{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:09:44Z","timestamp":1778285384396,"version":"3.51.4"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate disease prediction using clinical datasets is essential for improving early diagnosis and clinical decision-support systems; however, many existing deep learning approaches are disease-specific, computationally intensive, and difficult to generalize across heterogeneous biomedical datasets. This study addresses this challenge by proposing a unified and dataset-aware deep learning framework that enables accurate and interpretable disease prediction across diverse clinical datasets. The framework adopts a modular architecture that selects appropriate models based on dataset characteristics such as feature dimensionality, sample size, and class imbalance. It integrates multiple deep learning architectures, including MLP, one-dimensional CNN, FT-Transformer, autoencoder-based classifiers, and ensemble strategies. Robust preprocessing, fold-safe feature selection, and nested cross-validation are incorporated to ensure reliable performance evaluation. The framework is evaluated on three heterogeneous benchmark datasets: the UCI Heart Disease dataset (303 samples, 13 clinical features), the PIMA Indians Diabetes dataset (768 samples, 8 metabolic features), and the Parkinson\u2019s disease voice dataset (195 recordings, 22 acoustic features). Experimental results demonstrate competitive predictive performance relative to classical baselines across the diverse tasks. The FT-Transformer\u2009+\u2009autoencoder ensemble achieved an AUC of 0.8980 (\u00b10.0483) for heart disease prediction, while the CNN\u2009+\u2009Autoencoder ensemble obtained an AUC of 0.8451 (\u00b10.0270) for diabetes classification. For Parkinson\u2019s disease detection, the MLP achieved an AUC of 0.7538 with perfect specificity. Overall, all models achieved AUC values comparable to ML baselines. The study contributes a scalable and interpretable deep learning framework that improves reliability, generalization, and practical applicability for multi-disease prediction in real-world healthcare environments.<\/jats:p>","DOI":"10.1371\/journal.pone.0348670","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:10:45Z","timestamp":1778281845000},"page":"e0348670","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["A modular deep learning architecture for interpretable disease prediction across tabular clinical and biometric datasets"],"prefix":"10.1371","volume":"21","author":[{"given":"Vijay U.","family":"Rathod","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddhesh Sanjay","family":"Amrutkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirti A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoudumber D.","family":"Londhe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandip Y.","family":"Bobade","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Virendrakumar A.","family":"Dhotre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3395-4955","authenticated-orcid":true,"given":"Melkamu Workie","family":"Kebede","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"issue":"3","key":"pone.0348670.ref001","doi-asserted-by":"crossref","first-page":"2244","DOI":"10.35940\/ijitee.C9009.019320","article-title":"Heart Diseases Prediction using Deep Learning Neural Network Model","volume":"9","author":"S Sharma","year":"2020","journal-title":"IJITEE"},{"key":"pone.0348670.ref002","first-page":"3682","article-title":"Multiple disease prediction using Machine learning algorithms","volume":"80","author":"K Arumugam","year":"2023","journal-title":"Materials Today: Proceedings"},{"key":"pone.0348670.ref003","doi-asserted-by":"crossref","unstructured":"Dahiwade D, Patle G, Meshram E. Designing disease prediction model using machine learning approach. In: 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC), 2019.","DOI":"10.1109\/ICCMC.2019.8819782"},{"key":"pone.0348670.ref004","doi-asserted-by":"crossref","unstructured":"Grampurohit S, Sagarnal C. Disease prediction using machine learning algorithms. 2020 international conference for emerging technology (INCET). IEEE, 2020.","DOI":"10.1109\/INCET49848.2020.9154130"},{"issue":"1","key":"pone.0348670.ref005","doi-asserted-by":"crossref","DOI":"10.1186\/s43067-024-00150-4","article-title":"A comprehensive review for chronic disease prediction using machine learning algorithms","volume":"11","author":"R Islam","year":"2024","journal-title":"Journal of Electrical Systems and Inf Technol"},{"issue":"1","key":"pone.0348670.ref006","doi-asserted-by":"crossref","first-page":"36678","DOI":"10.1038\/s41598-025-20534-4","article-title":"A deep learning framework with hybrid stacked sparse autoencoder for type 2 diabetes prediction","volume":"15","author":"Abdussamad","year":"2025","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0348670.ref007","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/s10772-025-10182-4","article-title":"A lightweight CNN-based ensemble approach for early detecting Parkinson\u2019s disease with enhanced features","volume":"28","author":"DK Saha","year":"2025","journal-title":"Int J Speech Technol"},{"issue":"1","key":"pone.0348670.ref008","doi-asserted-by":"crossref","first-page":"20437","DOI":"10.1038\/s41598-025-04807-6","article-title":"Design of a deep fusion model for early Parkinson\u2019s disease prediction using handwritten image analysis","volume":"15","author":"K Shyamal","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0348670.ref009","doi-asserted-by":"crossref","first-page":"1657889","DOI":"10.3389\/fmed.2025.1657889","article-title":"Integrating convolutional neural networks with ensemble methods for enhanced diabetes diagnosis: a multi-dataset evaluation","volume":"12","author":"K Zhuang","year":"2025","journal-title":"Front Med (Lausanne)"},{"issue":"1","key":"pone.0348670.ref010","doi-asserted-by":"crossref","first-page":"12129","DOI":"10.1038\/s41598-025-96950-3","article-title":"Voice biomarkers as prognostic indicators for Parkinson\u2019s disease using machine learning techniques","volume":"15","author":"I Naeem","year":"2025","journal-title":"Sci Rep"},{"issue":"5","key":"pone.0348670.ref011","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1007\/s12553-020-00438-1","article-title":"Heart disease classification using data mining tools and machine learning techniques","volume":"10","author":"I Tougui","year":"2020","journal-title":"Health Technol"},{"issue":"6","key":"pone.0348670.ref012","doi-asserted-by":"crossref","first-page":"3317","DOI":"10.3390\/ijerph18063317","article-title":"Prediction of Type 2 Diabetes Based on Machine Learning Algorithm","volume":"18","author":"HM Deberneh","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"pone.0348670.ref013","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1038\/s41598-024-82420-9","article-title":"A novel RFE-GRU model for diabetes classification using PIMA Indian dataset","volume":"15","author":"MY Shams","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0348670.ref014","doi-asserted-by":"crossref","first-page":"1539588","DOI":"10.3389\/frai.2024.1539588","article-title":"Artificial intelligence-based framework for early detection of heart disease using enhanced multilayer perceptron","volume":"7","author":"M Abdullah","year":"2025","journal-title":"Front Artif Intell"},{"issue":"1","key":"pone.0348670.ref015","doi-asserted-by":"crossref","first-page":"8624","DOI":"10.1038\/s41598-025-88293-w","article-title":"Enhancing parkinson disease detection through feature based deep learning with autoencoders and neural networks","volume":"15","author":"P Valarmathi","year":"2025","journal-title":"Sci Rep"},{"issue":"8","key":"pone.0348670.ref016","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.3390\/jpm12081208","article-title":"MLP-PSO Hybrid Algorithm for Heart Disease Prediction","volume":"12","author":"A Al Bataineh","year":"2022","journal-title":"J Pers Med"},{"key":"pone.0348670.ref017","doi-asserted-by":"crossref","first-page":"1665128","DOI":"10.3389\/fphys.2025.1665128","article-title":"Heart disease prediction using hybrid TabNet architecture with stacked ensemble learning","volume":"16","author":"R Yasmeen","year":"2025","journal-title":"Front Physiol"},{"issue":"1","key":"pone.0348670.ref018","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1038\/s41598-024-51184-7","article-title":"Enhancing heart disease prediction using a self-attention-based transformer model","volume":"14","author":"AU Rahman","year":"2024","journal-title":"Sci Rep"},{"key":"pone.0348670.ref019","first-page":"81","article-title":"Heart Disease Prediction Using Machine Learning Techniques: A Quantitative Review","volume-title":"Advances in Intelligent Systems and Computing","author":"L Riyaz","year":"2021"},{"key":"pone.0348670.ref020","doi-asserted-by":"crossref","unstructured":"Lakshmanarao A, Babu MR, Kiran TSR. Plant Disease Prediction and classification using Deep Learning ConvNets. In: 2021 International Conference on Artificial Intelligence and Machine Vision (AIMV), 2021. 1\u20136. doi: 10.1109\/aimv53313.2021.9670918","DOI":"10.1109\/AIMV53313.2021.9670918"},{"key":"pone.0348670.ref021","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume":"34","author":"Y Gorishniy","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"pone.0348670.ref022","doi-asserted-by":"crossref","first-page":"3733","DOI":"10.1007\/s11831-025-10255-2","article-title":"A Comprehensive Review of Various Machine Learning and Deep Learning Models for Anti-Cancer Drug Response Prediction: Comparative Analysis With Existing State of the Art Methods","volume":"32","author":"DP Singh","year":"2025","journal-title":"Arch Computat Methods Eng"},{"key":"pone.0348670.ref023","doi-asserted-by":"crossref","first-page":"108500","DOI":"10.1016\/j.compbiolchem.2025.108500","article-title":"Towards automated and reliable lung cancer detection in histopathological images using DY-FSPAN: A feature-summarized pyramidal attention network for explainable AI","volume":"118","author":"T Banerjee","year":"2025","journal-title":"Comput Biol Chem"},{"issue":"1","key":"pone.0348670.ref024","doi-asserted-by":"crossref","first-page":"27207","DOI":"10.1038\/s41598-025-12602-6","article-title":"A novel hybrid deep learning approach combining deep feature attention and statistical validation for enhanced thyroid ultrasound segmentation","volume":"15","author":"T Banerjee","year":"2025","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0348670.ref025","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1007\/s11831-025-10379-5","article-title":"Comparing Bipartite Convoluted and Attention-Driven Methods for Skin Cancer Detection: A Review of Explainable AI and Transfer Learning Strategies","volume":"33","author":"T Banerjee","year":"2025","journal-title":"Arch Computat Methods Eng"},{"issue":"3","key":"pone.0348670.ref026","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.1007\/s11831-025-10411-8","article-title":"A Comparative Evaluation of Deep Learning Architectures for Prostate Cancer Segmentation: Introducing TrionixNet with N-Core Multi-Attention Mechanism","volume":"33","author":"Y Narayan","year":"2025","journal-title":"Arch Computat Methods Eng"},{"issue":"23","key":"pone.0348670.ref027","doi-asserted-by":"crossref","first-page":"3996","DOI":"10.3390\/electronics11233996","article-title":"Deep Learning for Predicting Congestive Heart Failure","volume":"11","author":"F Goretti","year":"2022","journal-title":"Electronics"},{"key":"pone.0348670.ref028","doi-asserted-by":"crossref","first-page":"109720","DOI":"10.1016\/j.compbiomed.2025.109720","article-title":"A robust and generalized framework in diabetes classification across heterogeneous environments","volume":"186","author":"H Zhou","year":"2025","journal-title":"Comput Biol Med"},{"issue":"2","key":"pone.0348670.ref029","doi-asserted-by":"crossref","first-page":"100219","DOI":"10.1016\/j.tbench.2025.100219","article-title":"Comparative study of deep learning models for Parkinson\u2019s disease detection","volume":"5","author":"A Salihu Aliero","year":"2025","journal-title":"BenchCouncil Transactions on Benchmarks, Standards and Evaluations"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:11:01Z","timestamp":1778281861000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0348670"}},"subtitle":[],"editor":[{"given":"Kyungwon","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":29,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0348670","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]}}}