Research

Jump to: Review

18 pages, 4350 KiB

Open AccessArticle

Implementation of an Intelligent EMG Signal Classifier Using Open-Source Hardware

by Nelson Cárdenas-Bolaño, Aura Polo and Carlos Robles-Algarín

Computers 2023, 12(12), 263; https://doi.org/10.3390/computers12120263 - 18 Dec 2023

Viewed by 1536

This paper presents the implementation of an intelligent real-time single-channel electromyography (EMG) signal classifier based on open-source hardware. The article shows the experimental design, analysis, and implementation of a solution to identify four muscle movements from the forearm (extension, pronation, supination, and flexion), [...] Read more.

This paper presents the implementation of an intelligent real-time single-channel electromyography (EMG) signal classifier based on open-source hardware. The article shows the experimental design, analysis, and implementation of a solution to identify four muscle movements from the forearm (extension, pronation, supination, and flexion), for future applications in transradial active prostheses. An EMG signal acquisition instrument was developed, with a 20–450 Hz bandwidth and 2 kHz sampling rate. The signals were stored in a Database, as a multidimensional array, using a desktop application. Numerical and graphic analysis approaches for discriminative capacity were proposed for feature analysis and four feature sets were used to feed the classifier. Artificial Neural Networks (ANN) were implemented for time-domain EMG pattern recognition (PR). The system obtained a classification accuracy of 98.44% and response times per signal of 8.522 ms. Results suggest these methods allow us to understand, intuitively, the behavior of user information. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

13 pages, 2908 KiB

Open AccessArticle

Brain Pathology Classification of MR Images Using Machine Learning Techniques

by Nehad T. A. Ramaha, Ruaa M. Mahmood, Alaa Ali Hameed, Norma Latif Fitriyani, Ganjar Alfian and Muhammad Syafrudin

Computers 2023, 12(8), 167; https://doi.org/10.3390/computers12080167 - 19 Aug 2023

Viewed by 1540

Abstract

A brain tumor is essentially a collection of aberrant tissues, so it is crucial to classify tumors of the brain using MRI before beginning therapy. Tumor segmentation and classification from brain MRI scans using machine learning techniques are widely recognized as challenging and [...] Read more.

A brain tumor is essentially a collection of aberrant tissues, so it is crucial to classify tumors of the brain using MRI before beginning therapy. Tumor segmentation and classification from brain MRI scans using machine learning techniques are widely recognized as challenging and important tasks. The potential applications of machine learning in diagnostics, preoperative planning, and postoperative evaluations are substantial. Accurate determination of the tumor’s location on a brain MRI is of paramount importance. The advancement of precise machine learning classifiers and other technologies will enable doctors to detect malignancies without requiring invasive procedures on patients. Pre-processing, skull stripping, and tumor segmentation are the steps involved in detecting a brain tumor and measurement (size and form). After a certain period, CNN models get overfitted because of the large number of training images used to train them. That is why this study uses deep CNN to transfer learning. CNN-based Relu architecture and SVM with fused retrieved features via HOG and LPB are used to classify brain MRI tumors (glioma or meningioma). The method’s efficacy is measured in terms of precision, recall, F-measure, and accuracy. This study showed that the accuracy of the SVM with combined LBP with HOG is 97%, and the deep CNN is 98%. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

13 pages, 2509 KiB

Open AccessArticle

Automated Diagnosis of Prostate Cancer Using mpMRI Images: A Deep Learning Approach for Clinical Decision Support

by Anil B. Gavade, Rajendra Nerli, Neel Kanwal, Priyanka A. Gavade, Shridhar Sunilkumar Pol and Syed Tahir Hussain Rizvi

Computers 2023, 12(8), 152; https://doi.org/10.3390/computers12080152 - 28 Jul 2023

Cited by 3 | Viewed by 1417

Abstract

Prostate cancer (PCa) is a significant health concern for men worldwide, where early detection and effective diagnosis can be crucial for successful treatment. Multiparametric magnetic resonance imaging (mpMRI) has evolved into a significant imaging modality in this regard, which provides detailed images of [...] Read more.

Prostate cancer (PCa) is a significant health concern for men worldwide, where early detection and effective diagnosis can be crucial for successful treatment. Multiparametric magnetic resonance imaging (mpMRI) has evolved into a significant imaging modality in this regard, which provides detailed images of the anatomy and tissue characteristics of the prostate gland. However, interpreting mpMRI images can be challenging for humans due to the wide range of appearances and features of PCa, which can be subtle and difficult to distinguish from normal prostate tissue. Deep learning (DL) approaches can be beneficial in this regard by automatically differentiating relevant features and providing an automated diagnosis of PCa. DL models can assist the existing clinical decision support system by saving a physician’s time in localizing regions of interest (ROIs) and help in providing better patient care. In this paper, contemporary DL models are used to create a pipeline for the segmentation and classification of mpMRI images. Our DL approach follows two steps: a U-Net architecture for segmenting ROI in the first stage and a long short-term memory (LSTM) network for classifying the ROI as either cancerous or non-cancerous. We trained our DL models on the I2CVB (Initiative for Collaborative Computer Vision Benchmarking) dataset and conducted a thorough comparison with our experimental setup. Our proposed DL approach, with simpler architectures and training strategy using a single dataset, outperforms existing techniques in the literature. Results demonstrate that the proposed approach can detect PCa disease with high precision and also has a high potential to improve clinical assessment. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

19 pages, 8279 KiB

Open AccessArticle

A Deep Learning Network with Aggregation Residual Transformation for Human Activity Recognition Using Inertial and Stretch Sensors

by Sakorn Mekruksavanich and Anuchit Jitpattanakul

Computers 2023, 12(7), 141; https://doi.org/10.3390/computers12070141 - 17 Jul 2023

Cited by 9 | Viewed by 1138

Abstract

With the rise of artificial intelligence, sensor-based human activity recognition (S-HAR) is increasingly being employed in healthcare monitoring for the elderly, fitness tracking, and patient rehabilitation using smart devices. Inertial sensors have been commonly used for S-HAR, but wearable devices have been demanding [...] Read more.

With the rise of artificial intelligence, sensor-based human activity recognition (S-HAR) is increasingly being employed in healthcare monitoring for the elderly, fitness tracking, and patient rehabilitation using smart devices. Inertial sensors have been commonly used for S-HAR, but wearable devices have been demanding more comfort and flexibility in recent years. Consequently, there has been an effort to incorporate stretch sensors into S-HAR with the advancement of flexible electronics technology. This paper presents a deep learning network model, utilizing aggregation residual transformation, that can efficiently extract spatial–temporal features and perform activity classification. The efficacy of the suggested model was assessed using the w-HAR dataset, which included both inertial and stretch sensor data. This dataset was used to train and test five fundamental deep learning models (CNN, LSTM, BiLSTM, GRU, and BiGRU), along with the proposed model. The primary objective of the w-HAR investigations was to determine the feasibility of utilizing stretch sensors for recognizing human actions. Additionally, this study aimed to explore the effectiveness of combining data from both inertial and stretch sensors in S-HAR. The results clearly demonstrate the effectiveness of the proposed approach in enhancing HAR using inertial and stretch sensors. The deep learning model we presented achieved an impressive accuracy of 97.68%. Notably, our method outperformed existing approaches and demonstrated excellent generalization capabilities. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

15 pages, 3539 KiB

Open AccessArticle

Peer-to-Peer Federated Learning for COVID-19 Detection Using Transformers

by Mohamed Chetoui and Moulay A. Akhloufi

Computers 2023, 12(5), 106; https://doi.org/10.3390/computers12050106 - 17 May 2023

Cited by 3 | Viewed by 1689

Abstract

The simultaneous advances in deep learning and the Internet of Things (IoT) have benefited distributed deep learning paradigms. Federated learning is one of the most promising frameworks, where a server works with local learners to train a global model. The intrinsic heterogeneity of [...] Read more.

The simultaneous advances in deep learning and the Internet of Things (IoT) have benefited distributed deep learning paradigms. Federated learning is one of the most promising frameworks, where a server works with local learners to train a global model. The intrinsic heterogeneity of IoT devices, or non-independent and identically distributed (Non-I.I.D.) data, combined with the unstable communication network environment, causes a bottleneck that slows convergence and degrades learning efficiency. Additionally, the majority of weight averaging-based model aggregation approaches raise questions about learning fairness. In this paper, we propose a peer-to-peer federated learning (P2PFL) framework based on Vision Transformers (ViT) models to help solve some of the above issues and classify COVID-19 vs. normal cases on Chest-X-Ray (CXR) images. Particularly, clients jointly iterate and aggregate the models in order to build a robust model. The experimental results demonstrate that the proposed approach is capable of significantly improving the performance of the model with an Area Under Curve (AUC) of 0.92 and 0.99 for hospital-1 and hospital-2, respectively. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

19 pages, 3763 KiB

Open AccessArticle

Rethinking Densely Connected Convolutional Networks for Diagnosing Infectious Diseases

by Prajoy Podder, Fatema Binte Alam, M. Rubaiyat Hossain Mondal, Md Junayed Hasan, Ali Rohan and Subrato Bharati

Computers 2023, 12(5), 95; https://doi.org/10.3390/computers12050095 - 02 May 2023

Cited by 4 | Viewed by 2102

Abstract

Due to its high transmissibility, the COVID-19 pandemic has placed an unprecedented burden on healthcare systems worldwide. X-ray imaging of the chest has emerged as a valuable and cost-effective tool for detecting and diagnosing COVID-19 patients. In this study, we developed a deep [...] Read more.

Due to its high transmissibility, the COVID-19 pandemic has placed an unprecedented burden on healthcare systems worldwide. X-ray imaging of the chest has emerged as a valuable and cost-effective tool for detecting and diagnosing COVID-19 patients. In this study, we developed a deep learning model using transfer learning with optimized DenseNet-169 and DenseNet-201 models for three-class classification, utilizing the Nadam optimizer. We modified the traditional DenseNet architecture and tuned the hyperparameters to improve the model’s performance. The model was evaluated on a novel dataset of 3312 X-ray images from publicly available datasets, using metrics such as accuracy, recall, precision, F1-score, and the area under the receiver operating characteristics curve. Our results showed impressive detection rate accuracy and recall for COVID-19 patients, with 95.98% and 96% achieved using DenseNet-169 and 96.18% and 99% using DenseNet-201. Unique layer configurations and the Nadam optimization algorithm enabled our deep learning model to achieve high rates of accuracy not only for detecting COVID-19 patients but also for identifying normal and pneumonia-affected patients. The model’s ability to detect lung problems early on, as well as its low false-positive and false-negative rates, suggest that it has the potential to serve as a reliable diagnostic tool for a variety of lung diseases. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

19 pages, 543 KiB

Open AccessArticle

An Integrated Statistical and Clinically Applicable Machine Learning Framework for the Detection of Autism Spectrum Disorder

by Md. Jamal Uddin, Md. Martuza Ahamad, Prodip Kumar Sarker, Sakifa Aktar, Naif Alotaibi, Salem A. Alyami, Muhammad Ashad Kabir and Mohammad Ali Moni

Computers 2023, 12(5), 92; https://doi.org/10.3390/computers12050092 - 30 Apr 2023

Cited by 6 | Viewed by 2189

Abstract

Autism Spectrum Disorder (ASD) is a neurological impairment condition that severely impairs cognitive, linguistic, object recognition, interpersonal, and communication skills. Its main cause is genetic, and early treatment and identification can reduce the patient’s expensive medical costs and lengthy examinations. We developed a [...] Read more.

Autism Spectrum Disorder (ASD) is a neurological impairment condition that severely impairs cognitive, linguistic, object recognition, interpersonal, and communication skills. Its main cause is genetic, and early treatment and identification can reduce the patient’s expensive medical costs and lengthy examinations. We developed a machine learning (ML) architecture that is capable of effectively analysing autistic children’s datasets and accurately classifying and identifying ASD traits. We considered the ASD screening dataset of toddlers in this study. We utilised the SMOTE method to balance the dataset, followed by feature transformation and selection methods. Then, we utilised several classification techniques in conjunction with a hyperparameter optimisation approach. The AdaBoost method yielded the best results among the classifiers. We employed ML and statistical approaches to identify the most crucial characteristics for the rapid recognition of ASD patients. We believe our proposed framework could be useful for early diagnosis and helpful for clinicians. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

19 pages, 649 KiB

Open AccessArticle

Machine Learning Model for Predicting Epidemics

by Patrick Loola Bokonda, Moussa Sidibe, Nissrine Souissi and Khadija Ouazzani-Touhami

Computers 2023, 12(3), 54; https://doi.org/10.3390/computers12030054 - 28 Feb 2023

Cited by 1 | Viewed by 1907

Abstract

COVID-19 has raised the issue of fighting epidemics. We were able to realize that in this fight, countering the spread of the disease was the main goal and we propose to contribute to it. To achieve this, we propose an enriched model of [...] Read more.

COVID-19 has raised the issue of fighting epidemics. We were able to realize that in this fight, countering the spread of the disease was the main goal and we propose to contribute to it. To achieve this, we propose an enriched model of Random Forest (RF) that we called RF EP (EP for Epidemiological Prediction). RF is based on the Forest RI algorithm, proposed by Leo Breiman. Our model (RF EP) is based on a modified version of Forest RI that we called Forest EP. Operations added on Forest RI to obtain Forest EP are as follows: the selection of significant variables, the standardization of data, the reduction in dimensions, and finally the selection of new variables that best synthesize information the algorithm needs. This study uses a data set designed for classification studies to predict whether a patient is suffering from COVID-19 based on the following 11 variables: Country, Age, Fever, Bodypain, Runny_nose, Difficult_in_breathing, Nasal_congestion, Sore_throat, Gender, Severity, and Contact_with_covid_patient. We compared default RF to five other machine learning models: GNB, LR, SVM, KNN, and DT. RF proved to be the best classifier of all with the following metrics: Accuracy (94.9%), Precision (94.0%), Recall (96.6%), and F1 Score (95.2%). Our model, RF EP, produced the following metrics: Accuracy (94.9%), Precision (93.1%), Recall (97.7%), and F1 Score (95.3%). The performance gain by RF EP on the Recall metric compared to default RF allowed us to propose a new model with a better score than default RF in the limitation of the virus propagation on the dataset used in this study. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

23 pages, 6706 KiB

Open AccessArticle

Channel Intensity and Edge-Based Estimation of Heart Rate via Smartphone Recordings

by Anusha Krishnamoorthy, G. Muralidhar Bairy, Nandish Siddeshappa, Hilda Mayrose, Niranjana Sampathila and Krishnaraj Chadaga

Computers 2023, 12(2), 43; https://doi.org/10.3390/computers12020043 - 17 Feb 2023

Cited by 1 | Viewed by 1264

Abstract

Smartphones, today, come equipped with a wide variety of sensors and high-speed processors that can capture, process, store, and communicate different types of data. Coupled with their ubiquity in recent years, these devices show potential as practical and portable healthcare monitors that are [...] Read more.

Smartphones, today, come equipped with a wide variety of sensors and high-speed processors that can capture, process, store, and communicate different types of data. Coupled with their ubiquity in recent years, these devices show potential as practical and portable healthcare monitors that are both cost-effective and accessible. To this end, this study focuses on examining the feasibility of smartphones in estimating the heart rate (HR), using video recordings of the users’ fingerprints. The proposed methodology involves two-stage processing that combines channel-intensity-based approaches (Channel-Intensity mode/Counter method) and a novel technique that relies on the spatial and temporal position of the recorded fingerprint edges (Edge-Detection mode). The dataset used here included 32 fingerprint video recordings taken from 6 subjects, using the rear camera of 2 smartphone models. Each video clip was first validated to determine whether it was suitable for Channel-Intensity mode or Edge-Detection mode, followed by further processing and heart rate estimation in the selected mode. The relative accuracy for recordings via the Edge-Detection mode was 93.04%, with a standard error of estimates (SEE) of 6.55 and Pearson’s correlation r > 0.91, while the Channel-Intensity mode showed a relative accuracy of 92.75%, with an SEE of 5.95 and a Pearson’s correlation r > 0.95. Further statistical analysis was also carried out using Pearson’s correlation test and the Bland–Altman method to verify the statistical significance of the results. The results thus show that the proposed methodology, through smartphones, is a potential alternative to existing technologies for monitoring a person’s heart rate. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Graphical abstract

15 pages, 874 KiB

Open AccessArticle

Supervised Machine Learning Models for Liver Disease Risk Prediction

by Elias Dritsas and Maria Trigka

Computers 2023, 12(1), 19; https://doi.org/10.3390/computers12010019 - 13 Jan 2023

Cited by 18 | Viewed by 5571

Abstract

The liver constitutes the largest gland in the human body and performs many different functions. It processes what a person eats and drinks and converts food into nutrients that need to be absorbed by the body. In addition, it filters out harmful substances [...] Read more.

The liver constitutes the largest gland in the human body and performs many different functions. It processes what a person eats and drinks and converts food into nutrients that need to be absorbed by the body. In addition, it filters out harmful substances from the blood and helps tackle infections. Exposure to viruses or dangerous chemicals can damage the liver. When this organ is damaged, liver disease can develop. Liver disease refers to any condition that causes damage to the liver and may affect its function. It is a serious condition that threatens human life and requires urgent medical attention. Early prediction of the disease using machine learning (ML) techniques will be the point of interest in this study. Specifically, in the content of this research work, various ML models and Ensemble methods were evaluated and compared in terms of Accuracy, Precision, Recall, F-measure and area under the curve (AUC) in order to predict liver disease occurrence. The experimental results showed that the Voting classifier outperforms the other models with an accuracy, recall, and F-measure of 80.1%, a precision of 80.4%, and an AUC equal to 88.4% after SMOTE with 10-fold cross-validation. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

Review

Jump to: Research

11 pages, 1083 KiB

Open AccessReview

Pressure-Based Posture Classification Methods and Algorithms: A Systematic Review

by Luís Fonseca, Fernando Ribeiro and José Metrôlho

Computers 2023, 12(5), 104; https://doi.org/10.3390/computers12050104 - 15 May 2023

Cited by 1 | Viewed by 1209

Abstract

There are many uses for machine learning in everyday life and there is a steady increase in the field of medicine; the use of such technologies facilitates the tiresome work of health professionals by either automating repetitive tasks or making them simpler. Bed-related [...] Read more.

There are many uses for machine learning in everyday life and there is a steady increase in the field of medicine; the use of such technologies facilitates the tiresome work of health professionals by either automating repetitive tasks or making them simpler. Bed-related disorders are a great example where tedious tasks could be facilitated by machine learning algorithms, as suggested by many authors, by providing information on the posture of a particular bedded patient to health professionals. To assess the already existing studies in this field, this study provides a systematic review where the literature is analyzed to find correlations between the various factors involved in the making of such a system and how they perform. The overall findings suggest that there is only a significant relationship between the postures considered for classification and the resulting accuracy, despite some other factors such as the amount of data available providing some differences according to the type of algorithm used, with neural networks needing larger datasets. This study aims to increase awareness in this field and give future researchers information based on previous works’ strengths and limitations while giving some suggestions based on the literature review. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

12 pages, 565 KiB

Open AccessReview

Crossing the AI Chasm in Neurocritical Care

by Marco Cascella, Jonathan Montomoli, Valentina Bellini, Alessandro Vittori, Helena Biancuzzi, Francesca Dal Mas and Elena Giovanna Bignami

Computers 2023, 12(4), 83; https://doi.org/10.3390/computers12040083 - 19 Apr 2023

Cited by 1 | Viewed by 1841

Abstract

Despite the growing interest in possible applications of computer science and artificial intelligence (AI) in the field of neurocritical care (neuro-ICU), widespread clinical applications are still missing. In neuro-ICU, the collection and analysis in real time of large datasets can play a crucial [...] Read more.

Despite the growing interest in possible applications of computer science and artificial intelligence (AI) in the field of neurocritical care (neuro-ICU), widespread clinical applications are still missing. In neuro-ICU, the collection and analysis in real time of large datasets can play a crucial role in advancing this medical field and improving personalized patient care. For example, AI algorithms can detect subtle changes in brain activity or vital signs, alerting clinicians to potentially life-threatening conditions and facilitating rapid intervention. Consequently, data-driven AI and predictive analytics can greatly enhance medical decision making, diagnosis, and treatment, ultimately leading to better outcomes for patients. Nevertheless, there is a significant disparity between the current capabilities of AI systems and the potential benefits and applications that could be achieved with more advanced AI technologies. This gap is usually indicated as the AI chasm. In this paper, the underlying causes of the AI chasm in neuro-ICU are analyzed, along with proposed recommendations for utilizing AI to attain a competitive edge, foster innovation, and enhance patient outcomes. To bridge the AI divide in neurocritical care, it is crucial to foster collaboration among researchers, clinicians, and policymakers, with a focus on specific use cases. Additionally, strategic investments in AI technology, education and training, and infrastructure are needed to unlock the potential of AI technology. Before implementing a technology in patient care, it is essential to conduct thorough studies and establish clinical validation in real-world environments to ensure its effectiveness and safety. Finally, the development of ethical and regulatory frameworks is mandatory to ensure the secure and efficient deployment of AI technology throughout the process. Full article

(This article belongs to the Special Issue Machine and Deep Learning in the Health Domain)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine and Deep Learning in the Health Domain

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI