Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Application of Data Analytics in Smart Healthcare
share announcement

Application of Data Analytics in Smart Healthcare

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (25 August 2022) | Viewed by 17858

Special Issue Editors

Prof. Dr. Konstantinos E. Psannis

E-Mail Website
Guest Editor
Department of Applied Informatics, University of Macedonia, 54124 Thessaloniki, Greece
Interests: haptics; IoT; HCI
Special Issues, Collections and Topics in MDPI journals
Dr. Christos L. Stergiou

E-Mail Website
Guest Editor
Department of Applied Informatics, School of Information Sciences, University of Macedonia, Thessaloniki, Greece
Interests: multimodal data communications systems; cloud transmission/streaming/synchronization; wireless communication systems; evolution of WiMAX technology; science information network; Internet of Things; cloud computing; big data
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, the rapid increase of digitalization and emerging technology appearing in the healthcare sector has contributed to the improvement of patient care and attention. Various technologies, such as the Internet of Medical Things (IoMT), wearable devices, a huge amount of healthcare data (eHealth Big Data), smart monitoring systems, and machine learning data analysis systems are being generated in more formats than ever before. Additionally, the scope and need of data analytics has become greater due to the rapid use of new software and technologies that make it easier to examine large volumes of data for hidden details. All these emerging technologies could be combined under the “management” of software solutions, that is, the smart applications. Applications could include data analytics for preventing diseases by the early recognition of risks, and tools recommending preventive plans. Moreover, another use of these applications is medical imaging, wherein the algorithms efficiently interpret X-rays, MRIs, mammograms, and other types of images, helping in the identification of patterns in the data and the detection of tumors and organ anomalies. Additionally, these applications could represent the future of smart healthcare because they could be used for treating home-based patients. The application of data analytics in remote in-home monitoring makes it easier for doctors to stay in touch with patients.

Topics of interest include but are not limited to the following:

  • Smart Monitoring systems for healthcare;
  • Health data collection and management in smart buildings;
  • Internet of Things sensor management over a wireless network in smart buildings;
  • Machine learning medical big data analytics in the cloud;
  • Internet of Things Sensor networks in artificial intelligence;
  • Machine learning with big data for smart healthcare;
  • Big data for the Internet of Medical Things;
  • Challenges and applications of big data in smart healthcare systems;
  • Security and privacy issues in Internet of Medical Things-enabled systems.

Prof. Dr. Konstantinos E. Psannis
Dr. Christos L. Stergiou
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sensor management
  • data collection
  • Internet of Medical Things
  • big data
  • smart buildings
  • smart health applications
  • analytics
  • cloud computing
  • machine learning
  • monitoring

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

10 pages, 2979 KiB  
Article
Utility of Features in a Natural-Language-Processing-Based Clinical De-Identification Model Using Radiology Reports for Advanced NSCLC Patients
by Tanmoy Paul, Humayera Islam, Nitesh Singh, Yaswitha Jampani, Teja Venkat Pavan Kotapati, Preethi Aishwarya Tautam, Md Kamruz Zaman Rana, Vasanthi Mandhadi, Vishakha Sharma, Michael Barnes, Richard D. Hammer and Abu Saleh Mohammad Mosa
Appl. Sci. 2022, 12(19), 9976; https://doi.org/10.3390/app12199976 - 04 Oct 2022
Cited by 1 | Viewed by 1235
Abstract
The de-identification of clinical reports is essential to protect the confidentiality of patients. The natural-language-processing-based named entity recognition (NER) model is a widely used technique of automatic clinical de-identification. The performance of such a machine learning model relies largely on the proper selection [...] Read more.
The de-identification of clinical reports is essential to protect the confidentiality of patients. The natural-language-processing-based named entity recognition (NER) model is a widely used technique of automatic clinical de-identification. The performance of such a machine learning model relies largely on the proper selection of features. The objective of this study was to investigate the utility of various features in a conditional-random-field (CRF)-based NER model. Natural language processing (NLP) toolkits were used to annotate the protected health information (PHI) from a total of 10,239 radiology reports that were divided into seven types. Multiple features were extracted by the toolkit and the NER models were built using these features and their combinations. A total of 10 features were extracted and the performance of the models was evaluated based on their precision, recall, and F1-score. The best-performing features were n-gram, prefix-suffix, word embedding, and word shape. These features outperformed others across all types of reports. The dataset we used was large in volume and divided into multiple types of reports. Such a diverse dataset made sure that the results were not subject to a small number of structured texts from where a machine learning model can easily learn the features. The manual de-identification of large-scale clinical reports is impractical. This study helps to identify the best-performing features for building an NER model for automatic de-identification from a wide array of features mentioned in the literature. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

21 pages, 3186 KiB  
Article
A Multi-Agent Approach Used to Predict Long-Term Glucose Oscillation in Individuals with Type 1 Diabetes
by João Paulo Aragão Pereira, Anarosa Alves Franco Brandão, Joyce da Silva Bevilacqua and Maria Lucia Cardillo Côrrea-Giannella
Appl. Sci. 2022, 12(19), 9641; https://doi.org/10.3390/app12199641 - 26 Sep 2022
Cited by 2 | Viewed by 1222
Abstract
The glucose–insulin regulatory system and its glucose oscillations is a recurring theme in the literature because of its impact on human lives, mostly the ones affected by diabetes mellitus. Several approaches have been proposed, from mathematical to data-based models, with the aim of [...] Read more.
The glucose–insulin regulatory system and its glucose oscillations is a recurring theme in the literature because of its impact on human lives, mostly the ones affected by diabetes mellitus. Several approaches have been proposed, from mathematical to data-based models, with the aim of modeling the glucose oscillation curve. Having such a curve, it is possible to predict when to inject insulin in type 1 diabetes (T1D) individuals. However, the literature presents prediction horizons of no longer than 6 h, which could be a problem considering their sleeping time. This work presents Tesseratus, a model that adopts a multi-agent approach used to combine machine learning and mathematical modeling to predict the glucose oscillation for up to 8 h. Tesseratus can support endocrinologists and provide personalized recommendations for T1D individuals to keep their glucose concentration in the ideal range. It brings pioneering results in an experiment with seven real T1D individuals. Using the Parkes error grid as an evaluation metric, it can be depicted that 93.7% of measurements fall in zones A and B during the night period with MAE 27.77 mg/dL. It is our claim that Tesseratus will be a reference for the classification of a glucose prediction model, supporting the mitigation of long-term complications in the T1D individuals. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

28 pages, 3488 KiB  
Article
Exploitation of Emerging Technologies and Advanced Networks for a Smart Healthcare System
by Georgios M. Minopoulos, Vasileios A. Memos, Christos L. Stergiou, Konstantinos D. Stergiou, Andreas P. Plageras, Maria P. Koidou and Konstantinos E. Psannis
Appl. Sci. 2022, 12(12), 5859; https://doi.org/10.3390/app12125859 - 09 Jun 2022
Cited by 13 | Viewed by 2584
Abstract
Current medical methods still confront numerous limitations and barriers to detect and fight against illnesses and disorders. The introduction of emerging technologies in the healthcare industry is anticipated to enable novel medical techniques for an efficient and effective smart healthcare system. Internet of [...] Read more.
Current medical methods still confront numerous limitations and barriers to detect and fight against illnesses and disorders. The introduction of emerging technologies in the healthcare industry is anticipated to enable novel medical techniques for an efficient and effective smart healthcare system. Internet of Things (IoT), Wireless Sensor Networks (WSN), Big Data Analytics (BDA), and Cloud Computing (CC) can play a vital role in the instant detection of illnesses, diseases, viruses, or disorders. Complicated techniques such as Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) could provide acceleration in drug and antibiotics discovery. Moreover, the integration of visualization techniques such as Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) with Tactile Internet (TI), can be applied from the medical staff to provide the most accurate diagnosis and treatment for the patients. A novel system architecture, which combines several future technologies, is proposed in this paper. The objective is to describe the integration of a mixture of emerging technologies in assistance with advanced networks to provide a smart healthcare system that may be established in hospitals or medical centers. Such a system will be able to deliver immediate and accurate data to the medical stuff in order to aim them in order to provide precise patient diagnosis and treatment. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

19 pages, 4464 KiB  
Article
Analysis of Functional Layout in Emergency Departments (ED). Shedding Light on the Free Standing Emergency Department (FSED) Model
by Andrea Brambilla, Silvia Mangili, Mohana Das, Sanchit Lal and Stefano Capolongo
Appl. Sci. 2022, 12(10), 5099; https://doi.org/10.3390/app12105099 - 18 May 2022
Cited by 9 | Viewed by 3652
Abstract
The ever-increasing number of hospital Emergency Department (ED) visits pose a challenge to the effective running of health systems in many countries globally and multiple strategies have been adopted over the years to tackle the plight. According to a systematic review of the [...] Read more.
The ever-increasing number of hospital Emergency Department (ED) visits pose a challenge to the effective running of health systems in many countries globally and multiple strategies have been adopted over the years to tackle the plight. According to a systematic review of the available literature, of the numerous models of healthcare systems used to address the issue in western countries, the FSED Model has the greatest potential for reducing hospital ED overcrowding as it can reduce the additional load by diverting minor cases, freeing up space for more urgent cases. The aim of the study is to shed light on the Free Standing Emergency Department (FSED) model and compare it with the traditional Hospital Based Emergency Department (HBED) in international contexts. In this study, 23 papers have been collected in a literature review and the main features have been highlighted; 12 case studies have been analyzed from a layout point of view and data have been collected in terms of surfaces, functions, and flow patterns. The percentages of floor areas devoted to each function have been compared to define evolution strategies in the development of emergency healthcare models and analyses. The use of FSED models is an interesting way to face the overcrowding problem and a specific range for functional area layout has been identified. Further studies on its application in different contexts are encouraged. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

17 pages, 2787 KiB  
Article
MOMIC: A Multi-Omics Pipeline for Data Analysis, Integration and Interpretation
by Laura Madrid-Márquez, Cristina Rubio-Escudero, Beatriz Pontes, Antonio González-Pérez, José C. Riquelme and Maria E. Sáez
Appl. Sci. 2022, 12(8), 3987; https://doi.org/10.3390/app12083987 - 14 Apr 2022
Cited by 1 | Viewed by 4159
Abstract
Background and Objectives: The burst of high-throughput omics technologies has given rise to a new era in systems biology, offering an unprecedented scenario for deriving meaningful biological knowledge through the integration of different layers of information. Methods: We have developed a new software [...] Read more.
Background and Objectives: The burst of high-throughput omics technologies has given rise to a new era in systems biology, offering an unprecedented scenario for deriving meaningful biological knowledge through the integration of different layers of information. Methods: We have developed a new software tool, MOMIC, that guides the user through the application of different analysis on a wide range of omic data, from the independent single-omics analysis to the combination of heterogeneous data at different molecular levels. Results: The proposed pipeline is developed as a collection of Jupyter notebooks, easily editable, reproducible and well documented. It can be modified to accommodate new analysis workflows and data types. It is accessible via momic.us.es, and as a docker project available at github that can be locally installed. Conclusions: MOMIC offers a complete analysis environment for analysing and integrating multi-omics data in a single, easy-to-use platform. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

Review

Jump to: Research

28 pages, 3203 KiB  
Review
IoT-Based Big Data Secure Transmission and Management over Cloud System: A Healthcare Digital Twin Scenario
by Christos L. Stergiou, Maria P. Koidou and Konstantinos E. Psannis
Appl. Sci. 2023, 13(16), 9165; https://doi.org/10.3390/app13169165 - 11 Aug 2023
Viewed by 1527
Abstract
The Internet of Things (IoT) was introduced as a recently developed technology in the telecommunications field. It is a network made up of real-world objects, things, and gadgets that are enabled by sensors and software that can communicate data with one another. Systems [...] Read more.
The Internet of Things (IoT) was introduced as a recently developed technology in the telecommunications field. It is a network made up of real-world objects, things, and gadgets that are enabled by sensors and software that can communicate data with one another. Systems for monitoring gather, exchange, and process video and image data captured by sensors and cameras across a network. Furthermore, the novel concept of Digital Twin offers new opportunities so that new proposed systems can work virtually, but without differing in operation from a “real” system. This paper is a meticulous survey of the IoT and monitoring systems to illustrate how their combination will improve certain types of the Monitoring systems of Healthcare–IoT in the Cloud. To achieve this goal, we discuss the characteristics of the IoT that improve the use of the types of monitoring systems over a Multimedia Transmission System in the Cloud. The paper also discusses some technical challenges of Multimedia in IoT, based on Healthcare data. Finally, it shows how the Mobile Cloud Computing (MCC) technology, settled as base technology, enhances the functionality of the IoT and has an impact on various types of monitoring technology, and also it proposes an algorithm approach to transmitting and processing video/image data through a Cloud-based Monitoring system. To gather pertinent data about the validity of our proposal in a more safe and useful way, we have implemented our proposal in a Digital Twin scenario of a Smart Healthcare system. The operation of the suggested scenario as a Digital Twin scenario offers a more sustainable and energy-efficient system and experimental findings ultimately demonstrate that the proposed system is more reliable and secure. Experimental results show the impact of our proposed model depicts the efficiency of the usage of a Cloud Management System operated over a Digital Twin scenario, using real-time large-scale data produced from the connected IoT system. Through these scenarios, we can observe that our proposal remains the best choice regardless of the time difference or energy load. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

11 pages, 909 KiB  
Review
A Machine Learning-Based Model for Epidemic Forecasting and Faster Drug Discovery
by Konstantinos D. Stergiou, Georgios M. Minopoulos, Vasileios A. Memos, Christos L. Stergiou, Maria P. Koidou and Konstantinos E. Psannis
Appl. Sci. 2022, 12(21), 10766; https://doi.org/10.3390/app122110766 - 24 Oct 2022
Cited by 7 | Viewed by 1980
Abstract
Today, healthcare system models should have high accuracy and sensitivity so that patients do not have a misdiagnosis. For this reason, sufficient knowledge of the area is required, with the medical staff being able to validate the correctness of their decisions. Therefore, artificial [...] Read more.
Today, healthcare system models should have high accuracy and sensitivity so that patients do not have a misdiagnosis. For this reason, sufficient knowledge of the area is required, with the medical staff being able to validate the correctness of their decisions. Therefore, artificial intelligence (AI) in combination with other emerging technologies could provide many benefits in the medical sector. In this paper, we demonstrate the combination of Internet of Things (IoT) and cloud computing (CC) with AI-related techniques such as artificial intelligence (AI), machine learning (ML), deep learning (DL), and neural networks (NN) in order to provide a useful approach for scientists and doctors. Our proposed model makes use of these immersive technologies so as to provide epidemic forecasting and help accelerate drug and antibiotic discovery. Full article
(This article belongs to the Special Issue Application of Data Analytics in Smart Healthcare)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop