Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

Journal Browser

Artificial Intelligence in Medicine and Healthcare

Special Issue Editors
Special Issue Information
Benefits of Publishing in a Special Issue
Published Papers

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

Deadline for manuscript submissions: 20 March 2025 | Viewed by 33980

Share This Special Issue

Special Issue Editors

Dr. Tianhua Chen

E-Mail Website
Guest Editor

Department of Computer Science, School of Computing and Engineering, University of Huddersfield, Huddersfield, UK
Interests: AI in medicine; healthcare informatics; computational intelligence; artificial intelligence
Special Issues, Collections and Topics in MDPI journals

Dr. Pan Su

E-Mail Website
Guest Editor

School of Control and Computer Engineering, North China Electric Power University, Beijing, China
Interests: AI for healthcare; medical Image processing; machine learning
Special Issues, Collections and Topics in MDPI journals

Dr. Zhenpeng Li

E-Mail Website
Guest Editor

Department of Psychiatry, University of Oxford, Oxford, UK
Interests: machine learning in medication and healthcare; data science and data mining; knowledge representation and discovery

Dr. Bakhtiar Amen

E-Mail Website
Guest Editor

Computer Science Department, University of Huddersfield, Huddersfield, UK
Interests: big data and AI for healthcare and diabetes; health sensor monitoring and detection; medical data stream anomaly detection

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) is increasingly applied in various disciplines, including the health and medicine sector, where AI has been leveraged to inform disease progression, make early diagnoses, optimize medication and treatment plans, and support decision making. In spite of considerable recent advances, AI for health and medicine is also facing major challenges, such as public trust building, patient privacy protection, ethical concerns on data usage and equity, and AI–human interaction/collaboration. While the patients and medical professionals still have much to benefit from rapidly developed AI techniques, this Special Issue encourages submissions of scientific findings that present the fundamental theory, techniques, applications, and practical experiences in the context of designing, implementing, or evaluating artificial intelligence for health and medicine.

The topics of this Special Issue include, but are not limited to:

computational intelligence for health and medicine;
artificial intelligence for health and medicine;
data mining and knowledge discovery in health and medicine;
machine learning in health and medicine;
clinical decision support systems for health and medicine;
text mining and natural language processing for health and medicine;
deep learning for health and medicine;
computer vision and medical imaging;
modelling and reasoning with time in healthcare systems.

Dr. Tianhua Chen
Dr. Pan Su
Dr. Zhenpeng Li
Dr. Bakhtiar Amen
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.

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

21 pages, 3696 KiB

Open AccessArticle

The Potential of AI-Powered Face Enhancement Technologies in Face-Driven Orthodontic Treatment Planning

by Juraj Tomášik, Márton Zsoldos, Kristína Majdáková, Alexander Fleischmann, Ľubica Oravcová, Dominika Sónak Ballová and Andrej Thurzo

Appl. Sci. 2024, 14(17), 7837; https://doi.org/10.3390/app14177837 - 4 Sep 2024

Cited by 1 | Viewed by 1590

Abstract

Improving one’s appearance is one of the main reasons to undergo an orthodontic therapy. While occlusion is important, not just for long-term stability, aesthetics is often considered a key factor in patient’s satisfaction. Following recent advances in artificial intelligence (AI), this study set out to investigate whether AI can help guide orthodontists in diagnosis and treatment planning. In this study, 25 male and 25 female faces were generated and consequently enhanced using FaceApp (ver. 11.10, FaceApp Technology Limited, Limassol, Cyprus), one of the many pictures transforming applications on the market. Both original and FaceApp-modified pictures were then assessed by 441 respondents regarding their attractiveness, and the pictures were further compared using a software for picture analyses. Statistical analysis was performed using Chi-square goodness of fit test R Studio Studio (ver. 4.1.1, R Core Team, Vienna, Austria) software and the level of statistical significance was set to 0.05. The interrater reliability was tested using Fleiss’ Kappa for m Raters. The results showed that in 49 out of 50 cases, the FaceApp-enhanced pictures were considered to be more attractive. Selected pictures were further analyzed using the graphical software GIMP. The most prominent changes were observed in lip fullness, eye size, and lower face height. The results suggest that AI-powered face enhancement could be a part of the diagnosis and treatment planning stages in orthodontics. These enhanced pictures could steer clinicians towards soft-tissue-oriented and personalized treatment planning, respecting patients’ wishes for improved face appearance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Graphical abstract

18 pages, 2198 KiB

Open AccessArticle

Integrating Structured and Unstructured Data with BERTopic and Machine Learning: A Comprehensive Predictive Model for Mortality in ICU Heart Failure Patients

by Shih-Wei Wu, Cheng-Cheng Li, Te-Nien Chien and Chuan-Mei Chu

Appl. Sci. 2024, 14(17), 7546; https://doi.org/10.3390/app14177546 - 26 Aug 2024

Viewed by 1070

Abstract

Heart failure remains a leading cause of mortality worldwide, particularly within Intensive Care Unit (ICU)-patient populations. This study introduces an innovative approach to predicting ICU mortality by seamlessly integrating electronic health record (EHR) data with a BERTopic-based hybrid machine-learning methodology. The MIMIC-III database serves as the primary data source, encompassing structured and unstructured data from 6606 ICU-admitted heart-failure patients. Unstructured data are processed using BERTopic, complemented by machine-learning algorithms for prediction and performance evaluation. The results indicate that the inclusion of unstructured data significantly enhances the model’s predictive accuracy regarding patient mortality. The amalgamation of structured and unstructured data effectively identifies key variables, enhancing the precision of the predictive model. The developed model demonstrates potential in improving healthcare decision-making, elevating patient outcomes, and optimizing resource allocation within the ICU setting. The handling and application of unstructured data emphasize the utilization of clinical narrative records by healthcare professionals, elevating this research beyond the traditional structured data predictive tools. This study contributes to the ongoing discourse in critical care and predictive modeling, offering valuable insights into the potential of integrating unstructured data into healthcare analytics. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

17 pages, 4111 KiB

Open AccessArticle

Enhancing Inter-Patient Performance for Arrhythmia Classification with Adversarial Learning Using Beat-Score Maps

by Yeji Jeong, Jaewon Lee and Miyoung Shin

Appl. Sci. 2024, 14(16), 7227; https://doi.org/10.3390/app14167227 - 16 Aug 2024

Cited by 2 | Viewed by 940

Abstract

Research on computer-aided arrhythmia classification is actively conducted, but the limited generalization capacity constrains its applicability in practical clinical settings. One of the primary challenges in deploying such techniques in real-world scenarios is the inter-patient variability and the consequent performance degradation. In this study, we leverage our previous innovation, the n-beat-score map (n-BSM), to introduce an adversarial framework to mitigate the issue of poor performance in arrhythmia classification within the inter-patient paradigm. The n-BSM is a 2D representation of the ECG signal, capturing its constituent beat characteristics through beat-score vectors derived from a pre-trained beat classifier. We employ adversarial learning to eliminate patient-dependent features during the training of the beat classifier, thereby generating the patient-independent n-BSM (PI-BSM). This approach enables us to concentrate primarily on the learning characteristics associated with beat type rather than patient-specific features. Through a beat classifier pre-trained with adversarial learning, a series of beat-score vectors are generated for the beat segments that make up a given ECG signal. These vectors are then concatenated chronologically to form a PI-BSM. Utilizing PI-BSMs as the input, an arrhythmia classifier is trained to differentiate between distinct types of rhythms. This approach yields a 14.27% enhancement in the F1-score in the MIT-BIH arrhythmia database and a 4.97% improvement in cross-database evaluation using the Chapman–Shaoxing 12-lead ECG database. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

18 pages, 674 KiB

Open AccessArticle

Why Are Explainable AI Methods for Prostate Lesion Detection Rated Poorly by Radiologists?

by Mehmet A. Gulum, Christopher M. Trombley, Merve Ozen, Enes Esen, Melih Aksamoglu and Mehmed Kantardzic

Appl. Sci. 2024, 14(11), 4654; https://doi.org/10.3390/app14114654 - 28 May 2024

Cited by 1 | Viewed by 1004

Abstract

Deep learning offers significant advancements in the accuracy of prostate identification and classification, underscoring its potential for clinical integration. However, the opacity of deep learning models presents interpretability challenges, critical for their acceptance and utility in medical diagnosis and detection. While explanation methods have been proposed to demystify these models, enhancing their clinical viability, the efficacy and acceptance of these methods in medical tasks are not well documented. This pilot study investigates the effectiveness of deep learning explanation methods in clinical settings and identifies the attributes that radiologists consider crucial for explainability, aiming to direct future enhancements. This study reveals that while explanation methods can improve clinical task performance by up to 20%, their perceived usefulness varies, with some methods being rated poorly. Radiologists prefer explanation methods that are robust against noise, precise, and consistent. These preferences underscore the need for refining explanation methods to align with clinical expectations, emphasizing clarity, accuracy, and reliability. The findings highlight the importance of developing explanation methods that not only improve performance but also are tailored to meet the stringent requirements of clinical practice, thereby facilitating deeper trust and a broader acceptance of deep learning in medical diagnostics. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

11 pages, 782 KiB

Open AccessArticle

Correlation between Neck Muscle Endurance Tests, Ultrasonography, and Self-Reported Outcomes in Women with Low Cervical Disability and Neck Pain

by Pilar Pardos-Aguilella, Luis Ceballos-Laita, Sara Cabanillas-Barea, Silvia Pérez-Guillén, Gianluca Ciuffreda, Sandra Jiménez-del-Barrio and Andoni Carrasco-Uribarren

Appl. Sci. 2023, 13(18), 10106; https://doi.org/10.3390/app131810106 - 7 Sep 2023

Viewed by 1820

Abstract

Background: Neck pain (NP) is a frequent condition in women, characterized by exhibiting distinct clinical manifestations such as the presence of deep neck (DN) muscle weakness. Endurance and ultrasonography of the DN muscles, and patient-reported outcome measures, are commonly used outcomes in clinical practice. The aim of this study is to assess and correlate the endurance of the DN muscles and their morphological characteristics with pain intensity, neck disability and headache impact. Methods: An observational and correlational study was carried out. Eighty-two women were recruited, and endurance tests of neck flexor and extensor (chin tuck flexion test and neck extensor muscles endurance test), ultrasonography of the DN muscles, pain intensity, disability (neck disability index) and headache impact (HIT-6) were measured. Spearman’s rho was used to evaluate the correlation between the outcome variables, and a simple linear regression analysis was carried out to explain the model in detail. Results: Statistically significant negative correlations between the chin tuck neck flexion test and neck disability index (NDI) (r = −0.38; p < 0.001) and HIT-6 (r = −0.26; p = 0.02) were found. The neck extensor muscles endurance test showed a negative correlation with NDI (r = −0.27; p = 0.01) and HIT-6 (r = −0.26; p = 0.02). The simple linear regression analysis showed an R squared of 26.7% and was statistically significant (NDI: R squared = 0.267; F = 3.13; p = 0.004) for NDI. Conclusion: A negative correlation between deep neck muscle endurance test results and self-reported outcome measures in women with low cervical disability and neck pain were observed. This suggests that lower endurance in the deep neck muscles may be associated with poorer self-reported symptoms and functionality in these patients. The chin tuck neck flexion test and deep extensor muscles endurance test could predict self-perceived neck disability in women with low cervical disability and NP. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

18 pages, 3583 KiB

Open AccessArticle

Review of Soft Computing Techniques in Monitoring Cardiovascular Disease in the Context of South Asian Countries

by Gajendra Singh Thakur, Sunil Kumar Sahu, N. Kumar Swamy, Manish Gupta, Tony Jan and Mukesh Prasad

Appl. Sci. 2023, 13(17), 9555; https://doi.org/10.3390/app13179555 - 23 Aug 2023

Cited by 2 | Viewed by 2629

Abstract

The term “soft computing” refers to a system that can work with varying degrees of uncertainty and approximations in real-life complex problems using various techniques such as Fuzzy Logic, Artificial Neural Networks (ANN), Machine Learning (ML), and Genetic Algorithms (GA). Owing to the low-cost and high-performance digital processors today, the use of soft computing techniques has become more prevalent. The main focus of this paper is to study the use of soft computing in the prediction and diagnosis of heart diseases, which are considered one of the major causes of fatalities in modern-day humans. The heart is a major human organ that can be affected by various conditions such as high blood pressure, diabetes, and heart failure. The main cause of heart failure is the narrowing of the blood vessels due to excess cholesterol deposits in the coronary arteries. The objective of this study is to review and compare the various soft computing techniques that are used for the prediction, diagnosis, failure, detection, identification, and classification of heart disease. In this paper, a comprehensive list of recent soft computing techniques in heart condition monitoring is reviewed and compared with an experiment with specific applications to developing countries including South Asian countries. The relevant experimental outcomes demonstrate the benefits of soft computing in medical services with a high accuracy of 99.4% from Fuzzy Logic and Convolutional Neural Networks, with comparable results from other competing state-of-the-art soft computing models. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

9 pages, 602 KiB

Open AccessArticle

A Computer Vision-Based Application for the Assessment of Head Posture: A Validation and Reliability Study

by Andoni Carrasco-Uribarren, Xavier Marimon, Flora Dantony, Sara Cabanillas-Barea, Alejandro Portela, Luis Ceballos-Laita and Albert Massip-Álvarez

Appl. Sci. 2023, 13(6), 3910; https://doi.org/10.3390/app13063910 - 19 Mar 2023

Cited by 2 | Viewed by 3530

Abstract

As its name implies, the forward head position (FHP) is when the head is further forward of the trunk than normal. This can cause neck and shoulder tension, as well as headaches. The craniovertebral angle (CVA) measured with 2D systems such as Kinovea software is often used to assess the FHP. Computer vision applications have proven to be reliable in different areas of daily life. The aim of this study is to analyze the test-retest and inter-rater reliability and the concurrent validity of a smartphone application based on computer vision for the measurement of the CVA. Methods: The CVAs of fourteen healthy volunteers, fourteen neck pain patients, and fourteen tension-type headache patients were assessed. The assessment was carried out twice, with a week of rest between sessions. Each examiner took a lateral photo in a standing position with the smartphone app based on computer vision. The test-retest reliability was calculated with the assessment of the CVA measured by the smartphone application, and the inter-rater reliability was also calculated. A third examiner assessed the CVA using 2D Kinovea software to calculate its concurrent validity. Results: The CVA in healthy volunteers was 54.65 (7.00); in patients with neck pain, 57.67 (5.72); and in patients with tension-type headaches, 54.63 (6.48). The test-retest reliability was excellent, showing an Intraclass Correlation Coefficient (ICC) of 0.92 (0.86–0.95) for the whole sample. The inter-rater reliability was excellent, with an ICC of 0.91 (0.84–0.95) for the whole sample. The standard error of the measurement with the app was stated as 1.83°, and the minimum detectable change was stated as 5.07°. The concurrent validity was high: r = 0.94, p < 0.001. Conclusion: The computer-based smartphone app showed excellent test-retest and inter-rater reliability and strong concurrent validity compared to Kinovea software for the measurement of CVA. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

Review

Jump to: Research

25 pages, 2807 KiB

Open AccessReview

XAI-Based Clinical Decision Support Systems: A Systematic Review

by Se Young Kim, Dae Ho Kim, Min Ji Kim, Hyo Jin Ko and Ok Ran Jeong

Appl. Sci. 2024, 14(15), 6638; https://doi.org/10.3390/app14156638 - 30 Jul 2024

Cited by 1 | Viewed by 2601

Abstract

With increasing electronic medical data and the development of artificial intelligence, clinical decision support systems (CDSSs) assist clinicians in diagnosis and prescription. Traditional knowledge-based CDSSs follow an accumulated medical knowledgebase and a predefined rule system, which clarifies the decision-making process; however, maintenance cost issues exist in the medical data quality control and standardization processes. Non-knowledge-based CDSSs utilize vast amounts of data and algorithms to effectively make decisions; however, the deep learning black-box problem causes unreliable results. EXplainable Artificial Intelligence (XAI)-based CDSSs provide valid rationales and explainable results. These systems ensure trustworthiness and transparency by showing the recommendation and prediction result process using explainable techniques. However, existing systems have limitations, such as the scope of data utilization and the lack of explanatory power of AI models. This study proposes a new XAI-based CDSS framework to address these issues; introduces resources, datasets, and models that can be utilized; and provides a foundation model to support decision-making in various disease domains. Finally, we propose future directions for CDSS technology and highlight societal issues that need to be addressed to emphasize the potential of CDSSs in the future. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Figure 1

25 pages, 1602 KiB

Open AccessReview

Deep Learning-Based ECG Arrhythmia Classification: A Systematic Review

by Qiao Xiao, Khuan Lee, Siti Aisah Mokhtar, Iskasymar Ismail, Ahmad Luqman bin Md Pauzi, Qiuxia Zhang and Poh Ying Lim

Appl. Sci. 2023, 13(8), 4964; https://doi.org/10.3390/app13084964 - 14 Apr 2023

Cited by 51 | Viewed by 14145

Abstract

Deep learning (DL) has been introduced in automatic heart-abnormality classification using ECG signals, while its application in practical medical procedures is limited. A systematic review is performed from perspectives of the ECG database, preprocessing, DL methodology, evaluation paradigm, performance metric, and code availability to identify research trends, challenges, and opportunities for DL-based ECG arrhythmia classification. Specifically, 368 studies meeting the eligibility criteria are included. A total of 223 (61%) studies use MIT-BIH Arrhythmia Database to design DL models. A total of 138 (38%) studies considered removing noise or artifacts in ECG signals, and 102 (28%) studies performed data augmentation to extend the minority arrhythmia categories. Convolutional neural networks are the dominant models (58.7%, 216) used in the reviewed studies while growing studies have integrated multiple DL structures in recent years. A total of 319 (86.7%) and 38 (10.3%) studies explicitly mention their evaluation paradigms, i.e., intra- and inter-patient paradigms, respectively, where notable performance degradation is observed in the inter-patient paradigm. Compared to the overall accuracy, the average

F_{1}

score, sensitivity, and precision are significantly lower in the selected studies. To implement the DL-based ECG classification in real clinical scenarios, leveraging diverse ECG databases, designing advanced denoising and data augmentation techniques, integrating novel DL models, and deeper investigation in the inter-patient paradigm could be future research opportunities. Full article

(This article belongs to the Special Issue Artificial Intelligence in Medicine and Healthcare)

► Show Figures

Journal Menu

Journal Browser

Artificial Intelligence in Medicine and Healthcare

Share This Special Issue

Special Issue Editors

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI