Deep Supplement Learning for Healthcare and Biomedical Applications

Topic Information

Dear Colleagues,

During the challenging years of the ongoing COVID-19 pandemic, the need for efficient artificial intelligence models, tools, and applications in healthcare has been more evident than ever. Deep learning algorithms, supplemented by advanced learning techniques, have the potential to revolutionize healthcare and biomedical technologies. This Topic aims to bring together interdisciplinary approaches, focusing on innovative applications and existing AI methodologies to address pressing challenges in the healthcare sector. The topics of interest include deep learning algorithms in healthcare, supplemental learning techniques, biomedical data analysis, and medical image processing. These areas are crucial for interpreting genomic data, developing predictive models, and creating health monitoring systems. AI-driven drug discovery, personalized medicine, and the integration of deep learning with electronic health records (EHRs) are also key focal points. Moreover, this Topic will explore the development of clinical decision support systems, healthcare diagnostics, and AI-driven diagnosis in healthcare. The role of AI in health science education, rehabilitation, assistive technologies, public health, and ethical and legal considerations in AI healthcare applications will also be addressed. By highlighting the latest research, innovative approaches, and practical implementations, this Topic aims to improve patient outcomes, enhance diagnostic accuracy, and optimize treatment protocols. Researchers are encouraged to develop new or adapt existing AI models, tools, and applications to effectively solve the dynamic and heterogeneous nature of healthcare data problems. In addition to the open call for papers, extended versions of articles presented at relevant conferences are invited. Each submission should contain at least 50% new material, such as technical extensions, more in-depth evaluations, or additional use cases, to contribute significantly to the scientific literature in this field.

Prof. Dr. Tahir Cetin Akinci
Prof. Dr. Ömer Faruk Ertuğrul
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
AI ai	6.5	7.3	2020	20.4 Days	CHF 1800
Applied Sciences applsci	2.9	6.1	2011	15 Days	CHF 2400
Electronics electronics	2.9	7.0	2012	14.8 Days	CHF 2400
Machine Learning and Knowledge Extraction make	8.4	12.7	2019	18.7 Days	CHF 1800

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (7 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All AI Applied Sciences Electronics MAKE

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

attachment

Supplementary material:
Supplementary File 1 (ZIP, 2793 KB)

24 pages, 9905 KB  

Open AccessArticle

Artificial Intelligence Framework for Respiratory Disease Classification Using Multi-Spectral-Feature-Driven and Deep Neural Architectures

by Vijayalakshmi Sankaran, Paramasivam Alagumariappan, Sumendra Yogarayan, Thayananth Caran Varshana and Balaguru Ramana

AI 2026, 7(8), 315; https://doi.org/10.3390/ai7080315 - 18 Aug 2026

Viewed by 424

Abstract

Globally, respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD) and pneumonia affect populations significantly, requiring early and accurate diagnosis for effective clinical management. Manual auscultation and expert interpretation are the common shortcomings in conventional diagnostic approaches, as they lead to time-consuming [...] Read more.

Globally, respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD) and pneumonia affect populations significantly, requiring early and accurate diagnosis for effective clinical management. Manual auscultation and expert interpretation are the common shortcomings in conventional diagnostic approaches, as they lead to time-consuming and inconsistent analysis. To address these limitations, an artificial intelligence-driven framework for respiratory disease classification using multi-spectral feature extraction and deep learning architectures is proposed to classify four different respiratory conditions: Asthma, COPD, Pneumonia and Healthy. The dataset is collected from Kaggle’s respiratory sound database and the COUGHVID V3 database, which together contain 322 Asthma signals, 746 COPD signals, 323 Pneumonia signals and 174 Healthy signals. Subsequently, the features are extracted using four different feature extraction techniques—Constant Q Transform (CQT), a Gammatone spectrogram, Mel-Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP)—and these extracted spectral representations are provided as inputs to various deep learning models such as a Deep Convolutional Neural Network (Deep CNN), a Temporal Attention Network (TAN) and an Autoencoder for automated feature learning and disease classification. The proposed framework is evaluated using several performance metrics, and the experimental results clearly indicate that the performance of the proposed classification framework strongly depends on the selection of spectral feature extraction techniques and deep learning models. Among all the evaluated combinations, it is evident that the Autoencoder model integrated with CQT features exhibited the best classification performance, with an accuracy of 98.72%, precision of 98.74%, recall of 98.72%, Matthews correlation coefficient (MCC) of 98.11%, Cohen’s kappa value of 98.10% and the least log loss of 0.025. The proposed artificial intelligence (AI)-enabled respiratory disease classification framework has demonstrated the ability to produce a reliable computer-aided diagnostic system which is suitable for smart healthcare applications and automated pulmonary disease screening. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Figure 1

attachment

Supplementary material:
Supplementary File 1 (ZIP, 2657 KB)

31 pages, 7713 KB  

Open AccessArticle

Temporal Knowledge Extraction Through BayeStack with Multi-Level Explainability for Optimal Sepsis Classification

by Anjana Geetha, K. L. Nisha, Arun Sankar Muttathu Sivasankara Pillai and Sreenath Rajeev

Mach. Learn. Knowl. Extr. 2026, 8(6), 150; https://doi.org/10.3390/make8060150 - 1 Jun 2026

Viewed by 695

Abstract

Sepsis, a life-threatening condition causing significant global mortality, requires rapid diagnosis and intervention. Although recent advances in machine learning have supported clinical decision-making, existing sepsis classification approaches exhibit several limitations, including inadequate temporal modeling of disease progression, lack of systematic hyperparameter optimization, fragmented [...] Read more.

Sepsis, a life-threatening condition causing significant global mortality, requires rapid diagnosis and intervention. Although recent advances in machine learning have supported clinical decision-making, existing sepsis classification approaches exhibit several limitations, including inadequate temporal modeling of disease progression, lack of systematic hyperparameter optimization, fragmented interpretability approaches that do not fully address multi-stakeholder clinical needs, and challenges in achieving balanced sensitivity–specificity trade-offs. These limitations restrict effective extraction of knowledge from complex temporal clinical data and hinder actionable decision-making. To address these challenges, this work proposes BayeStack, a temporal knowledge-extraction framework that integrates Bayesian optimization-driven ensemble learning with hierarchical interpretability to optimize sepsis classification. This framework captures the progression of sepsis through multi-window temporal aggregation, performs optimal classification by applying AUROC-maximizing hyperparameter space exploration, and enables comprehensive clinical knowledge extraction by applying a three-level interpretability framework that includes global feature importance, population-level partial dependence analysis, and patient-specific contribution-level analysis. Evaluation results indicated that BayeStack achieved an AUROC of 0.99 with balanced sensitivity and specificity of 0.97, substantially outperforming all baseline methods ($p<0.001$). Ablation studies validated that temporal aggregation and data balancing contributed to performance improvements. A strong Spearman correlation ($\rho =0.856$) validated the feature ranking convergence and effectiveness of the ensemble strategy. The interpretability framework provides insights into complementary model behavior and extracts evidence-based clinical thresholds for priority-based treatment monitoring, thereby enabling robust clinical decision support. This first phase systematic integration framework of traditional machine learning models establishes baseline performance and explainability standards for subsequent deep learning advancements. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Figure 1

26 pages, 1085 KB  

Open AccessArticle

Looking Ahead When It Is Safe: An Uncertainty-Aware Paradigm for Blood Glucose Prediction with Dynamic Horizon Control

by Sarala Ghimire, Turgay Celik, Martin Gerdes and Christian W. Omlin

Mach. Learn. Knowl. Extr. 2026, 8(6), 145; https://doi.org/10.3390/make8060145 - 26 May 2026

Viewed by 1029

Abstract

Reliable time-series forecasting under rapidly changing conditions remains a critical challenge across many domains, particularly in healthcare, where physiological signals are inherently dynamic and uncertain. Blood glucose level prediction exemplifies this challenge, as accurate and timely forecasts are essential for effective diabetes management, [...] Read more.

Reliable time-series forecasting under rapidly changing conditions remains a critical challenge across many domains, particularly in healthcare, where physiological signals are inherently dynamic and uncertain. Blood glucose level prediction exemplifies this challenge, as accurate and timely forecasts are essential for effective diabetes management, yet traditional approaches rely on fixed prediction horizons and single-point estimates, which may yield unreliable decisions under rapidly changing physiological conditions. In this work, we propose a novel approach for adaptive horizon selection, applied to BGL prediction, employing a deep learning model. It employs evidential learning-based uncertainty quantification that decompose uncertainty into epistemic and aleatoric. Each set of models is trained to predict blood glucose levels at different future time steps, each providing both a point prediction and an associated uncertainty measure. At inference time, it dynamically balances predictive accuracy and reliability by selecting the longest horizon whose predicted uncertainty remains below a predefined threshold. This enables confidence-based horizon selection, using longer prediction horizons during stable periods and switching to shorter horizons when uncertainty signals critical glucose events requiring immediate intervention. This uncertainty-aware prediction approach promotes transparency by exposing confidence levels alongside predictions. Applicable to time-series forecasting tasks broadly, the proposed framework demonstrates encouraging potential, and when applied to BGL prediction as a representative clinical case, shows particular promise for supporting glycemic management through calibrated uncertainty estimation, offering a more transparent and interpretable alternative to fixed-horizon models toward trustworthy decision support in diabetes care. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Figure 1

31 pages, 1222 KB  

Open AccessArticle

Personalized Blood Glucose Prediction Using Physiology- Informed Machine Learning

by Sarala Ghimire, Turgay Celik, Martin Gerdes and Christian W. Omlin

Mach. Learn. Knowl. Extr. 2026, 8(4), 96; https://doi.org/10.3390/make8040096 - 10 Apr 2026

Cited by 1 | Viewed by 1953

Abstract

Data-driven approaches to blood glucose predictive modeling face significant challenges due to the inherent variability in biological systems. While these methods efficiently capture statistical patterns through automated processes, they often lack the biological interpretability necessary to link model behavior with underlying physiological mechanisms. [...] Read more.

Data-driven approaches to blood glucose predictive modeling face significant challenges due to the inherent variability in biological systems. While these methods efficiently capture statistical patterns through automated processes, they often lack the biological interpretability necessary to link model behavior with underlying physiological mechanisms. In contrast, physiological models offer accurate mechanistic representations but require complex parameterization and specialized domain expertise. In this work, we present an approach for predicting blood glucose levels (BGLs) leveraging the concept of physiology-informed neural networks (PINNs). This approach addresses the challenge of BGL prediction by incorporating the parameters of insulin and meal dynamics within the architecture of a predictive network. It employs a two-stage learning approach for modeling physiology and predicting BGLs. The neural network is pretrained to approximate the solutions of the physiological dynamics, and the output of this pretrained model, representing the insulin and glucose concentration states, is then fed as input into a predictive model, enabling simultaneous optimization of predictive accuracy and physiological parameter estimation, offering advantages over traditional modeling approaches in terms of personalized prediction and interpretability. The results highlight the model’s ability to estimate physiological parameters while maintaining strong predictive performance that aligns with the underlying physiological principles. This framework offers significant potential for personalized predictive modeling where precise and efficient understanding of individual metabolism is essential. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Graphical abstract

25 pages, 964 KB  

Open AccessArticle

Adapting EHR Foundational Models to Predict Diabetes Complications with Precision Explainability

by Timothy Joseph, Ahmed Dhaouadi, Jayroop Ramesh, Assim Sagahyroon and Fadi Aloul

Mach. Learn. Knowl. Extr. 2026, 8(4), 89; https://doi.org/10.3390/make8040089 - 4 Apr 2026

Viewed by 1438

Abstract

Diabetes mellitus is a chronic condition that frequently leads to severe complications that are difficult to detect in their early stages using conventional clinical monitoring. This paper presents a data-driven framework for predicting multiple diabetes-related complications using structured electronic health record data while [...] Read more.

Diabetes mellitus is a chronic condition that frequently leads to severe complications that are difficult to detect in their early stages using conventional clinical monitoring. This paper presents a data-driven framework for predicting multiple diabetes-related complications using structured electronic health record data while ensuring clinically meaningful explainability. The proposed approach adapts a pretrained electronic health record foundation model to operate on static patient data and integrates it with classical machine learning baselines to address class imbalance, feature sparsity, and interpretability challenges. A multi-label prediction setting covering eight common diabetes complications is evaluated using a real-world dataset from a regional diabetes center in the United Arab Emirates. Synthetic data generation and clinical constraint enforcement are applied to improve robustness for underrepresented outcomes, while feature selection is guided by model importance and attribution-based explanations. The best-performing configuration, a weighted ensemble combining a low-rank adapted Hyena-based foundation model with a tree-based predictor, achieved an average F1-score of 0.77, an average recall of 0.85, and an example-based F1-score of 0.71, outperforming all individual models. In addition, this ensemble produced the most stable explanations under input perturbations, indicating improved consistency of dominant clinical risk drivers. These results demonstrate that explainable foundation model-based ensembles can deliver accurate, robust, and clinically transparent risk prediction for diabetes complications. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Graphical abstract

30 pages, 9811 KB  

Open AccessArticle

Audio-Based Screening of Respiratory Diseases Using Machine Learning: A Methodological Framework Evaluated on a Clinically Validated COVID-19 Cough Dataset

by Arley Magnolia Aquino-García, Humberto Pérez-Espinosa, Javier Andreu-Perez and Ansel Y. Rodríguez González

Mach. Learn. Knowl. Extr. 2026, 8(3), 80; https://doi.org/10.3390/make8030080 - 20 Mar 2026

Viewed by 1372

Abstract

The development of AI-driven computational methods has enabled rapid and non-invasive analysis of respiratory sounds using acoustic data, particularly cough recordings. Although the COVID-19 pandemic accelerated research on cough-based acoustic analysis, many early studies were limited by insufficient data quality, lack of standardized [...] Read more.

The development of AI-driven computational methods has enabled rapid and non-invasive analysis of respiratory sounds using acoustic data, particularly cough recordings. Although the COVID-19 pandemic accelerated research on cough-based acoustic analysis, many early studies were limited by insufficient data quality, lack of standardized protocols, and limited reproducibility due to data scarcity. In this study, we propose an audio analysis framework for cough-based respiratory disease screening research using COVID-19 as a clinically validated case dataset. All analyses were conducted on a single clinically acquired multicentric dataset collected under standardized conditions in certified laboratories in Mexico and Spain, comprising cough recordings from 1105 individuals. Model training and testing were performed exclusively within this dataset. The framework incorporates signal preprocessing and a comparative evaluation of segmentation strategies, showing that segmented cough analysis significantly outperforms full-signal analysis. Class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE) for CNN2D models and the supervised Resample filter implemented in WEKA for classical machine learning models, both applied exclusively to the training subset to generate balanced training sets and prevent data leakage. Feature extraction and classification were carried out using Random Forest, Support Vector Machine (SVM), XGBoost, and a 2D Convolutional Neural Network (CNN2D), with hyperparameter optimization via AutoML. The proposed framework achieved a best balanced screening performance of 85.58% sensitivity and 86.65% specificity (Random Forest with GeMAPSvB01), while the highest-specificity configuration reached 93.90% specificity with 18.14% sensitivity (CNN2D with SMOTE and AutoML). These results demonstrate the methodological feasibility of the proposed framework under the evaluated conditions. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ Show Figures

Figure 1

17 pages, 2856 KB  

Open AccessArticle

Improved Deep Learning for Parkinson’s Diagnosis Based on Wearable Sensors

by Jintao Yu, Ke Meng, Tingwei Liang, He Liu and Xiaowen Wang

Electronics 2024, 13(23), 4638; https://doi.org/10.3390/electronics13234638 - 25 Nov 2024

Cited by 9 | Viewed by 5769

Abstract

Parkinson’s disease is a neurodegenerative disease that seriously affects the quality of life of patients. In this study, we propose a new Parkinson’s diagnosis method using deep learning techniques. The method takes multi-channel sensor signals as inputs, and the full convolutional and LSTM [...] Read more.

Parkinson’s disease is a neurodegenerative disease that seriously affects the quality of life of patients. In this study, we propose a new Parkinson’s diagnosis method using deep learning techniques. The method takes multi-channel sensor signals as inputs, and the full convolutional and LSTM blocks of the model perceive the same time-series inputs from two different views, and connect the extracted spatial features with temporal features. In order to improve the detection performance, a channel attention mechanism was incorporated into the model, and a data augmentation approach was used to eliminate the effect of unbalanced datasets on model training. The pd vs. hc and pd vs. dd classification tasks were performed, which improved accuracy by 4.25% and 8.03%, respectively, compared to the previous best results. Both improvements were higher than the previous methods using machine learning combined with feature extraction. To utilize the available data resources more effectively, this study conducted the pd vs. hc vs. dd triple classification task for the first time, which improved the model’s ability to identify disease features. In that task, the accuracy rate reached 78.23%. The experimental results fully demonstrated the effectiveness of the proposed deep learning method for Parkinson’s diagnosis. Full article

(This article belongs to the Topic Deep Supplement Learning for Healthcare and Biomedical Applications)

►▼ 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 1-7