compared the AUC ROC of our algorithm with a well-known public solution and did not find a statistically relevant difference between both performances. We provide full access to the code and the test dataset, enabling this work to be used as a tool for supporting the fast screening of COVID-19 on chest X-ray exams, serving as a reference for educators, and supporting further algorithm enhancements. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Graphical abstract

22 pages, 668 KiB  

Open AccessReview

A Literature Review on the Use of Artificial Intelligence for the Diagnosis of COVID-19 on CT and Chest X-ray

by Ciara Mulrenan, Kawal Rhode and Barbara Malene Fischer

Diagnostics 2022, 12(4), 869; https://doi.org/10.3390/diagnostics12040869 - 31 Mar 2022

Cited by 11 | Viewed by 3214

Abstract

A COVID-19 diagnosis is primarily determined by RT-PCR or rapid lateral-flow testing, although chest imaging has been shown to detect manifestations of the virus. This article reviews the role of imaging (CT and X-ray), in the diagnosis of COVID-19, focusing on the published [...] Read more.

A COVID-19 diagnosis is primarily determined by RT-PCR or rapid lateral-flow testing, although chest imaging has been shown to detect manifestations of the virus. This article reviews the role of imaging (CT and X-ray), in the diagnosis of COVID-19, focusing on the published studies that have applied artificial intelligence with the purpose of detecting COVID-19 or reaching a differential diagnosis between various respiratory infections. In this study, ArXiv, MedRxiv, PubMed, and Google Scholar were searched for studies using the criteria terms ‘deep learning’, ‘artificial intelligence’, ‘medical imaging’, ‘COVID-19’ and ‘SARS-CoV-2’. The identified studies were assessed using a modified version of the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). Twenty studies fulfilled the inclusion criteria for this review. Out of those selected, 11 papers evaluated the use of artificial intelligence (AI) for chest X-ray and 12 for CT. The size of datasets ranged from 239 to 19,250 images, with sensitivities, specificities and AUCs ranging from 0.789–1.00, 0.843–1.00 and 0.850–1.00. While AI demonstrates excellent diagnostic potential, broader application of this method is hindered by the lack of relevant comparators in studies, sufficiently sized datasets, and independent testing. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

13 pages, 1515 KiB  

Open AccessArticle

Machine Learning-Based Pressure Ulcer Prediction in Modular Critical Care Data

by Petr Šín, Alica Hokynková, Nováková Marie, Pokorná Andrea, Rostislav Krč and Jan Podroužek

Diagnostics 2022, 12(4), 850; https://doi.org/10.3390/diagnostics12040850 - 30 Mar 2022

Cited by 17 | Viewed by 3191

Abstract

Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper [...] Read more.

Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper to pressure ulcer prediction in modular critical care data. An inherent property of many health-related datasets is a high number of irregularly sampled time-variant and scarcely populated features, often exceeding the number of observations. Although machine learning methods are known to work well under such circumstances, many choices regarding model and data processing exist. In particular, this paper address both theoretical and practical aspects related to the application of six classification models to pressure ulcers, while utilizing one of the largest available Medical Information Mart for Intensive Care (MIMIC-IV) databases. Random forest, with an accuracy of 96%, is the best-performing approach among the considered machine learning algorithms. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 5870 KiB  

Open AccessArticle

Liver Tumor Localization Based on YOLOv3 and 3D-Semantic Segmentation Using Deep Neural Networks

by Javaria Amin, Muhammad Almas Anjum, Muhammad Sharif, Seifedine Kadry, Ahmed Nadeem and Sheikh F. Ahmad

Diagnostics 2022, 12(4), 823; https://doi.org/10.3390/diagnostics12040823 - 27 Mar 2022

Cited by 15 | Viewed by 3169

Abstract

Worldwide, more than 1.5 million deaths are occur due to liver cancer every year. The use of computed tomography (CT) for early detection of liver cancer could save millions of lives per year. There is also an urgent need for a computerized method [...] Read more.

Worldwide, more than 1.5 million deaths are occur due to liver cancer every year. The use of computed tomography (CT) for early detection of liver cancer could save millions of lives per year. There is also an urgent need for a computerized method to interpret, detect and analyze CT scans reliably, easily, and correctly. However, precise segmentation of minute tumors is a difficult task because of variation in the shape, intensity, size, low contrast of the tumor, and the adjacent tissues of the liver. To address these concerns, a model comprised of three parts: synthetic image generation, localization, and segmentation, is proposed. An optimized generative adversarial network (GAN) is utilized for generation of synthetic images. The generated images are localized by using the improved localization model, in which deep features are extracted from pre-trained Resnet-50 models and fed into a YOLOv3 detector as an input. The proposed modified model localizes and classifies the minute liver tumor with 0.99 mean average precision (mAp). The third part is segmentation, in which pre-trained Inceptionresnetv2 employed as a base-Network of Deeplabv3 and subsequently is trained on fine-tuned parameters with annotated ground masks. The experiments reflect that the proposed approach has achieved greater than 95% accuracy in the testing phase and it is proven that, in comparison to the recently published work in this domain, this research has localized and segmented the liver and minute liver tumor with more accuracy. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

12 pages, 2175 KiB  

Open AccessArticle

Deep Learning–Based Brain Computed Tomography Image Classification with Hyperparameter Optimization through Transfer Learning for Stroke

by Yung-Ting Chen, Yao-Liang Chen, Yi-Yun Chen, Yu-Ting Huang, Ho-Fai Wong, Jiun-Lin Yan and Jiun-Jie Wang

Diagnostics 2022, 12(4), 807; https://doi.org/10.3390/diagnostics12040807 - 25 Mar 2022

Cited by 19 | Viewed by 3599

Abstract

Brain computed tomography (CT) is commonly used for evaluating the cerebral condition, but immediately and accurately interpreting emergent brain CT images is tedious, even for skilled neuroradiologists. Deep learning networks are commonly employed for medical image analysis because they enable efficient computer-aided diagnosis. [...] Read more.

Brain computed tomography (CT) is commonly used for evaluating the cerebral condition, but immediately and accurately interpreting emergent brain CT images is tedious, even for skilled neuroradiologists. Deep learning networks are commonly employed for medical image analysis because they enable efficient computer-aided diagnosis. This study proposed the use of convolutional neural network (CNN)-based deep learning models for efficient classification of strokes based on unenhanced brain CT image findings into normal, hemorrhage, infarction, and other categories. The included CNN models were CNN-2, VGG-16, and ResNet-50, all of which were pretrained through transfer learning with various data sizes, mini-batch sizes, and optimizers. Their performance in classifying unenhanced brain CT images was tested thereafter. This performance was then compared with the outcomes in other studies on deep learning–based hemorrhagic or ischemic stroke diagnoses. The results revealed that among our CNN-2, VGG-16, and ResNet-50 analyzed by considering several hyperparameters and environments, the CNN-2 and ResNet-50 outperformed the VGG-16, with an accuracy of 0.9872; however, ResNet-50 required a longer time to present the outcome than did the other networks. Moreover, our models performed much better than those reported previously. In conclusion, after appropriate hyperparameter optimization, our deep learning–based models can be applied to clinical scenarios where neurologist or radiologist may need to verify whether their patients have a hemorrhage stroke, an infarction, and any other symptom. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 5160 KiB  

Open AccessArticle

Lightweight Ensemble Network for Detecting Heart Disease Using ECG Signals

by Siho Shin, Mingu Kang, Gengjia Zhang, Jaehyo Jung and Youn Tae Kim

Appl. Sci. 2022, 12(7), 3291; https://doi.org/10.3390/app12073291 - 24 Mar 2022

Cited by 7 | Viewed by 2174

Abstract

Heart disease should be treated quickly when symptoms appear. Machine-learning methods for detecting heart disease require desktop computers, an obstacle that can have fatal consequences for patients who must check their health periodically. Herein, we propose a MobileNet-based ensemble algorithm for arrhythmia diagnosis [...] Read more.

Heart disease should be treated quickly when symptoms appear. Machine-learning methods for detecting heart disease require desktop computers, an obstacle that can have fatal consequences for patients who must check their health periodically. Herein, we propose a MobileNet-based ensemble algorithm for arrhythmia diagnosis that can be easily and quickly operated in a mobile environment. The electrocardiogram (ECG) signal measured over a short period of time was augmented using the matching pursuit algorithm to achieve a high accuracy. The arrhythmia data were classified through an ensemble classifier combining MobileNetV2 and BiLSTM. By classifying the data using this algorithm, an accuracy of 91.7% was achieved. The performance of the algorithm was evaluated using a confusion matrix and a receiver operating characteristic curve. The sensitivity, specificity, precision, and F1 score were 0.92, 0.91, 0.92, and 0.92, respectively. Because the proposed algorithm does not require long-term ECG signal measurement, it facilitates health management for busy people. Moreover, parameters are exchanged when learning data, enhancing the security of the system. In addition, owing to the lightweight deep-learning model, the proposed algorithm can be applied to mobile healthcare, object detection, text recognition, and authentication. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 203 KiB)

9 pages, 1003 KiB  

Open AccessArticle

Automatic Recognition of Ragged Red Fibers in Muscle Biopsy from Patients with Mitochondrial Disorders

by Jacopo Baldacci, Marco Calderisi, Chiara Fiorillo, Filippo Maria Santorelli and Anna Rubegni

Healthcare 2022, 10(3), 574; https://doi.org/10.3390/healthcare10030574 - 19 Mar 2022

Cited by 2 | Viewed by 2138

Abstract

Mitochondrial dysfunction is considered to be a major cause of primary mitochondrial myopathy in children and adults, as reduced mitochondrial respiration and morphological changes such as ragged red fibers (RRFs) are observed in muscle biopsies. However, it is also possible to hypothesize the [...] Read more.

Mitochondrial dysfunction is considered to be a major cause of primary mitochondrial myopathy in children and adults, as reduced mitochondrial respiration and morphological changes such as ragged red fibers (RRFs) are observed in muscle biopsies. However, it is also possible to hypothesize the role of mitochondrial dysfunction in aging muscle or in secondary mitochondrial dysfunctions. The recognition of true histological patterns of mitochondrial myopathy can avoid unnecessary genetic investigations. The aim of our study was to develop and validate machine-learning methods for RRF detection in light microscopy images of skeletal muscle tissue. We used image sets of 489 color images captured from representative areas of Gomori’s trichrome-stained tissue retrieved from light microscopy images at a 20× magnification. We compared the performance of random forest, gradient boosting machine, and support vector machine classifiers. Our results suggested that the advent of scanning technologies, combined with the development of machine-learning models for image classification, make neuromuscular disorders’ automated diagnostic systems a concrete possibility. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

11 pages, 3301 KiB  

Open AccessArticle

Artificial Intelligence-Enhanced Smartwatch ECG for Heart Failure-Reduced Ejection Fraction Detection by Generating 12-Lead ECG

by Joon-myoung Kwon, Yong-Yeon Jo, Soo Youn Lee, Seonmi Kang, Seon-Yu Lim, Min Sung Lee and Kyung-Hee Kim

Diagnostics 2022, 12(3), 654; https://doi.org/10.3390/diagnostics12030654 - 08 Mar 2022

Cited by 15 | Viewed by 4784

Abstract

Background: We developed and validated an artificial intelligence (AI)-enabled smartwatch ECG to detect heart failure-reduced ejection fraction (HFrEF). Methods: This was a cohort study involving two hospitals (A and B). We developed the AI in two steps. First, we developed an AI model [...] Read more.

Background: We developed and validated an artificial intelligence (AI)-enabled smartwatch ECG to detect heart failure-reduced ejection fraction (HFrEF). Methods: This was a cohort study involving two hospitals (A and B). We developed the AI in two steps. First, we developed an AI model (ECGT2T) to synthesize ten-lead ECG from the asynchronized 2-lead ECG (Lead I and II). ECGT2T is a deep learning model based on a generative adversarial network, which translates source ECGs to reference ECGs by learning styles of the reference ECGs. For this, we included adult patients aged ≥18 years from hospital A with at least one digitally stored 12-lead ECG. Second, we developed an AI model to detect HFrEF using a 10 s 12-lead ECG. The AI model was based on convolutional neural network. For this, we included adult patients who underwent ECG and echocardiography within 14 days. To validate the AI, we included adult patients from hospital B who underwent two-lead smartwatch ECG and echocardiography on the same day. The AI model generates a 10 s 12-lead ECG from a two-lead smartwatch ECG using ECGT2T and detects HFrEF using the generated 12-lead ECG. Results: We included 137,673 patients with 458,745 ECGs and 38,643 patients with 88,900 ECGs from hospital A for developing the ECGT2T and HFrEF detection models, respectively. The area under the receiver operating characteristic curve of AI for detecting HFrEF using smartwatch ECG was 0.934 (95% confidence interval 0.913–0.955) with 755 patients from hospital B. The sensitivity, specificity, positive predictive value, and negative predictive value of AI were 0.897, 0.860, 0.258, and 0.994, respectively. Conclusions: An AI-enabled smartwatch 2-lead ECG could detect HFrEF with reasonable performance. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Graphical abstract

attachment

Supplementary material:
Supplementary File 1 (ZIP, 996 KiB)

15 pages, 5192 KiB  

Open AccessArticle

An Intelligent System for Proper Management and Disposal of Unused and Expired Medications

by Haneen Banjar, Rahaf Alrowithi, Sara Alhadrami, Esraa Magrabi, Reema Munshi and Mayda Alrige

Int. J. Environ. Res. Public Health 2022, 19(5), 2875; https://doi.org/10.3390/ijerph19052875 - 01 Mar 2022

Cited by 5 | Viewed by 3124

Abstract

For years, several countries have been concerned about how to dispose of unused pharmaceuticals that can endanger human health and the environment. Moreover, some people are in desperate need of medical attention and medications, but they lack the financial resources to obtain them. [...] Read more.

For years, several countries have been concerned about how to dispose of unused pharmaceuticals that can endanger human health and the environment. Moreover, some people are in desperate need of medical attention and medications, but they lack the financial resources to obtain them. In Saudi Arabia, there are no take-back medicine programs, and there is no published research on how medications properly are disposed. The aim of this research is to use the power of artificial intelligence to assist in the proper management and disposal of expired and unused medications and to develop a prototype device for collecting medication by automatically classifying medications for proper disposal and donation. In this research, artificial intelligence technologies such as web-based expert systems, image recognition and classification algorithms, chatbots, and the internet of things are used to assist in a take-back medications program. In conclusion, the prototype design of a web-based expert system and the device reduced improper disposal risks by providing significant advice on the safe disposal of unwanted pharmaceuticals. By using an organized method of collecting expired medications, the benefits were made possible. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

21 pages, 2924 KiB  

Open AccessArticle

A Novel Pathological Voice Identification Technique through Simulated Cochlear Implant Processing Systems

by Rumana Islam, Esam Abdel-Raheem and Mohammed Tarique

Appl. Sci. 2022, 12(5), 2398; https://doi.org/10.3390/app12052398 - 25 Feb 2022

Cited by 12 | Viewed by 2309

Abstract

This paper presents a pathological voice identification system employing signal processing techniques through cochlear implant models. The fundamentals of the biological process for speech perception are investigated to develop this technique. Two cochlear implant models are considered in this work: one uses a [...] Read more.

This paper presents a pathological voice identification system employing signal processing techniques through cochlear implant models. The fundamentals of the biological process for speech perception are investigated to develop this technique. Two cochlear implant models are considered in this work: one uses a conventional bank of bandpass filters, and the other one uses a bank of optimized gammatone filters. The critical center frequencies of those filters are selected to mimic the human cochlear vibration patterns caused by audio signals. The proposed system processes the speech samples and applies a CNN for final pathological voice identification. The results show that the two proposed models adopting bandpass and gammatone filterbanks can discriminate the pathological voices from healthy ones, resulting in F1 scores of 77.6% and 78.7%, respectively, with speech samples. The obtained results of this work are also compared with those of other related published works. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

16 pages, 3868 KiB  

Open AccessArticle

Modeling COVID-19 Outbreaks in Long-Term Care Facilities Using an Agent-Based Modeling and Simulation Approach

by Ali Asgary, Hudson Blue, Adriano O. Solis, Zachary McCarthy, Mahdi Najafabadi, Mohammad Ali Tofighi and Jianhong Wu

Int. J. Environ. Res. Public Health 2022, 19(5), 2635; https://doi.org/10.3390/ijerph19052635 - 24 Feb 2022

Cited by 3 | Viewed by 1968

Abstract

The elderly, especially those individuals with pre-existing health problems, have been disproportionally at a higher risk during the COVID-19 pandemic. Residents of long-term care facilities have been gravely affected by the pandemic and resident death numbers have been far above those of the [...] Read more.

The elderly, especially those individuals with pre-existing health problems, have been disproportionally at a higher risk during the COVID-19 pandemic. Residents of long-term care facilities have been gravely affected by the pandemic and resident death numbers have been far above those of the general population. To better understand how infectious diseases such as COVID-19 can spread through long-term care facilities, we developed an agent-based simulation tool that uses a contact matrix adapted from previous infection control research in these types of facilities. This matrix accounts for the average distinct daily contacts between seven different agent types that represent the roles of individuals in long-term care facilities. The simulation results were compared to actual COVID-19 outbreaks in some of the long-term care facilities in Ontario, Canada. Our analysis shows that this simulation tool is capable of predicting the number of resident deaths after 50 days with a less than 0.1 variation in death rate. We modeled and predicted the effectiveness of infection control measures by utilizing this simulation tool. We found that to reduce the number of resident deaths, the effectiveness of personal protective equipment must be above 50%. We also found that daily random COVID-19 tests for as low as less than 10% of a long-term care facility’s population will reduce the number of resident deaths by over 75%. The results further show that combining several infection control measures will lead to more effective outcomes. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 1359 KiB  

Open AccessArticle

Auditory Property-Based Features and Artificial Neural Network Classifiers for the Automatic Detection of Low-Intensity Snoring/Breathing Episodes

by Kenji Hamabe, Takahiro Emoto, Osamu Jinnouchi, Naoki Toda and Ikuji Kawata

Appl. Sci. 2022, 12(4), 2242; https://doi.org/10.3390/app12042242 - 21 Feb 2022

Viewed by 1444

Abstract

The definitive diagnosis of obstructive sleep apnea syndrome (OSAS) is made using an overnight polysomnography (PSG) test. This test requires that a patient wears multiple measurement sensors during an overnight hospitalization. However, this setup imposes physical constraints and a heavy burden on the [...] Read more.

The definitive diagnosis of obstructive sleep apnea syndrome (OSAS) is made using an overnight polysomnography (PSG) test. This test requires that a patient wears multiple measurement sensors during an overnight hospitalization. However, this setup imposes physical constraints and a heavy burden on the patient. Recent studies have reported on another technique for conducting OSAS screening based on snoring/breathing episodes (SBEs) extracted from recorded data acquired by a noncontact microphone. However, SBEs have a high dynamic range and are barely audible at intensities >90 dB. A method is needed to detect SBEs even in low-signal-to-noise-ratio (SNR) environments. Therefore, we developed a method for the automatic detection of low-intensity SBEs using an artificial neural network (ANN). However, when considering its practical use, this method required further improvement in terms of detection accuracy and speed. To accomplish this, we propose in this study a new method to detect low SBEs based on neural activity pattern (NAP)-based cepstral coefficients (NAPCC) and ANN classifiers. Comparison results of the leave-one-out cross-validation demonstrated that our proposed method is superior to previous methods for the classification of SBEs and non-SBEs, even in low-SNR conditions (accuracy: 85.99 ± 5.69% vs. 75.64 ± 18.8%). Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 578 KiB  

Open AccessArticle

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

by Matthew Oyeleye, Tianhua Chen, Sofya Titarenko and Grigoris Antoniou

Int. J. Environ. Res. Public Health 2022, 19(4), 2417; https://doi.org/10.3390/ijerph19042417 - 19 Feb 2022

Cited by 30 | Viewed by 5708

Abstract

Heart disease, caused by low heart rate, is one of the most significant causes of mortality in the world today. Therefore, it is critical to monitor heart health by identifying the deviation in the heart rate very early, which makes it easier to [...] Read more.

Heart disease, caused by low heart rate, is one of the most significant causes of mortality in the world today. Therefore, it is critical to monitor heart health by identifying the deviation in the heart rate very early, which makes it easier to detect and manage the heart’s function irregularities at a very early stage. The fast-growing use of advanced technology such as the Internet of Things (IoT), wearable monitoring systems and artificial intelligence (AI) in the healthcare systems has continued to play a vital role in the analysis of huge amounts of health-based data for early and accurate disease detection and diagnosis for personalized treatment and prognosis evaluation. It is then important to analyze the effectiveness of using data analytics and machine learning to monitor and predict heart rates using wearable device (accelerometer)-generated data. Hence, in this study, we explored a number of powerful data-driven models including the autoregressive integrated moving average (ARIMA) model, linear regression, support vector regression (SVR), k-nearest neighbor (KNN) regressor, decision tree regressor, random forest regressor and long short-term memory (LSTM) recurrent neural network algorithm for the analysis of accelerometer data to make future HR predictions from the accelerometer’s univariant HR time-series data from healthy people. The performances of the models were evaluated under different durations. Evaluated on a very recently created data set, our experimental results demonstrate the effectiveness of using an ARIMA model with a walk-forward validation and linear regression for predicting heart rate under all durations and other models for durations longer than 1 min. The results of this study show that employing these data analytics techniques can be used to predict future HR more accurately using accelerometers. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

15 pages, 1609 KiB  

Open AccessReview

Telehealth and Artificial Intelligence Insights into Healthcare during the COVID-19 Pandemic

by Dina M. El-Sherif, Mohamed Abouzid, Mohamed Tarek Elzarif, Alhassan Ali Ahmed, Ashwag Albakri and Mohammed M. Alshehri

Healthcare 2022, 10(2), 385; https://doi.org/10.3390/healthcare10020385 - 18 Feb 2022

Cited by 46 | Viewed by 11384

Abstract

Soon after the coronavirus disease 2019 pandemic was proclaimed, digital health services were widely adopted to respond to this public health emergency, including comprehensive monitoring technologies, telehealth, creative diagnostic, and therapeutic decision-making methods. The World Health Organization suggested that artificial intelligence might be [...] Read more.

Soon after the coronavirus disease 2019 pandemic was proclaimed, digital health services were widely adopted to respond to this public health emergency, including comprehensive monitoring technologies, telehealth, creative diagnostic, and therapeutic decision-making methods. The World Health Organization suggested that artificial intelligence might be a valuable way of dealing with the crisis. Artificial intelligence is an essential technology of the fourth industrial revolution that is a critical nonmedical intervention for overcoming the present global health crisis, developing next-generation pandemic preparation, and regaining resilience. While artificial intelligence has much potential, it raises fundamental privacy, transparency, and safety concerns. This study seeks to address these issues and looks forward to an intelligent healthcare future based on best practices and lessons learned by employing telehealth and artificial intelligence during the COVID-19 pandemic. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Graphical abstract

16 pages, 2467 KiB  

Open AccessArticle

Early Prediction of Sepsis Onset Using Neural Architecture Search Based on Genetic Algorithms

by Jae Kwan Kim, Wonbin Ahn, Sangin Park, Soo-Hong Lee and Laehyun Kim

Int. J. Environ. Res. Public Health 2022, 19(4), 2349; https://doi.org/10.3390/ijerph19042349 - 18 Feb 2022

Cited by 7 | Viewed by 2228

Abstract

Sepsis is a life-threatening condition with a high mortality rate. Early prediction and treatment are the most effective strategies for increasing survival rates. This paper proposes a neural architecture search (NAS) model to predict the onset of sepsis with a low computational cost [...] Read more.

Sepsis is a life-threatening condition with a high mortality rate. Early prediction and treatment are the most effective strategies for increasing survival rates. This paper proposes a neural architecture search (NAS) model to predict the onset of sepsis with a low computational cost and high search performance by applying a genetic algorithm (GA). The proposed model shares the weights of all possible connection nodes internally within the neural network. Externally, the search cost is reduced through the weight-sharing effect between the genotypes of the GA. A predictive analysis was performed using the Medical Information Mart for Intensive Care III (MIMIC-III), a medical time-series dataset, with the primary objective of predicting sepsis onset 3 h before occurrence. In addition, experiments were conducted under various prediction times (0–12 h) for comparison. The proposed model exhibited an area under the receiver operating characteristic curve (AUROC) score of 0.94 (95% CI: 0.92–0.96) for 3 h, which is 0.31–0.26 higher than the scores obtained using the Sequential Organ Failure Assessment (SOFA), quick SOFA (qSOFA), and Simplified Acute Physiology Score (SAPS) II scoring systems. Furthermore, the proposed model exhibited a 12% improvement in the AUROC value over a simple model based on the long short-term memory neural network. Additionally, it is not only optimally searchable for sepsis onset prediction, but also outperforms conventional models that use similar predictive purposes and datasets. Notably, it is sufficiently robust to shape changes in the input data and has less structural dependence. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

19 pages, 24244 KiB  

Open AccessArticle

Investigation of Eye-Tracking Scan Path as a Biomarker for Autism Screening Using Machine Learning Algorithms

by Mujeeb Rahman Kanhirakadavath and Monica Subashini Mohan Chandran

Diagnostics 2022, 12(2), 518; https://doi.org/10.3390/diagnostics12020518 - 17 Feb 2022

Cited by 29 | Viewed by 3776

Abstract

Autism spectrum disorder is a group of disorders marked by difficulties with social skills, repetitive activities, speech, and nonverbal communication. Deficits in paying attention to, and processing, social stimuli are common for children with autism spectrum disorders. It is uncertain whether eye-tracking technologies [...] Read more.

Autism spectrum disorder is a group of disorders marked by difficulties with social skills, repetitive activities, speech, and nonverbal communication. Deficits in paying attention to, and processing, social stimuli are common for children with autism spectrum disorders. It is uncertain whether eye-tracking technologies can assist in establishing an early biomarker of autism based on the children’s atypical visual preference patterns. In this study, we used machine learning methods to test the applicability of eye-tracking data in children to aid in the early screening of autism. We looked into the effectiveness of various machine learning techniques to discover the best model for predicting autism using visualized eye-tracking scan path images. We adopted three traditional machine learning models and a deep neural network classifier to run experimental trials. This study employed a publicly available dataset of 547 graphical eye-tracking scan paths from 328 typically developing and 219 autistic children. We used image augmentation to populate the dataset to prevent the model from overfitting. The deep neural network model outperformed typical machine learning approaches on the populated dataset, with 97% AUC, 93.28% sensitivity, 91.38% specificity, 94.46% NPV, and 90.06% PPV (fivefold cross-validated). The findings strongly suggest that eye-tracking data help clinicians for a quick and reliable autism screening. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Graphical abstract

attachment

Supplementary material:
Supplementary File 1 (ZIP, 679 KiB)

14 pages, 16943 KiB  

Open AccessArticle

MRI-Based Radiomics Analysis for Intraoperative Risk Assessment in Gravid Patients at High Risk with Placenta Accreta Spectrum

by Caiting Chu, Ming Liu, Yuzhen Zhang, Shuhui Zhao, Yaqiong Ge, Wenhua Li and Chengjin Gao

Diagnostics 2022, 12(2), 485; https://doi.org/10.3390/diagnostics12020485 - 14 Feb 2022

Cited by 6 | Viewed by 1882

Abstract

Background: Gravid patients at high risk with placenta accreta spectrum (PAS) face life-threatening risk at delivery. Intraoperative risk assessment for patients is currently insufficient. We aimed to develop an assessment system of intraoperative risks through MRI-based radiomics. Methods: A total of 131 patients [...] Read more.

Background: Gravid patients at high risk with placenta accreta spectrum (PAS) face life-threatening risk at delivery. Intraoperative risk assessment for patients is currently insufficient. We aimed to develop an assessment system of intraoperative risks through MRI-based radiomics. Methods: A total of 131 patients enrolled were randomly grouped according to a ratio of 7:3. Clinical data were analyzed retrospectively. Radiomic features were extracted from sagittal Fast Imaging Employing State-sate Acquisition images. Univariate and multivariate regression analyses were performed to build models using R software. A receiver operating characteristic curve and decision curve analysis (DCA) were performed to determine the predictive performance of models. Results: Six radiomic features and two clinical variables were used to construct the combined model for selection of removal protocols of the placenta, with an area under the curve (AUC) of 0.90 and 0.91 in the training and test cohorts, respectively. Nine radiomic features and two clinical variables were obtained to establish the combined model for prediction of intraoperative blood loss, with an AUC of 0.90 and 0.88 in the both cohorts, respectively. The DCA confirmed the clinical utility of the combined model. Conclusion: The analysis of combined MRI-based radiomics with clinics could be clinically beneficial for patients. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

11 pages, 4959 KiB  

Open AccessArticle

Design and Application of Secret Codes for Learning Medical Data

by Dongsik Jo and Jin-Ho Chung

Appl. Sci. 2022, 12(3), 1709; https://doi.org/10.3390/app12031709 - 07 Feb 2022

Viewed by 1221

Abstract

In distributed learning for data requiring privacy preservation, such as medical data, the distribution of secret information is an important problem. In this paper, we propose a framework for secret codes in application to distributed systems. Then, we provide new methods to construct [...] Read more.

In distributed learning for data requiring privacy preservation, such as medical data, the distribution of secret information is an important problem. In this paper, we propose a framework for secret codes in application to distributed systems. Then, we provide new methods to construct such codes using the synthesis or decomposition of previously known minimal codes. The numerical results show that new constructions can generate codes with more flexible parameters than original constructions in the sense of the number of possible weights and the range of weights. Thus, the secret codes from new constructions may be applied to more general situations or environments in distributed systems. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

12 pages, 1182 KiB  

Open AccessArticle

Necessity of Local Modification for Deep Learning Algorithms to Predict Diabetic Retinopathy

by Ching-Yao Tsai, Chueh-Tan Chen, Guan-An Chen, Chun-Fu Yeh, Chin-Tzu Kuo, Ya-Chuan Hsiao, Hsiao-Yun Hu, I-Lun Tsai, Ching-Hui Wang, Jian-Ren Chen, Su-Chen Huang, Tzu-Chieh Lu and Lin-Chung Woung

Int. J. Environ. Res. Public Health 2022, 19(3), 1204; https://doi.org/10.3390/ijerph19031204 - 21 Jan 2022

Cited by 6 | Viewed by 2178

Abstract

Deep learning (DL) algorithms are used to diagnose diabetic retinopathy (DR). However, most of these algorithms have been trained using global data or data from patients of a single region. Using different model architectures (e.g., Inception-v3, ResNet101, and DenseNet121), we assessed the necessity [...] Read more.

Deep learning (DL) algorithms are used to diagnose diabetic retinopathy (DR). However, most of these algorithms have been trained using global data or data from patients of a single region. Using different model architectures (e.g., Inception-v3, ResNet101, and DenseNet121), we assessed the necessity of modifying the algorithms for universal society screening. We used the open-source dataset from the Kaggle Diabetic Retinopathy Detection competition to develop a model for the detection of DR severity. We used a local dataset from Taipei City Hospital to verify the necessity of model localization and validated the three aforementioned models with local datasets. The experimental results revealed that Inception-v3 outperformed ResNet101 and DenseNet121 with a foreign global dataset, whereas DenseNet121 outperformed Inception-v3 and ResNet101 with the local dataset. The quadratic weighted kappa score ($\kappa$) was used to evaluate the model performance. All models had 5–8% higher κ for the local dataset than for the foreign dataset. Confusion matrix analysis revealed that, compared with the local ophthalmologists’ diagnoses, the severity predicted by the three models was overestimated. Thus, DL algorithms using artificial intelligence based on global data must be locally modified to ensure the applicability of a well-trained model to make diagnoses in clinical environments. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 77 KiB)

14 pages, 2079 KiB  

Open AccessArticle

Feature Importance Analysis for Postural Deformity Detection System Using Explainable Predictive Modeling Technique

by Kwang Hyeon Kim, Woo-Jin Choi and Moon-Jun Sohn

Appl. Sci. 2022, 12(2), 925; https://doi.org/10.3390/app12020925 - 17 Jan 2022

Cited by 1 | Viewed by 2198

Abstract

This study aimed to analyze feature importance by applying explainable artificial intelligence (XAI) to postural deformity parameters extracted from a computer vision-based posture analysis system (CVPAS). Overall, 140 participants were screened for CVPAS and enrolled. The main data analyzed were shoulder height difference [...] Read more.

This study aimed to analyze feature importance by applying explainable artificial intelligence (XAI) to postural deformity parameters extracted from a computer vision-based posture analysis system (CVPAS). Overall, 140 participants were screened for CVPAS and enrolled. The main data analyzed were shoulder height difference (SHD), wrist height difference (WHD), and pelvic height difference (PHD) extracted using a CVPAS. Standing X-ray imaging and radiographic assessments were performed. Predictive modeling was implemented with XGBoost, random forest regressor, and logistic regression using XAI techniques for global and local feature analyses. Correlation analysis was performed between radiographic assessment and AI evaluation for PHD, SHD, and Cobb angle. Main global features affecting scoliosis were analyzed in the order of importance for PHD (0.18) and ankle height difference (0.06) in predictive modeling. Outstanding local features were PHD, WHD, and KHD that predominantly contributed to the increase in the probability of scoliosis, and the prediction probability of scoliosis was 94%. When the PHD was >3 mm, the probability of scoliosis increased sharply to 85.3%. The paired t-test result for AI and radiographic assessments showed that the SHD, Cobb angle, and scoliosis probability were significant (p < 0.05). Feature importance analysis using XAI to postural deformity parameters extracted from a CVPAS is a useful clinical decision support system for the early detection of posture deformities. PHD was a major parameter for both global and local analyses, and 3 mm was a threshold for significantly increasing the probability of local interpretation of each participant and the prediction of postural deformation, which leads to the prediction of participant-specific scoliosis. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Graphical abstract

26 pages, 75205 KiB  

Open AccessArticle

Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images

by Mohamed Mouhafid, Mokhtar Salah, Chi Yue and Kewen Xia

Healthcare 2022, 10(1), 166; https://doi.org/10.3390/healthcare10010166 - 15 Jan 2022

Cited by 15 | Viewed by 2554

Abstract

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along [...] Read more.

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along with RT-PCR, computed tomography (CT) has become a vital technique in diagnosing and managing COVID-19 patients. COVID-19 reveals a number of radiological signatures that can be easily recognized through chest CT. These signatures must be analyzed by radiologists. It is, however, an error-prone and time-consuming process. Deep Learning-based methods can be used to perform automatic chest CT analysis, which may shorten the analysis time. The aim of this study is to design a robust and rapid medical recognition system to identify positive cases in chest CT images using three Ensemble Learning-based models. There are several techniques in Deep Learning for developing a detection system. In this paper, we employed Transfer Learning. With this technique, we can apply the knowledge obtained from a pre-trained Convolutional Neural Network (CNN) to a different but related task. In order to ensure the robustness of the proposed system for identifying positive cases in chest CT images, we used two Ensemble Learning methods namely Stacking and Weighted Average Ensemble (WAE) to combine the performances of three fine-tuned Base-Learners (VGG19, ResNet50, and DenseNet201). For Stacking, we explored 2-Levels and 3-Levels Stacking. The three generated Ensemble Learning-based models were trained on two chest CT datasets. A variety of common evaluation measures (accuracy, recall, precision, and F1-score) are used to perform a comparative analysis of each method. The experimental results show that the WAE method provides the most reliable performance, achieving a high recall value which is a desirable outcome in medical applications as it poses a greater risk if a true infected patient is not identified. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

22 pages, 5380 KiB  

Open AccessArticle

A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease

by Vijendra Singh, Vijayan K. Asari and Rajkumar Rajasekaran

Diagnostics 2022, 12(1), 116; https://doi.org/10.3390/diagnostics12010116 - 05 Jan 2022

Cited by 80 | Viewed by 6252

Abstract

Diabetes and high blood pressure are the primary causes of Chronic Kidney Disease (CKD). Glomerular Filtration Rate (GFR) and kidney damage markers are used by researchers around the world to identify CKD as a condition that leads to reduced renal function over time. [...] Read more.

Diabetes and high blood pressure are the primary causes of Chronic Kidney Disease (CKD). Glomerular Filtration Rate (GFR) and kidney damage markers are used by researchers around the world to identify CKD as a condition that leads to reduced renal function over time. A person with CKD has a higher chance of dying young. Doctors face a difficult task in diagnosing the different diseases linked to CKD at an early stage in order to prevent the disease. This research presents a novel deep learning model for the early detection and prediction of CKD. This research objectives to create a deep neural network and compare its performance to that of other contemporary machine learning techniques. In tests, the average of the associated features was used to replace all missing values in the database. After that, the neural network’s optimum parameters were fixed by establishing the parameters and running multiple trials. The foremost important features were selected by Recursive Feature Elimination (RFE). Hemoglobin, Specific Gravity, Serum Creatinine, Red Blood Cell Count, Albumin, Packed Cell Volume, and Hypertension were found as key features in the RFE. Selected features were passed to machine learning models for classification purposes. The proposed Deep neural model outperformed the other four classifiers (Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic regression, Random Forest, and Naive Bayes classifier) by achieving 100% accuracy. The proposed approach could be a useful tool for nephrologists in detecting CKD. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 2485 KiB  

Open AccessArticle

Determinant of Covariance Matrix Model Coupled with AdaBoost Classification Algorithm for EEG Seizure Detection

by Hanan Al-Hadeethi, Shahab Abdulla, Mohammed Diykh and Jonathan H. Green

Diagnostics 2022, 12(1), 74; https://doi.org/10.3390/diagnostics12010074 - 29 Dec 2021

Cited by 11 | Viewed by 2231

Abstract

Experts usually inspect electroencephalogram (EEG) recordings page-by-page in order to identify epileptic seizures, which leads to heavy workloads and is time consuming. However, the efficient extraction and effective selection of informative EEG features is crucial in assisting clinicians to diagnose epilepsy accurately. In [...] Read more.

Experts usually inspect electroencephalogram (EEG) recordings page-by-page in order to identify epileptic seizures, which leads to heavy workloads and is time consuming. However, the efficient extraction and effective selection of informative EEG features is crucial in assisting clinicians to diagnose epilepsy accurately. In this paper, a determinant of covariance matrix (Cov–Det) model is suggested for reducing EEG dimensionality. First, EEG signals are segmented into intervals using a sliding window technique. Then, Cov–Det is applied to each interval. To construct a features vector, a set of statistical features are extracted from each interval. To eliminate redundant features, the Kolmogorov–Smirnov (KST) and Mann–Whitney U (MWUT) tests are integrated, the extracted features ranked based on KST and MWUT metrics, and arithmetic operators are adopted to construe the most pertinent classified features for each pair in the EEG signal group. The selected features are then fed into the proposed AdaBoost Back-Propagation neural network (AB_BP_NN) to effectively classify EEG signals into seizure and free seizure segments. Finally, the AB_BP_NN is compared with several classical machine learning techniques; the results demonstrate that the proposed mode of AB_BP_NN provides insignificant false positive rates, simpler design, and robustness in classifying epileptic signals. Two datasets, the Bern–Barcelona and Bonn datasets, are used for performance evaluation. The proposed technique achieved an average accuracy of 100% and 98.86%, respectively, for the Bern–Barcelona and Bonn datasets, which is considered a noteworthy improvement compared to the current state-of-the-art methods. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

28 pages, 11603 KiB  

Open AccessArticle

A Multimodal Approach for the Risk Prediction of Intensive Care and Mortality in Patients with COVID-19

by Vasileios C. Pezoulas, Konstantina D. Kourou, Costas Papaloukas, Vassiliki Triantafyllia, Vicky Lampropoulou, Eleni Siouti, Maria Papadaki, Maria Salagianni, Evangelia Koukaki, Nikoletta Rovina, Antonia Koutsoukou, Evangelos Andreakos and Dimitrios I. Fotiadis

Diagnostics 2022, 12(1), 56; https://doi.org/10.3390/diagnostics12010056 - 28 Dec 2021

Cited by 5 | Viewed by 1986

Abstract

Background: Although several studies have been launched towards the prediction of risk factors for mortality and admission in the intensive care unit (ICU) in COVID-19, none of them focuses on the development of explainable AI models to define an ICU scoring index using [...] Read more.

Background: Although several studies have been launched towards the prediction of risk factors for mortality and admission in the intensive care unit (ICU) in COVID-19, none of them focuses on the development of explainable AI models to define an ICU scoring index using dynamically associated biological markers. Methods: We propose a multimodal approach which combines explainable AI models with dynamic modeling methods to shed light into the clinical features of COVID-19. Dynamic Bayesian networks were used to seek associations among cytokines across four time intervals after hospitalization. Explainable gradient boosting trees were trained to predict the risk for ICU admission and mortality towards the development of an ICU scoring index. Results: Our results highlight LDH, IL-6, IL-8, Cr, number of monocytes, lymphocyte count, TNF as risk predictors for ICU admission and survival along with LDH, age, CRP, Cr, WBC, lymphocyte count for mortality in the ICU, with prediction accuracy 0.79 and 0.81, respectively. These risk factors were combined with dynamically associated biological markers to develop an ICU scoring index with accuracy 0.9. Conclusions: to our knowledge, this is the first multimodal and explainable AI model which quantifies the risk of intensive care with accuracy up to 0.9 across multiple timepoints. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 3012 KiB  

Open AccessArticle

A Smart Healthcare Knowledge Service Framework for Hierarchical Medical Treatment System

by Yi Xie, Dongxiao Gu, Xiaoyu Wang, Xuejie Yang, Wang Zhao, Aida K. Khakimova and Hu Liu

Healthcare 2022, 10(1), 32; https://doi.org/10.3390/healthcare10010032 - 24 Dec 2021

Cited by 4 | Viewed by 2725

Abstract

This paper reveals the research hotspots and development directions of case-based reasoning in the field of health care, and proposes the framework and key technologies of medical knowledge service systems based on case-based reasoning (CBR) in the big data environment. The 2124 articles [...] Read more.

This paper reveals the research hotspots and development directions of case-based reasoning in the field of health care, and proposes the framework and key technologies of medical knowledge service systems based on case-based reasoning (CBR) in the big data environment. The 2124 articles on medical CBR in the Web of Science were visualized and analyzed using a bibliometrics method, and a CBR-based knowledge service system framework was constructed in the medical Internet of all people, things and data resources environment. An intelligent construction method for the clinical medical case base and the gray case knowledge reasoning model were proposed. A cloud-edge collaboration knowledge service system was developed and applied in a pilot project. Compared with other diagnostic tools, the system provides case-based explanations for its predicted results, making it easier for physicians to understand and accept, so that they can make better decisions. The results show that the system has good interpretability, has better acceptance than the common intelligent decision support system, and strongly supports physician auxiliary diagnosis and treatment as well as clinical teaching. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

19 pages, 1938 KiB  

Open AccessArticle

The Design of an Intelligent Robotic Wheelchair Supporting People with Special Needs, Including for Their Visual System

by Dorian Cojocaru, Liviu Florin Manta, Cristina Floriana Pană, Andrei Dragomir, Alexandru Marin Mariniuc and Ionel Cristian Vladu

Healthcare 2022, 10(1), 13; https://doi.org/10.3390/healthcare10010013 - 22 Dec 2021

Cited by 5 | Viewed by 3215

Abstract

The paper aims to study the applicability and limitations of the solution resulting from a design process for an intelligent system supporting people with special needs who are not physically able to control a wheelchair using classical systems. The intelligent system uses information [...] Read more.

The paper aims to study the applicability and limitations of the solution resulting from a design process for an intelligent system supporting people with special needs who are not physically able to control a wheelchair using classical systems. The intelligent system uses information from smart sensors and offers a control system that replaces the use of a joystick. The necessary movements of the chair in the environment can be determined by an intelligent vision system analyzing the direction of the patient’s gaze and point of view, as well as the actions of the head. In this approach, an important task is to detect the destination target in the 3D workspace. This solution has been evaluated, outdoor and indoor, under different lighting conditions. In order to design the intelligent wheelchair, and because sometimes people with special needs also have specific problems with their optical system (e.g., strabismus, Nystagmus) the system was tested on different subjects, some of them wearing eyeglasses. During the design process of the intelligent system, all the tests involving human subjects were performed in accordance with specific rules of medical security and ethics. In this sense, the process was supervised by a company specialized in health activities that involve people with special needs. The main results and findings are as follows: validation of the proposed solution for all indoor lightning conditions; methodology to create personal profiles, used to improve the HMI efficiency and to adapt it to each subject needs; a primary evaluation and validation for the use of personal profiles in real life, indoor conditions. The conclusion is that the proposed solution can be used for persons who are not physically able to control a wheelchair using classical systems, having with minor vision deficiencies or major vision impairment affecting one of the eyes. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

19 pages, 2994 KiB  

Open AccessArticle

A Machine Learning Approach to Predicting Diabetes Complications

by Yazan Jian, Michel Pasquier, Assim Sagahyroon and Fadi Aloul

Healthcare 2021, 9(12), 1712; https://doi.org/10.3390/healthcare9121712 - 09 Dec 2021

Cited by 20 | Viewed by 4958

Abstract

Diabetes mellitus (DM) is a chronic disease that is considered to be life-threatening. It can affect any part of the body over time, resulting in serious complications such as nephropathy, neuropathy, and retinopathy. In this work, several supervised classification algorithms were applied for [...] Read more.

Diabetes mellitus (DM) is a chronic disease that is considered to be life-threatening. It can affect any part of the body over time, resulting in serious complications such as nephropathy, neuropathy, and retinopathy. In this work, several supervised classification algorithms were applied for building different models to predict and classify eight diabetes complications. The complications include metabolic syndrome, dyslipidemia, neuropathy, nephropathy, diabetic foot, hypertension, obesity, and retinopathy. For this study, a dataset collected by the Rashid Center for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset consists of 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Furthermore, feature selection was performed to select the top five and ten features for each complication. The final number of records used to train and build the binary classifiers for each complication was as follows: 428—metabolic syndrome, 836—dyslipidemia, 223—neuropathy, 233—nephropathy, 240—diabetic foot, 586—hypertension, 498—obesity, 228—retinopathy. Repeated stratified k-fold cross-validation (with k = 10 and a total of 10 repetitions) was employed for a better estimation of the performance. Accuracy and F1-score were used to evaluate the models’ performance reaching a maximum of 97.8% and 97.7% for accuracy and F1-scores, respectively. Moreover, by comparing the performance achieved using different attributes’ sets, it was found that by using a selected number of features, we can still build adequate classifiers. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

15 pages, 3844 KiB  

Open AccessArticle

An Adaptive Deep Ensemble Learning Method for Dynamic Evolving Diagnostic Task Scenarios

by Kaixiang Su, Jiao Wu, Dongxiao Gu, Shanlin Yang, Shuyuan Deng and Aida K. Khakimova

Diagnostics 2021, 11(12), 2288; https://doi.org/10.3390/diagnostics11122288 - 07 Dec 2021

Cited by 3 | Viewed by 2282

Abstract

Increasingly, machine learning methods have been applied to aid in diagnosis with good results. However, some complex models can confuse physicians because they are difficult to understand, while data differences across diagnostic tasks and institutions can cause model performance fluctuations. To address this [...] Read more.

Increasingly, machine learning methods have been applied to aid in diagnosis with good results. However, some complex models can confuse physicians because they are difficult to understand, while data differences across diagnostic tasks and institutions can cause model performance fluctuations. To address this challenge, we combined the Deep Ensemble Model (DEM) and tree-structured Parzen Estimator (TPE) and proposed an adaptive deep ensemble learning method (TPE-DEM) for dynamic evolving diagnostic task scenarios. Different from previous research that focuses on achieving better performance with a fixed structure model, our proposed model uses TPE to efficiently aggregate simple models more easily understood by physicians and require less training data. In addition, our proposed model can choose the optimal number of layers for the model and the type and number of basic learners to achieve the best performance in different diagnostic task scenarios based on the data distribution and characteristics of the current diagnostic task. We tested our model on one dataset constructed with a partner hospital and five UCI public datasets with different characteristics and volumes based on various diagnostic tasks. Our performance evaluation results show that our proposed model outperforms other baseline models on different datasets. Our study provides a novel approach for simple and understandable machine learning models in tasks with variable datasets and feature sets, and the findings have important implications for the application of machine learning models in computer-aided diagnosis. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 1098 KiB  

Open AccessArticle

Predicting Prolonged Length of ICU Stay through Machine Learning

by Jingyi Wu, Yu Lin, Pengfei Li, Yonghua Hu, Luxia Zhang and Guilan Kong

Diagnostics 2021, 11(12), 2242; https://doi.org/10.3390/diagnostics11122242 - 30 Nov 2021

Cited by 13 | Viewed by 2688

Abstract

This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the [...] Read more.

This study aimed to construct machine learning (ML) models for predicting prolonged length of stay (pLOS) in intensive care units (ICU) among general ICU patients. A multicenter database called eICU (Collaborative Research Database) was used for model derivation and internal validation, and the Medical Information Mart for Intensive Care (MIMIC) III database was used for external validation. We used four different ML methods (random forest, support vector machine, deep learning, and gradient boosting decision tree (GBDT)) to develop prediction models. The prediction performance of the four models were compared with the customized simplified acute physiology score (SAPS) II. The area under the receiver operation characteristic curve (AUROC), area under the precision-recall curve (AUPRC), estimated calibration index (ECI), and Brier score were used to measure performance. In internal validation, the GBDT model achieved the best overall performance (Brier score, 0.164), discrimination (AUROC, 0.742; AUPRC, 0.537), and calibration (ECI, 8.224). In external validation, the GBDT model also achieved the best overall performance (Brier score, 0.166), discrimination (AUROC, 0.747; AUPRC, 0.536), and calibration (ECI, 8.294). External validation showed that the calibration curve of the GBDT model was an optimal fit, and four ML models outperformed the customized SAPS II model. The GBDT-based pLOS-ICU prediction model had the best prediction performance among the five models on both internal and external datasets. Furthermore, it has the potential to assist ICU physicians to identify patients with pLOS-ICU risk and provide appropriate clinical interventions to improve patient outcomes. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

11 pages, 16689 KiB  

Open AccessArticle

Development of an Artificial Intelligence System for the Automatic Evaluation of Cervical Vertebral Maturation Status

by Jing Zhou, Hong Zhou, Lingling Pu, Yanzi Gao, Ziwei Tang, Yi Yang, Meng You, Zheng Yang, Wenli Lai and Hu Long

Diagnostics 2021, 11(12), 2200; https://doi.org/10.3390/diagnostics11122200 - 25 Nov 2021

Cited by 19 | Viewed by 2568

Abstract

Background: Cervical vertebral maturation (CVM) is widely used to evaluate growth potential in the field of orthodontics. This study is aimed to develop an artificial intelligence (AI) system to automatically determine the CVM status and evaluate the AI performance. Methods: A total of [...] Read more.

Background: Cervical vertebral maturation (CVM) is widely used to evaluate growth potential in the field of orthodontics. This study is aimed to develop an artificial intelligence (AI) system to automatically determine the CVM status and evaluate the AI performance. Methods: A total of 1080 cephalometric radiographs, with the age of patients ranging from 6 to 22 years old, were included in the dataset (980 in training dataset and 100 in testing dataset). Two reference points and thirteen anatomical points were labelled and the cervical vertebral maturation staging (CS) was assessed by human examiners as gold standard. A convolutional neural network (CNN) model was built to train on 980 images and to test on 100 images. Statistical analysis was conducted to detect labelling differences between AI and human examiners, AI performance was also evaluated. Results: The mean labelling error between human examiners was 0.48 ± 0.12 mm. The mean labelling error between AI and human examiners was 0.36 ± 0.09 mm. In general, the agreement between AI results and the gold standard was good, with the intraclass correlation coefficient (ICC) value being up to 98%. Moreover, the accuracy of CVM staging was 71%. In terms of F1 score, CS6 stage (85%) ranked the highest accuracy. Conclusions: In this study, AI showed a good agreement with human examiners, being a useful and reliable tool in assessing the cervical vertebral maturation. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 4169 KiB  

Open AccessCase Report

Visualization of Complex Processes in Cardiovascular System during Electrical Auricular Vagus Nerve Stimulation

by Vaiva Šiaučiūnaitė, Minvydas Ragulskis, Alfonsas Vainoras, Babak Dabiri and Eugenijus Kaniusas

Diagnostics 2021, 11(12), 2190; https://doi.org/10.3390/diagnostics11122190 - 25 Nov 2021

Cited by 2 | Viewed by 1953

Abstract

The analysis of human physiological systems from the point of view of complex systems theory remains a very ambitious task. The complexity of the problem often encourages the use of innovative mathematical methods analyzing the processes that take place in space and time. [...] Read more.

The analysis of human physiological systems from the point of view of complex systems theory remains a very ambitious task. The complexity of the problem often encourages the use of innovative mathematical methods analyzing the processes that take place in space and time. The main goal of this paper is to visualize the cardiovascular system during auricular vagus nerve stimulation (aVNS) using the matrix differences to evaluate the dynamic signal interfaces by cointegrating the initial signal data into the matrices during each case. Algebraic relationships between RR/JT and JT/QRS cardiac intervals are used not only to track the cardiovascular changes during aVNS but also to characterize individual features of the person during the transit through the therapy. This paper presents the computational techniques that can visualize the complex dynamical processes taking place in the cardiovascular system using the electrical aVNS therapy. Four healthy volunteers participated in two verum and two placebo experiments. We discovered that the body’s reaction to the stimulation was very different in each of the cases, but the presented techniques opened new possibilities for a novel interpretation of the dynamics of the cardiovascular system. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 2863 KiB  

Open AccessArticle

Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

by Wansuk Choi and Seoyoon Heo

Healthcare 2021, 9(11), 1579; https://doi.org/10.3390/healthcare9111579 - 18 Nov 2021

Cited by 6 | Viewed by 5060

Abstract

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning [...] Read more.

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 4371 KiB)

17 pages, 3449 KiB  

Open AccessArticle

Automation of Lung Ultrasound Interpretation via Deep Learning for the Classification of Normal versus Abnormal Lung Parenchyma: A Multicenter Study

by Robert Arntfield, Derek Wu, Jared Tschirhart, Blake VanBerlo, Alex Ford, Jordan Ho, Joseph McCauley, Benjamin Wu, Jason Deglint, Rushil Chaudhary, Chintan Dave, Bennett VanBerlo, John Basmaji and Scott Millington

Diagnostics 2021, 11(11), 2049; https://doi.org/10.3390/diagnostics11112049 - 04 Nov 2021

Cited by 12 | Viewed by 3044

Abstract

Lung ultrasound (LUS) is an accurate thoracic imaging technique distinguished by its handheld size, low-cost, and lack of radiation. User dependence and poor access to training have limited the impact and dissemination of LUS outside of acute care hospital environments. Automated interpretation of [...] Read more.

Lung ultrasound (LUS) is an accurate thoracic imaging technique distinguished by its handheld size, low-cost, and lack of radiation. User dependence and poor access to training have limited the impact and dissemination of LUS outside of acute care hospital environments. Automated interpretation of LUS using deep learning can overcome these barriers by increasing accuracy while allowing point-of-care use by non-experts. In this multicenter study, we seek to automate the clinically vital distinction between A line (normal parenchyma) and B line (abnormal parenchyma) on LUS by training a customized neural network using 272,891 labelled LUS images. After external validation on 23,393 frames, pragmatic clinical application at the clip level was performed on 1162 videos. The trained classifier demonstrated an area under the receiver operating curve (AUC) of 0.96 (±0.02) through 10-fold cross-validation on local frames and an AUC of 0.93 on the external validation dataset. Clip-level inference yielded sensitivities and specificities of 90% and 92% (local) and 83% and 82% (external), respectively, for detecting the B line pattern. This study demonstrates accurate deep-learning-enabled LUS interpretation between normal and abnormal lung parenchyma on ultrasound frames while rendering diagnostically important sensitivity and specificity at the video clip level. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

17 pages, 4845 KiB  

Open AccessArticle

An Effective Convolutional Neural Network Model for the Early Detection of COVID-19 Using Chest X-ray Images

by Muhammad Shoaib Farooq, Attique Ur Rehman, Muhammad Idrees, Muhammad Ahsan Raza, Jehad Ali, Mehedi Masud, Jehad F. Al-Amri and Syed Hasnain Raza Kazmi

Appl. Sci. 2021, 11(21), 10301; https://doi.org/10.3390/app112110301 - 02 Nov 2021

Cited by 3 | Viewed by 2849

Abstract

COVID-19 has been difficult to diagnose and treat at an early stage all over the world. The numbers of patients showing symptoms for COVID-19 have caused medical facilities at hospitals to become unavailable or overcrowded, which is a major challenge. Studies have recently [...] Read more.

COVID-19 has been difficult to diagnose and treat at an early stage all over the world. The numbers of patients showing symptoms for COVID-19 have caused medical facilities at hospitals to become unavailable or overcrowded, which is a major challenge. Studies have recently allowed us to determine that COVID-19 can be diagnosed with the aid of chest X-ray images. To combat the COVID-19 outbreak, developing a deep learning (DL) based model for automated COVID-19 diagnosis on chest X-ray is beneficial. In this research, we have proposed a customized convolutional neural network (CNN) model to detect COVID-19 from chest X-ray images. The model is based on nine layers which uses a binary classification method to differentiate between COVID-19 and normal chest X-rays. It provides COVID-19 detection early so the patients can be admitted in a timely fashion. The proposed model was trained and tested on two publicly available datasets. Cross-dataset studies are used to assess the robustness in a real-world context. Six hundred X-ray images were used for training and two hundred X-rays were used for validation of the model. The X-ray images of the dataset were preprocessed to improve the results and visualized for better analysis. The developed algorithm reached 98% precision, recall and f1-score. The cross-dataset studies also demonstrate the resilience of deep learning algorithms in a real-world context with 98.5 percent accuracy. Furthermore, a comparison table was created which shows that our proposed model outperforms other relative models in terms of accuracy. The quick and high-performance of our proposed DL-based customized model identifies COVID-19 patients quickly, which is helpful in controlling the COVID-19 outbreak. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

11 pages, 909 KiB  

Open AccessArticle

A Home-Based Multimedia Pulmonary Rehabilitation Program Improves Clinical Symptoms and Physical Performance of Patients with Chronic Obstructive Pulmonary Disease

by Anoma Santiworakul, Nitita Piya-amornphan and Netchanok Jianramas

Int. J. Environ. Res. Public Health 2021, 18(21), 11479; https://doi.org/10.3390/ijerph182111479 - 31 Oct 2021

Cited by 2 | Viewed by 2597

Abstract

Home-based pulmonary rehabilitation can decrease symptoms in chronic obstructive pulmonary disease (COPD) patients. The purpose of this study was to compare the effects of a home-based pulmonary rehabilitation by instructive multimedia in the form of videos and flip charts on clinical symptoms and [...] Read more.

Home-based pulmonary rehabilitation can decrease symptoms in chronic obstructive pulmonary disease (COPD) patients. The purpose of this study was to compare the effects of a home-based pulmonary rehabilitation by instructive multimedia in the form of videos and flip charts on clinical symptoms and exercise performance in COPD patients. An eight-week home-based pulmonary rehabilitation program was performed with twenty COPD patients older than 60 years of age with moderate to severe stages. They were separated into two groups: a multimedia group (n = 10) and a control group, which was only provided with telephone monitoring (n = 10). Clinical symptoms were measured by using the clinical COPD questionnaire (CCQ), and exercise performance was measured using a six-minute walk test (6MWT) and an upper-lower limb muscle strengthening test. After 8 weeks, the results showed that both groups showed a statistically significant decrease in the CCQ (p < 0.05). The multimedia group showed a statistically significant increase in the lower-limb muscle strengthening (p < 0.05), while the control group was not found to show a statistically significant increase in the lower-limb muscle strengthening. Therefore, a pulmonary rehabilitation program using multimedia at home can lessen symptoms and improve exercise performance in COPD patients. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 15293 KiB  

Open AccessArticle

Classification for Breast Ultrasound Using Convolutional Neural Network with Multiple Time-Domain Feature Maps

by Hyungsuk Kim, Juyoung Park, Hakjoon Lee, Geuntae Im, Jongsoo Lee, Ki-Baek Lee and Heung Jae Lee

Appl. Sci. 2021, 11(21), 10216; https://doi.org/10.3390/app112110216 - 31 Oct 2021

Cited by 5 | Viewed by 4511

Abstract

Ultrasound (US) imaging is widely utilized as a diagnostic screening method, and deep learning has recently drawn attention for the analysis of US images for the pathological status of tissues. While low image quality and poor reproducibility are the common obstacles in US [...] Read more.

Ultrasound (US) imaging is widely utilized as a diagnostic screening method, and deep learning has recently drawn attention for the analysis of US images for the pathological status of tissues. While low image quality and poor reproducibility are the common obstacles in US analysis, the small size of the dataset is a new limitation for deep learning due to lack of generalization. In this work, a convolutional neural network (CNN) using multiple feature maps, such as entropy and phase images, as well as a B-mode image, was proposed to classify breast US images. Although B-mode images contain both anatomical and textual information, traditional CNNs experience difficulties in abstracting features automatically, especially with small datasets. For the proposed CNN framework, two distinct feature maps were obtained from a B-mode image and utilized as new inputs for training the CNN. These feature maps can also be made from the evaluation data and applied to the CNN separately for the final classification decision. The experimental results with 780 breast US images in three categories of benign, malignant, and normal, showed that the proposed CNN framework using multiple feature maps exhibited better performances than the traditional CNN with B-mode only for most deep network models. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

16 pages, 2007 KiB  

Open AccessArticle

Hybrid Machine Learning Model for Body Fat Percentage Prediction Based on Support Vector Regression and Emotional Artificial Neural Networks

by Solaf A. Hussain, Nadire Cavus and Boran Sekeroglu

Appl. Sci. 2021, 11(21), 9797; https://doi.org/10.3390/app11219797 - 20 Oct 2021

Cited by 11 | Viewed by 3340

Abstract

Obesity or excessive body fat causes multiple health problems and diseases. However, obesity treatment and control need an accurate determination of body fat percentage (BFP). The existing methods for BFP estimation require several procedures, which reduces their cost-effectivity and generalization. Therefore, developing cost-effective [...] Read more.

Obesity or excessive body fat causes multiple health problems and diseases. However, obesity treatment and control need an accurate determination of body fat percentage (BFP). The existing methods for BFP estimation require several procedures, which reduces their cost-effectivity and generalization. Therefore, developing cost-effective models for BFP estimation is vital for obesity treatment. Machine learning models, particularly hybrid models, have a strong ability to analyze challenging data and perform predictions by combining different characteristics of the models. This study proposed a hybrid machine learning model based on support vector regression and emotional artificial neural networks (SVR-EANNs) for accurate recent BFP prediction using a primary BFP dataset. SVR was applied as a consistent attribute selection model on seven properties and measurements, using the left-out sensitivity analysis, and the regression ability of the EANN was considered in the prediction phase. The proposed model was compared to seven benchmark machine learning models. The obtained results show that the proposed hybrid model (SVR-EANN) outperformed other machine learning models by achieving superior results in the three considered evaluation metrics. Furthermore, the proposed model suggested that abdominal circumference is a significant factor in BFP prediction, while age has a minor effect. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

12 pages, 3516 KiB  

Open AccessArticle

Deep-Learning-Based Hair Damage Diagnosis Method Applying Scanning Electron Microscopy Images

by Lintong Zhang, Qiaoyue Man and Young Im Cho

Diagnostics 2021, 11(10), 1831; https://doi.org/10.3390/diagnostics11101831 - 03 Oct 2021

Cited by 2 | Viewed by 3620

Abstract

In recent years, with the gradual development of medicine and deep learning, many technologies have been developed. In the field of beauty services or medicine, it is particularly important to judge the degree of hair damage. Because people in modern society pay more [...] Read more.

In recent years, with the gradual development of medicine and deep learning, many technologies have been developed. In the field of beauty services or medicine, it is particularly important to judge the degree of hair damage. Because people in modern society pay more attention to their own dressing and makeup, changes in the shape of their hair have become more frequent, e.g., owing to a perm or dyeing. Thus, the hair is severely damaged through this process. Because hair is relatively thin, a quick determination of the degree of damage has also become a major problem. Currently, there are three specific methods for this purpose. In the first method, professionals engaged in the beauty service industry make a direct judgement with the naked eye. The second way is to observe the damaged cuticle layers of the hair using a microscope, and then make a judgment. The third approach is to conduct experimental tests using physical and chemical methods. However, all of these methods entail certain limitations, inconveniences, and a high complexity and time consumption. Therefore, our proposed method is to use scanning electron microscope to collect various hair sample images, combined with deep learning to identify and judge the degree of hair damage. This method will be used for hair quality diagnosis. Experiment on the data set we made, compared with the experimental results of other lightweight networks, our method showed the highest accuracy rate of 94.8%. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

24 pages, 8000 KiB  

Open AccessArticle

A Machine-Learning Method of Predicting Vital Capacity Plateau Value for Ventilatory Pump Failure Based on Data Mining

by Wenbing Chang, Xinpeng Ji, Liping Wang, Houxiang Liu, Yue Zhang, Bang Chen and Shenghan Zhou

Healthcare 2021, 9(10), 1306; https://doi.org/10.3390/healthcare9101306 - 30 Sep 2021

Cited by 12 | Viewed by 1986

Abstract

Ventilatory pump failure is a common cause of death for patients with neuromuscular diseases. The vital capacity plateau value (VCPLAT) is an important indicator to judge the status of ventilatory pump failure for patients with congenital myopathy, Duchenne muscular dystrophy and spinal muscular [...] Read more.

Ventilatory pump failure is a common cause of death for patients with neuromuscular diseases. The vital capacity plateau value (VCPLAT) is an important indicator to judge the status of ventilatory pump failure for patients with congenital myopathy, Duchenne muscular dystrophy and spinal muscular atrophy. Due to the complex relationship between VCPLAT and the patient’s own condition, it is difficult to predict the VCPLAT for pediatric disease from a medical perspective. We established a VCPLAT prediction model based on data mining and machine learning. We first performed the correlation analysis and recursive feature elimination with cross-validation (RFECV) to provide high-quality feature combinations. Based on this, the Light Gradient Boosting Machine (LightGBM) algorithm was to establish a prediction model with powerful performance. Finally, we verified the validity and superiority of the proposed method via comparison with other prediction models in similar works. After 10-fold cross-validation, the proposed prediction method had the best performance and its explained variance score (EVS), mean absolute error (MAE), mean squared error (MSE), root mean square error (RMSE), median absolute error (MedAE) and R² were 0.949, 0.028, 0.002, 0.045, 0.015 and 0.948, respectively. It also performed well on test datasets. Therefore, it can accurately and effectively predict the VCPLAT, thereby determining the severity of the condition to provide auxiliary decision-making for doctors in clinical diagnosis and treatment. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 104 KiB)

12 pages, 1576 KiB  

Open AccessArticle

Green Line Hospital-Territory Study: A Single-Blind Randomized Clinical Trial for Evaluation of Technological Challenges of Continuous Wireless Monitoring in Internal Medicine, Preliminary Results

by Filomena Pietrantonio, Antonio Vinci, Francesco Rosiello, Elena Alessi, Matteo Pascucci, Marianna Rainone, Michela Delli Castelli, Angela Ciamei, Fabrizio Montagnese, Roberto D’Amico, Antonella Valerio and Dario Manfellotto

Int. J. Environ. Res. Public Health 2021, 18(19), 10328; https://doi.org/10.3390/ijerph181910328 - 30 Sep 2021

Cited by 4 | Viewed by 2184

Abstract

Background: Wireless vital parameter continuous monitoring (WVPCM) after discharge is compared to regular monitoring to provide data on the clinical-economic impact of complex patients (CPs) discharged from Internal Medicine Units of Ospedale dei Castelli, Lazio. Primary outcome: Major complications (MC) reduction. Secondary outcomes: [...] Read more.

Background: Wireless vital parameter continuous monitoring (WVPCM) after discharge is compared to regular monitoring to provide data on the clinical-economic impact of complex patients (CPs) discharged from Internal Medicine Units of Ospedale dei Castelli, Lazio. Primary outcome: Major complications (MC) reduction. Secondary outcomes: Patients who reached discharge criteria within the 7th day from admission; difference in MC incidence at the conclusion of the standard telemonitoring/clinical monitoring phase, 5 and 30 days after discharge; and conditions predisposing to MC occurrence. Methods: Open label randomized controlled trial with wearable wireless system that creates alerts on portable devices. Continuous glycemic monitoring is performed for patients with diabetes mellitus. Results: There were 110 patients enrolled (mean age: 76.2 years). Comorbidity: Cumulative Illness Rating Scale CIRS-CI (comorbidities index): 3.93, CIRS SI (severity index): 1.93. About 19% scored a BRASS (Blaylock Risk Assessment Screening Score) ≥20 indicating need for discharge planning requiring step-down care. Globally, 48% of patients in the control group had major complications (27 out of 56 patients), in contrast to 22% in the intervention group (12 out of 54 patients). Conclusions: Since WVPCM detects early complications during the post-discharge CPs monitoring, it increases safety and reduces inappropriate access to the Emergency Room, preventing avoidable re-hospitalizations. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

13 pages, 1691 KiB  

Open AccessArticle

The Comparison and Interpretation of Machine-Learning Models in Post-Stroke Functional Outcome Prediction

by Shih-Chieh Chang, Chan-Lin Chu, Chih-Kuang Chen, Hsiang-Ning Chang, Alice M. K. Wong, Yueh-Peng Chen and Yu-Cheng Pei

Diagnostics 2021, 11(10), 1784; https://doi.org/10.3390/diagnostics11101784 - 28 Sep 2021

Cited by 9 | Viewed by 2686

Abstract

Prediction of post-stroke functional outcomes is crucial for allocating medical resources. In this study, a total of 577 patients were enrolled in the Post-Acute Care-Cerebrovascular Disease (PAC-CVD) program, and 77 predictors were collected at admission. The outcome was whether a patient could achieve [...] Read more.

Prediction of post-stroke functional outcomes is crucial for allocating medical resources. In this study, a total of 577 patients were enrolled in the Post-Acute Care-Cerebrovascular Disease (PAC-CVD) program, and 77 predictors were collected at admission. The outcome was whether a patient could achieve a Barthel Index (BI) score of >60 upon discharge. Eight machine-learning (ML) methods were applied, and their results were integrated by stacking method. The area under the curve (AUC) of the eight ML models ranged from 0.83 to 0.887, with random forest, stacking, logistic regression, and support vector machine demonstrating superior performance. The feature importance analysis indicated that the initial Berg Balance Test (BBS-I), initial BI (BI-I), and initial Concise Chinese Aphasia Test (CCAT-I) were the top three predictors of BI scores at discharge. The partial dependence plot (PDP) and individual conditional expectation (ICE) plot indicated that the predictors’ ability to predict outcomes was the most pronounced within a specific value range (e.g., BBS-I < 40 and BI-I < 60). BI at discharge could be predicted by information collected at admission with the aid of various ML models, and the PDP and ICE plots indicated that the predictors could predict outcomes at a certain value range. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 207 KiB)

12 pages, 826 KiB  

Open AccessArticle

Keyword Extraction Algorithm for Classifying Smoking Status from Unstructured Bilingual Electronic Health Records Based on Natural Language Processing

by Ye Seul Bae, Kyung Hwan Kim, Han Kyul Kim, Sae Won Choi, Taehoon Ko, Hee Hwa Seo, Hae-Young Lee and Hyojin Jeon

Appl. Sci. 2021, 11(19), 8812; https://doi.org/10.3390/app11198812 - 22 Sep 2021

Cited by 3 | Viewed by 2875

Abstract

Smoking is an important variable for clinical research, but there are few studies regarding automatic obtainment of smoking classification from unstructured bilingual electronic health records (EHR). We aim to develop an algorithm to classify smoking status based on unstructured EHRs using natural language [...] Read more.

Smoking is an important variable for clinical research, but there are few studies regarding automatic obtainment of smoking classification from unstructured bilingual electronic health records (EHR). We aim to develop an algorithm to classify smoking status based on unstructured EHRs using natural language processing (NLP). With acronym replacement and Python package Soynlp, we normalize 4711 bilingual clinical notes. Each EHR notes was classified into 4 categories: current smokers, past smokers, never smokers, and unknown. Subsequently, SPPMI (Shifted Positive Point Mutual Information) is used to vectorize words in the notes. By calculating cosine similarity between these word vectors, keywords denoting the same smoking status are identified. Compared to other keyword extraction methods (word co-occurrence-, PMI-, and NPMI-based methods), our proposed approach improves keyword extraction precision by as much as 20.0%. These extracted keywords are used in classifying 4 smoking statuses from our bilingual EHRs. Given an identical SVM classifier, the F1 score is improved by as much as 1.8% compared to those of the unigram and bigram Bag of Words. Our study shows the potential of SPPMI in classifying smoking status from bilingual, unstructured EHRs. Our current findings show how smoking information can be easily acquired for clinical practice and research. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

10 pages, 324 KiB  

Open AccessArticle

Analysis of Factors Affecting Depression in Older Adults in South Korea

by Ah-Ram Kim, Jin-Hyuck Park and Hae Yean Park

Int. J. Environ. Res. Public Health 2021, 18(18), 9887; https://doi.org/10.3390/ijerph18189887 - 20 Sep 2021

Cited by 5 | Viewed by 2944

Abstract

Objective: This study aimed to analyze the factors affecting depression among South Korean middle-aged and older adults using data from the Korean Longitudinal Study of Aging. Methods: We analyzed data regarding demographic characteristics, lifestyle, quality of life, cognitive level, and depression. Cognitive level [...] Read more.

Objective: This study aimed to analyze the factors affecting depression among South Korean middle-aged and older adults using data from the Korean Longitudinal Study of Aging. Methods: We analyzed data regarding demographic characteristics, lifestyle, quality of life, cognitive level, and depression. Cognitive level and depression were evaluated using the Korean-Mini-Mental Status Examination and Center for Epidemiological Studies Depression Scale, respectively. Results: Depression was correlated with age, gender, residential area, level of education, alcohol intake, regular exercise, life satisfaction, and cognitive level, but not smoking. Furthermore, depression was highly affected by age, residential area, regular exercise, life satisfaction, and cognitive level, with a prediction accuracy of 80.26% achieved through machine learning analysis. Conclusions: Various factors are associated with depression in middle-aged and older adults. Therefore, multifaceted interventions for preventing depression in these age groups are required. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

15 pages, 7677 KiB  

Open AccessArticle

The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

by Mohammed R. S. Sunoqrot, Kirsten M. Selnæs, Elise Sandsmark, Sverre Langørgen, Helena Bertilsson, Tone F. Bathen and Mattijs Elschot

Diagnostics 2021, 11(9), 1690; https://doi.org/10.3390/diagnostics11091690 - 16 Sep 2021

Cited by 13 | Viewed by 2241

Abstract

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from [...] Read more.

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from 244 patients was used to investigate the intra-patient reproducibility of 14 shape features for DL-based segmentation methods of the whole prostate gland (WP), peripheral zone (PZ), and the remaining prostate zones (non-PZ) on T2-weighted (T2W) magnetic resonance (MR) images compared to manual segmentations. The DL-based segmentation was performed using three different convolutional neural networks (CNNs): V-Net, nnU-Net-2D, and nnU-Net-3D. The two-way random, single score intra-class correlation coefficient (ICC) was used to measure the inter-scan reproducibility of each feature for each CNN and the manual segmentation. We found that the reproducibility of the investigated methods is comparable to manual for all CNNs (14/14 features), except for V-Net in PZ (7/14 features). The ICC score for segmentation volume was found to be 0.888, 0.607, 0.819, and 0.903 in PZ; 0.988, 0.967, 0.986, and 0.983 in non-PZ; 0.982, 0.975, 0.973, and 0.984 in WP for manual, V-Net, nnU-Net-2D, and nnU-Net-3D, respectively. The results of this work show the feasibility of embedding DL-based segmentation in CAD systems, based on multiple T2W MR scans of the prostate, which is an important step towards the clinical implementation. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

18 pages, 14087 KiB  

Open AccessArticle

A Personalized Medical Decision Support System Based on Explainable Machine Learning Algorithms and ECC Features: Data from the Real World

by Dongxiao Gu, Wang Zhao, Yi Xie, Xiaoyu Wang, Kaixiang Su and Oleg V. Zolotarev

Diagnostics 2021, 11(9), 1677; https://doi.org/10.3390/diagnostics11091677 - 14 Sep 2021

Cited by 8 | Viewed by 2239

Abstract

Artificial intelligence can help physicians improve the accuracy of breast cancer diagnosis. However, the effectiveness of AI applications is limited by doctors’ adoption of the results recommended by the personalized medical decision support system. Our primary purpose is to study the impact of [...] Read more.

Artificial intelligence can help physicians improve the accuracy of breast cancer diagnosis. However, the effectiveness of AI applications is limited by doctors’ adoption of the results recommended by the personalized medical decision support system. Our primary purpose is to study the impact of external case characteristics (ECC) on the effectiveness of the personalized medical decision support system for breast cancer assisted diagnosis (PMDSS-BCAD) in making accurate recommendations. Therefore, we designed a novel comprehensive framework for case-based reasoning (CBR) that takes the impact of external features of cases into account, made use of the naive Bayes and k-nearest neighbor (KNN) algorithms (CBR-ECC), and developed a PMDSS-BCAD system by using the CBR-ECC model and external features as system components. Under the new case-based reasoning framework, the accuracy of the combined model of naive Bayes and KNN with an optimal K value of 2 is 99.40%. Moreover, in a real hospital scenario, users rated the PMDSS-BCAD system, which takes into account the external characteristics of the case, better than the original personalized system. These results suggest that PMDSS-BCD can not only provide doctors with more personalized and accurate results for auxiliary diagnosis, but also improve doctors’ trust in the results, so as to encourage doctors to adopt the results recommended by the personalized system. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

15 pages, 4038 KiB  

Open AccessArticle

Recognition Rate Advancement and Data Error Improvement of Pathology Cutting with H-DenseUNet for Hepatocellular Carcinoma Image

by Wen-Fan Chen, Hsin-You Ou, Cheng-Tang Pan, Chien-Chang Liao, Wen Huang, Han-Yu Lin, Yu-Fan Cheng and Chia-Po Wei

Diagnostics 2021, 11(9), 1599; https://doi.org/10.3390/diagnostics11091599 - 02 Sep 2021

Viewed by 2336

Abstract

Due to the fact that previous studies have rarely investigated the recognition rate discrepancy and pathology data error when applied to different databases, the purpose of this study is to investigate the improvement of recognition rate via deep learning-based liver lesion segmentation with [...] Read more.

Due to the fact that previous studies have rarely investigated the recognition rate discrepancy and pathology data error when applied to different databases, the purpose of this study is to investigate the improvement of recognition rate via deep learning-based liver lesion segmentation with the incorporation of hospital data. The recognition model used in this study is H-DenseUNet, which is applied to the segmentation of the liver and lesions, and a mixture of 2D/3D Hybrid-DenseUNet is used to reduce the recognition time and system memory requirements. Differences in recognition results were determined by comparing the training files of the standard LiTS competition data set with the training set after mixing in an additional 30 patients. The average error value of 9.6% was obtained by comparing the data discrepancy between the actual pathology data and the pathology data after the analysis of the identified images imported from Kaohsiung Chang Gung Memorial Hospital. The average error rate of the recognition output after mixing the LiTS database with hospital data for training was 1%. In the recognition part, the Dice coefficient was 0.52 after training 50 epochs using the standard LiTS database, while the Dice coefficient was increased to 0.61 after adding 30 hospital data to the training. After importing 3D Slice and ITK-Snap software, a 3D image of the lesion and liver segmentation can be developed. It is hoped that this method could be used to stimulate more research in addition to the general public standard database in the future, as well as to study the applicability of hospital data and improve the generality of the database. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

15 pages, 736 KiB  

Open AccessArticle

Medical Health Records-Based Mild Cognitive Impairment (MCI) Prediction for Effective Dementia Care

by Soo-Jin Lim, Zoonky Lee, Lee-Nam Kwon and Hong-Woo Chun

Int. J. Environ. Res. Public Health 2021, 18(17), 9223; https://doi.org/10.3390/ijerph18179223 - 01 Sep 2021

Cited by 7 | Viewed by 2556

Abstract

Dementia is a cognitive impairment that poses a global threat. Current dementia treatments slow the progression of the disease. The timing of starting such treatment markedly affects the effectiveness of the treatment. Some experts mentioned that the optimal timing for starting the currently [...] Read more.

Dementia is a cognitive impairment that poses a global threat. Current dementia treatments slow the progression of the disease. The timing of starting such treatment markedly affects the effectiveness of the treatment. Some experts mentioned that the optimal timing for starting the currently available treatment in order to delay progression to dementia is the mild cognitive impairment stage, which is the prior stage of dementia. However, medical records are typically only available at a later stage, i.e., from the early or middle stage of dementia. In order to address this limitation, this study developed a model using national health information data from 5 years prior, to predict dementia development 5 years in the future. The Senior Cohort Database, comprising 550,000 samples, were used for model development. The F-measure of the model predicting dementia development after a 5-year incubation period was 77.38%. Models for a 1- and 3-year incubation period were also developed for comparative analysis of dementia risk factors. The three models had some risk factors in common, but also had unique risk factors, depending on the stage. For the common risk factors, a difference in disease severity was confirmed. These findings indicate that the diagnostic criteria and treatment strategy for dementia should differ depending on the timing. Furthermore, since the results of this study present new dementia risk factors that have not been reported previously, this study may also contribute to identification of new dementia risk factors. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

17 pages, 300 KiB  

Open AccessArticle

Calibrating Mini-Mental State Examination Scores to Predict Misdiagnosed Dementia Patients

by Akhilesh Vyas, Fotis Aisopos, Maria-Esther Vidal, Peter Garrard and George Paliouras

Appl. Sci. 2021, 11(17), 8055; https://doi.org/10.3390/app11178055 - 30 Aug 2021

Cited by 2 | Viewed by 3818

Abstract

Mini-Mental State Examination (MMSE) is used as a diagnostic test for dementia to screen a patient’s cognitive assessment and disease severity. However, these examinations are often inaccurate and unreliable either due to human error or due to patients’ physical disability to correctly interpret [...] Read more.

Mini-Mental State Examination (MMSE) is used as a diagnostic test for dementia to screen a patient’s cognitive assessment and disease severity. However, these examinations are often inaccurate and unreliable either due to human error or due to patients’ physical disability to correctly interpret the questions as well as motor deficit. Erroneous data may lead to a wrong assessment of a specific patient. Therefore, other clinical factors (e.g., gender and comorbidities) existing in electronic health records, can also play a significant role, while reporting her examination results. This work considers various clinical attributes of dementia patients to accurately determine their cognitive status in terms of the Mini-Mental State Examination (MMSE) Score. We employ machine learning models to calibrate MMSE score and classify the correctness of diagnosis among patients, in order to assist clinicians in a better understanding of the progression of cognitive impairment and subsequent treatment. For this purpose, we utilize a curated real-world ageing study data. A random forest prediction model is employed to estimate the Mini-Mental State Examination score, related to the diagnostic classification of patients.This model uses various clinical attributes to provide accurate MMSE predictions, succeeding in correcting an important percentage of cases that contain previously identified miscalculated scores in our dataset. Furthermore, we provide an effective classification mechanism for automatically identifying patient episodes with inaccurate MMSE values with high confidence. These tools can be combined to assist clinicians in automatically finding episodes within patient medical records where the MMSE score is probably miscalculated and estimating what the correct value should be. This provides valuable support in the decision making process for diagnosing potential dementia patients. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

12 pages, 831 KiB  

Open AccessArticle

k-Labelsets Method for Multi-Label ECG Signal Classification Based on SE-ResNet

by Jihye Yoo, Yeongbong Jin, Bonggyun Ko and Min-Soo Kim

Appl. Sci. 2021, 11(16), 7758; https://doi.org/10.3390/app11167758 - 23 Aug 2021

Cited by 4 | Viewed by 2459

Abstract

Cardiovascular diseases are the leading cause of death globally. The ECG is the most commonly used tool for diagnosing cardiovascular diseases, and, recently, there are a number of attempts to use deep learning to analyze ECG. In this study, we propose a method [...] Read more.

Cardiovascular diseases are the leading cause of death globally. The ECG is the most commonly used tool for diagnosing cardiovascular diseases, and, recently, there are a number of attempts to use deep learning to analyze ECG. In this study, we propose a method for performing multi-label classification on standard ECG (12-lead with duration of 10 s) data. We used the ResNet model that can perform residual learning as a base model for classification in this work, and we tried to improve performance through SE-ResNet, which added squeeze and excitation blocks on the plain ResNet. As a result of the experiment, it was possible to induce overall performance improvement through squeeze and excitation blocks. In addition, the random k-labelsets (RAKEL) algorithm was applied to improve the performance in multi-label classification problems. As a result, the model that applied soft voting through the RAKEL algorithm to SE-ResNet-34 represented the best performance, and the average performances according to the number of label divisions k were achieved 0.99%, 88.49%, 92.43%, 90.54%, and 93.40% in exact match, accuracy, F1-score, precision, and recall, respectively. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

13 pages, 2739 KiB  

Open AccessArticle

Effect of Mobile-Based Lifestyle Intervention on Weight Loss among the Overweight and Obese Elderly Population in China: A Randomized Controlled Trial

by Mingzhu Zhou, Na Zhang, Yu Zhang, Xinyu Yan, Muxia Li, Wen Guo, Xiaohui Guo, Hairong He, Kaiwei Guo and Guansheng Ma

Int. J. Environ. Res. Public Health 2021, 18(16), 8825; https://doi.org/10.3390/ijerph18168825 - 21 Aug 2021

Cited by 4 | Viewed by 2339

Abstract

Background and Objective: Overweight or obesity, as an independent risk factor for chronic diseases, has been on the rise globally. Adopting a healthy lifestyle is positive to weight control. Mobile-based lifestyle interventions have shown potential benefits in weight loss, but most studies were [...] Read more.

Background and Objective: Overweight or obesity, as an independent risk factor for chronic diseases, has been on the rise globally. Adopting a healthy lifestyle is positive to weight control. Mobile-based lifestyle interventions have shown potential benefits in weight loss, but most studies were carried out among non-elderly population, so it is necessary to perform well-designed randomized controlled trials among the elderly with overweight or obesity. The purpose of this study is to assess the effect of mobile-based lifestyle intervention on weight loss among the overweight and obese elderly population in China. Methods: This is a prospective, open-labeled, three-month, multicenter, randomized controlled trial involving 750 participants from five cities who were randomly assigned to dietary and physical activity interventions group (DPG; mobile phone with the App and bracelet), physical activity interventions group (PG; mobile phone with the App and bracelet) and control group (CG; no interventions and kept their lifestyle as before). The outcomes evaluated were changes in weight, body mass index (BMI), waist circumference (WC), and hip circumference (HC). Results: In total, 642 (85.6%) participants completed the study, 237 (94.8%), 203 (81.2%), and 202 (80.8%) for DPG, PG, and CG respectively. Comparing with PG and CG, the DPG showed a significant decrease in all outcomes after three months, including body weight (−4.1 kg vs. −1.0 kg; −4.1 kg vs. −0.8 kg; p < 0.05), BMI (−1.6 kg/m² vs. −0.4 kg/m²; −1.6 kg/m² vs. −0.3 kg/m²; p < 0.05), WC (−2.8 cm vs. −0.1 cm; −2.8 cm vs. −0.5 cm; p < 0.05), and HC (−3.8 cm vs. −1.3 cm; −3.8 cm vs. −1.3 cm; p < 0.05). Similar effects were seen across sex and BMI subgroups. Conclusions: Mobile-based lifestyle intervention obtained beneficial effect in weight loss among the elderly with overweight or obesity. Nevertheless, further studies are needed to confirm the effectiveness and its sustainability. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

14 pages, 4703 KiB  

Open AccessArticle

Interactive Machine Learning-Based Multi-Label Segmentation of Solid Tumors and Organs

by Dimitrios Bounias, Ashish Singh, Spyridon Bakas, Sarthak Pati, Saima Rathore, Hamed Akbari, Michel Bilello, Benjamin A. Greenberger, Joseph Lombardo, Rhea D. Chitalia, Nariman Jahani, Aimilia Gastounioti, Michelle Hershman, Leonid Roshkovan, Sharyn I. Katz, Bardia Yousefi, Carolyn Lou, Amber L. Simpson, Richard K. G. Do, Russell T. Shinohara, Despina Kontos, Konstantina Nikita and Christos Davatzikosadd Show full author list remove Hide full author list

Appl. Sci. 2021, 11(16), 7488; https://doi.org/10.3390/app11167488 - 15 Aug 2021

Cited by 5 | Viewed by 3225

Abstract

We seek the development and evaluation of a fast, accurate, and consistent method for general-purpose segmentation, based on interactive machine learning (IML). To validate our method, we identified retrospective cohorts of 20 brain, 50 breast, and 50 lung cancer patients, as well as [...] Read more.

We seek the development and evaluation of a fast, accurate, and consistent method for general-purpose segmentation, based on interactive machine learning (IML). To validate our method, we identified retrospective cohorts of 20 brain, 50 breast, and 50 lung cancer patients, as well as 20 spleen scans, with corresponding ground truth annotations. Utilizing very brief user training annotations and the adaptive geodesic distance transform, an ensemble of SVMs is trained, providing a patient-specific model applied to the whole image. Two experts segmented each cohort twice with our method and twice manually. The IML method was faster than manual annotation by 53.1% on average. We found significant (p < 0.001) overlap difference for spleen (Dice_IML/Dice_Manual = 0.91/0.87), breast tumors (Dice_IML/Dice_Manual = 0.84/0.82), and lung nodules (Dice_IML/Dice_Manual = 0.78/0.83). For intra-rater consistency, a significant (p = 0.003) difference was found for spleen (Dice_IML/Dice_Manual = 0.91/0.89). For inter-rater consistency, significant (p < 0.045) differences were found for spleen (Dice_IML/Dice_Manual = 0.91/0.87), breast (Dice_IML/Dice_Manual = 0.86/0.81), lung (Dice_IML/Dice_Manual = 0.85/0.89), the non-enhancing (Dice_IML/Dice_Manual = 0.79/0.67) and the enhancing (Dice_IML/Dice_Manual = 0.79/0.84) brain tumor sub-regions, which, in aggregation, favored our method. Quantitative evaluation for speed, spatial overlap, and consistency, reveals the benefits of our proposed method when compared with manual annotation, for several clinically relevant problems. We publicly release our implementation through CaPTk (Cancer Imaging Phenomics Toolkit) and as an MITK plugin. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

17 pages, 8459 KiB  

Open AccessArticle

Fast Pre-Diagnosis of Neoplastic Changes in Cytology Images Using Machine Learning

by Jakub Caputa, Daria Łukasik, Maciej Wielgosz, Michał Karwatowski, Rafał Frączek, Paweł Russek and Kazimierz Wiatr

Appl. Sci. 2021, 11(16), 7181; https://doi.org/10.3390/app11167181 - 04 Aug 2021

Cited by 2 | Viewed by 1877

Abstract

We present the experiment results to use the YOLOv3 neural network architecture to automatically detect tumor cells in cytological samples taken from the skin in canines. A rich dataset of 1219 smeared sample images with 28,149 objects was gathered and annotated by the [...] Read more.

We present the experiment results to use the YOLOv3 neural network architecture to automatically detect tumor cells in cytological samples taken from the skin in canines. A rich dataset of 1219 smeared sample images with 28,149 objects was gathered and annotated by the vet doctor to perform the experiments. It covers three types of common round cell neoplasms: mastocytoma, histiocytoma, and lymphoma. The dataset has been thoroughly described in the paper and is publicly available. The YOLOv3 neural network architecture was trained using various schemes involving original dataset modification and the different model parameters. The experiments showed that the prototype model achieved 0.7416 mAP, which outperforms the state-of-the-art machine learning and human estimated results. We also provided a series of analyses that may facilitate ML-based solutions by casting more light on some aspects of its performance. We also presented the main discrepancies between ML-based and human-based diagnoses. This outline may help depict the scenarios and how the automated tools may support the diagnosis process. Full article

(This article belongs to the Topic Artificial Intelligence in Healthcare)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-71