Precision Healthcare-Oriented Artificial Intelligence

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Bioelectronics".

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 16001

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung 413310, Taiwan
Interests: electronic circuits; development of medical instruments; cardiovascular measurement system; deep learning; machine learning; biomedical signal process; development of embedded systems in health care
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Biomedical Engineering, I-Shou University, Kaohsiung City 82445, Taiwan
Interests: design of biomedical instrument; sensor design and application; biomedical engineering; smart healthcare; medical electronics

E-Mail Website
Guest Editor
Biomedical Information Engineering Lab, The University of Aizu, Aizu-Wakamatsu City, Fukushima Prefecture 965-8580, Japan
Interests: biomedical instrumentation; signal processing; data analysis; seamless monitoring for daily healthcare; heaven–earth–human interaction; healthology
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Recent advances in the health informatics, the artificial intelligence and sensing technique have increasingly attracted lots of interests from both industry and academia. Moreover, the precision healthcare issue becomes more important and critical due to promising achievements in the studies related to big data and deep learning application. This special issue, titled as “Precision Healthcare-Oriented Artificial Intelligence”, will bring researchers and experts together to present and discuss the latest development and technical solutions concerning various aspects of advances in the artificial intelligence application in precision healthcare areas. This special issue welcomes your contribution of original unpublished articles focusing on theoretical analysis, biomedical signal processing, novel system architecture construction and integration, longitudinal and cross-sectional studies, and development of seamless monitoring devices.

Prof. Dr. Shing-Hong Liu
Prof. Dr. Jia-Jung Wang
Prof. Dr. Wenxi Chen
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. Electronics 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

  • Precision healthcare
  • Daily healthcare
  • Artificial intelligence
  • Sensor development
  • Wearable device

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 4185 KiB  
Article
Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach
by Waqas Haider Bangyal, Najeeb Ur Rehman, Asma Nawaz, Kashif Nisar, Ag. Asri Ag. Ibrahim, Rabia Shakir and Danda B. Rawat
Electronics 2022, 11(12), 1890; https://doi.org/10.3390/electronics11121890 - 16 Jun 2022
Cited by 23 | Viewed by 2344
Abstract
Facts can be exchanged in multiple fields with the help of disease-specific ontologies. A range of diverse values can be produced by mining ontological approaches for demonstrating disease mechanisms. Alzheimer’s disease (AD) is an incurable neurological brain illness. An early diagnosis of AD [...] Read more.
Facts can be exchanged in multiple fields with the help of disease-specific ontologies. A range of diverse values can be produced by mining ontological approaches for demonstrating disease mechanisms. Alzheimer’s disease (AD) is an incurable neurological brain illness. An early diagnosis of AD can be helpful for better treatment and the prevention of brain tissue destruction. Researchers have used machine learning techniques to predict the early detection of AD. However, Alzheimer’s disorders are still underexplored in the knowledge domain. In the biomedical field, the illustration of terminologies and notions is essential. Multiple methods are adopted to represent these notions, but ontologies are the most frequent and accurate. Ontology construction is a complex and time-consuming process. The designed ontology relies on Disease Ontology (DO), which is considered the benchmark in medical practice. Ontology reasoning mechanisms can be adopted for AD identification. In this paper, a deep convolutional neural network-based approach is proposed to diagnose Alzheimer’s disease, using an AD dataset acquired from Kaggle. Machine learning-based approaches (logistic regression, gradient boosting, XGB, SGD, MLP, SVM, KNN, random forest) are also used for a fair comparison. The simulation results are generated using three strategies (default parameters, 10-cross validation, and grid search), and MLP provides superior results on a default parameter strategy with an accuracy of 92.12%. Furthermore, the deep learning-based approach convolutional neural network (CNN) achieved an accuracy of 94.61%. The experimental results indicate that the construction of ontology, with the help of deep learning knowledge, can produce better results where the robustness and scalability can be enhanced. In comparisons to other methods, the CNN results are excellent and encouraging. Full article
(This article belongs to the Special Issue Precision Healthcare-Oriented Artificial Intelligence)
Show Figures

Figure 1

17 pages, 3288 KiB  
Article
Bathtub ECG as a Potential Alternative to Light Stress Test in Daily Life
by Tianhui Li and Wenxi Chen
Electronics 2022, 11(9), 1310; https://doi.org/10.3390/electronics11091310 - 20 Apr 2022
Cited by 1 | Viewed by 1627
Abstract
The exercise stress test (EST) is a common procedure to evaluate cardiovascular functions. However, the EST is not suitable for daily use, is sometimes risky, and even accompanies fatal incidents of myocardial infarction, arrhythmia, and sudden death during the test. The aim of [...] Read more.
The exercise stress test (EST) is a common procedure to evaluate cardiovascular functions. However, the EST is not suitable for daily use, is sometimes risky, and even accompanies fatal incidents of myocardial infarction, arrhythmia, and sudden death during the test. The aim of this study was to evaluate heart rate variability (HRV) behaviors in the EST and during bathing, and to explore if daily bathing can serve as a potential alternative means of performing the EST. Electrocardiogram (ECG) signals were collected from 10 healthy subjects during the EST and bathing test (BT). The EST follows the modified Bruce protocol. ECG collection in the BT was conducted at five water temperatures ranging from 37 to 41 degrees Celsius (°C); each BT lasted 15 min. Twenty-three HRV features were used to group different bathing conditions corresponding to the EST stages using the Voronoi diagram method in terms of HRV behaviors. In all equivalent EST stages of BTs at the five water temperatures, the low stage, medium stage, and high stage account for 17.86%, 52.86%, and 29.29%, respectively. The results show that higher water temperatures and longer bathing durations in BT correspond to higher stages in the EST. The BT at the most severe condition of 41 °C and 15 min corresponds to a high EST stage in terms of HRV behavior. The results suggest that daily bathing can serve not only for healthcare monitoring but also as a reference for an at-home alternative to the EST. Full article
(This article belongs to the Special Issue Precision Healthcare-Oriented Artificial Intelligence)
Show Figures

Figure 1

14 pages, 2283 KiB  
Article
Theoretical and Experimental Study on Assessment of Flow-Mediated Dilatation Using the Cuff Method in Brachial Arteries
by Jia-Jung Wang, Shing-Hong Liu, Yong-Hong Pan, Wei-Kung Tseng and Wenxi Chen
Electronics 2022, 11(3), 351; https://doi.org/10.3390/electronics11030351 - 24 Jan 2022
Viewed by 2202
Abstract
Endothelial dysfunction has been shown to be an important risk factor in the pathogenesis of atherosclerosis, hypertension, and heart failure. The flow-mediated vasodilation (FMD) of the peripheral arteries is an endothelium-dependent function, which is assessed by measuring the diameter change in the brachial [...] Read more.
Endothelial dysfunction has been shown to be an important risk factor in the pathogenesis of atherosclerosis, hypertension, and heart failure. The flow-mediated vasodilation (FMD) of the peripheral arteries is an endothelium-dependent function, which is assessed by measuring the diameter change in the brachial artery before and after ischemic stress. Brachial-artery ultrasound scanning (BAUS) is the gold standard for assessing the FMD in clinical practice. However, ultrasonography requires an operator or physician with a professional training to perform accurate measurement of the diameter of the brachial artery. Thus, some studies have used the cuff method to measure the FMD in percentage, the value of which is significantly larger than that using BAUS. The goal of this study was to explore this phenomenon. We explain the interaction between the volume changes (oscillation magnitudes in volume due to cardiac pulsations) of the artery and cuff bladder under different transmural pressures when a sphygmomanometer is wrapped around an upper arm. The compliance of the cuff bladder would be of a fixed value when the cuff pressure is low. The cuff-volume change could be replaced with a cuff-pressure change (oscillation magnitude in cuff pressure due to cardiac pulsation). With the cuff method, the FMDc could be assessed with pressure changes. Then, an inequality formula regarding FMD values by both BAUS (FMDu) and the cuff method (FMDc) was derived; FMDc > 2*FMDu + FMDu2. In order to experimentally verify this inequality formula, fifty-one subjects, including thirty-eight healthy adults and thirteen patients with hypertension, participated in this study. The systolic and diastolic diameters of their brachial arteries and cuff-pressure changes due to cardiac pulsations were separately measured by BAUS and a pressure sensor before and after an ischemic stress. The results showed that FMDu and FMDc were 8.1 ± 4.3% and 121.6 ± 48.6% in the healthy group and 4.5 ± 1.1% and 55.2 ± 22.8% in the patient group, respectively. Thus, the experimental findings comply with the theoretically derived inequality formula. Full article
(This article belongs to the Special Issue Precision Healthcare-Oriented Artificial Intelligence)
Show Figures

Figure 1

17 pages, 5725 KiB  
Article
Human Activity Recognition Using an Ensemble Learning Algorithm with Smartphone Sensor Data
by Tan-Hsu Tan, Jie-Ying Wu, Shing-Hong Liu and Munkhjargal Gochoo
Electronics 2022, 11(3), 322; https://doi.org/10.3390/electronics11030322 - 20 Jan 2022
Cited by 40 | Viewed by 3496
Abstract
Human activity recognition (HAR) can monitor persons at risk of COVID-19 virus infection to manage their activity status. Currently, many people are isolated at home or quarantined in some specified places due to the spread of COVID-19 virus all over the world. This [...] Read more.
Human activity recognition (HAR) can monitor persons at risk of COVID-19 virus infection to manage their activity status. Currently, many people are isolated at home or quarantined in some specified places due to the spread of COVID-19 virus all over the world. This situation raises the requirement of using the HAR to observe physical activity levels to assess physical and mental health. This study proposes an ensemble learning algorithm (ELA) to perform activity recognition using the signals recorded by smartphone sensors. The proposed ELA combines a gated recurrent unit (GRU), a convolutional neural network (CNN) stacked on the GRU and a deep neural network (DNN). The input samples of DNN were an extra feature vector consisting of 561 time-domain and frequency-domain parameters. The full connected DNN was used to fuse three models for the activity classification. The experimental results show that the precision, recall, F1-score and accuracy achieved by the ELA are 96.8%, 96.8%, 96.8%, and 96.7%, respectively, which are superior to the existing schemes. Full article
(This article belongs to the Special Issue Precision Healthcare-Oriented Artificial Intelligence)
Show Figures

Figure 1

13 pages, 4686 KiB  
Article
Bone Metastasis Detection in the Chest and Pelvis from a Whole-Body Bone Scan Using Deep Learning and a Small Dataset
by Da-Chuan Cheng, Chia-Chuan Liu, Te-Chun Hsieh, Kuo-Yang Yen and Chia-Hung Kao
Electronics 2021, 10(10), 1201; https://doi.org/10.3390/electronics10101201 - 18 May 2021
Cited by 19 | Viewed by 5459
Abstract
The aim of this study was to establish an early diagnostic system for the identification of the bone metastasis of prostate cancer in whole-body bone scan images by using a deep convolutional neural network (D-CNN). The developed system exhibited satisfactory performance for a [...] Read more.
The aim of this study was to establish an early diagnostic system for the identification of the bone metastasis of prostate cancer in whole-body bone scan images by using a deep convolutional neural network (D-CNN). The developed system exhibited satisfactory performance for a small dataset containing 205 cases, 100 of which were of bone metastasis. The sensitivity and precision for bone metastasis detection and classification in the chest were 0.82 ± 0.08 and 0.70 ± 0.11, respectively. The sensitivity and specificity for bone metastasis classification in the pelvis were 0.87 ± 0.12 and 0.81 ± 0.11, respectively. We propose the use of hard example mining for increasing the sensitivity and precision of the chest D-CNN. The developed system has the potential to provide a prediagnostic report for physicians’ final decisions. Full article
(This article belongs to the Special Issue Precision Healthcare-Oriented Artificial Intelligence)
Show Figures

Figure 1

Back to TopTop