{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:48:33Z","timestamp":1782366513452,"version":"3.54.5"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>The reliable prediction of endocrine disorders remains a significant challenge in clinical decision support, particularly regarding the simultaneous achievement of predictive accuracy, interpretability, and reliability. In this study, we propose a Gated Multi-Task Attention Network (GMTAN) for endocrine disorder prediction and clinically oriented decision support. The framework jointly models thyroid disorder and polycystic ovary syndrome (PCOS) prediction using heterogeneous endocrine datasets while integrating uncertainty estimation and explainability within a unified architecture. The proposed model combines shared feature representation learning with task-specific gating and attention mechanisms to capture both common and disease-specific endocrine patterns. To improve reliability, Monte Carlo Dropout is incorporated during inference to estimate predictive uncertainty and confidence. In addition, Shapley Additive exPlanations (SHAP)-based feature attribution and attention visualization are used to provide clinically interpretable explanations for individual predictions. Experiments were conducted using the UCI Thyroid dataset and the Kaggle PCOS clinical dataset. To improve reproducibility, all experiments were repeated across multiple runs using fixed random seeds, and model performance was evaluated using classification, calibration, and reliability metrics. The proposed GMTAN achieved area under the receiver operating characteristic curve (AUROC) scores of 0.98 and 0.97 for thyroid and PCOS prediction tasks, respectively, demonstrating improved calibration performance compared with baseline machine learning and deep learning models. The results suggest that integrating multi-task learning, uncertainty-aware inference, and explainability within a single framework can improve both predictive performance and interpretability for endocrine disorder prediction. While additional clinical validation is still necessary, the proposed framework demonstrates potential as a clinically oriented assistive decision support system.<\/jats:p>","DOI":"10.3389\/frai.2026.1881082","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:31:14Z","timestamp":1782365474000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A reliable and explainable deep learning framework for clinical-grade endocrine disorder risk prediction and decision support"],"prefix":"10.3389","volume":"9","author":[{"given":"Mohammed Yacoob","family":"B A","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology (VIT University)","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayashree","family":"J","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology (VIT University)","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"515","DOI":"10.3390\/computers14120515","article-title":"Fair and explainable multitask deep learning on synthetic endocrine trajectories for real-time prediction of stress, performance, and neuroendocrine states","volume":"14","author":"Abdullah","year":"2025","journal-title":"Computers"},{"key":"ref5001","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/s12911-025-02944-6","article-title":"The role of explainable artificial intelligence in disease prediction: a systematic literature review and future research directions","volume":"25","author":"Alkhanbouli","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"106156","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of CXR images into COVID-19, pneumonia and tuberculosis using deep learning and XAI","volume":"150","author":"Bhandari","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref7001","doi-asserted-by":"publisher","first-page":"102506","DOI":"10.1016\/j.artmed.2023.102506","article-title":"Rams, hounds and white boxes: investigating human\u2013AI collaboration protocols in medical diagnosis","volume":"138","author":"Cabitza","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"ref6001","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1038\/s41467-023-43095-4","article-title":"Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma","volume":"15","author":"Chanda","year":"2024","journal-title":"Nat. Commun."},{"key":"ref3","author":"Chauhan","year":"2025"},{"key":"ref4","author":"Chauhan","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1007\/s11277-022-09467-7","article-title":"Performance assessment of machine learning classifiers using selective feature approaches for cervical cancer detection","volume":"124","author":"Chauhan","year":"2022","journal-title":"Wirel. Pers. Commun."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"4214817","DOI":"10.1155\/2023\/4214817","article-title":"HDFCN: a robust hybrid deep network based on feature concatenation for cervical cancer diagnosis on WSI pap smear slides","volume":"2023","author":"Chauhan","year":"2023","journal-title":"Biomed. Res. Int."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"18167","DOI":"10.1007\/s11227-023-05356-3","article-title":"XAI\u2013reduct: accuracy preservation despite dimensionality reduction for heart disease classification using explainable AI","volume":"79","author":"Das","year":"2023","journal-title":"J. Supercomput."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"3081","DOI":"10.1007\/s11831-025-10380-y","article-title":"Advances in machine learning and deep learning for hormonal disorder diagnosis: an exhaustive review on PCOS, thyroid, and optimization techniques","volume":"33","author":"Dhanka","year":"2025","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1038\/s41746-023-00813-y","article-title":"Explainable artificial intelligence incorporated with domain knowledge diagnosing early gastric neoplasms under white light endoscopy","volume":"6","author":"Dong","year":"2023","journal-title":"npj Digital Med"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.08608","article-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017","journal-title":"arXiv"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41746-021-00445-0","article-title":"A hierarchical expert-guided machine learning framework for clinical decision support systems: an application to traumatic brain injury prognostication","volume":"4","author":"Farzaneh","year":"2021","journal-title":"npj Digital Med"},{"key":"ref9002","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.3389\/fnins.2019.01346","article-title":"Explainable artificial intelligence for neuroscience: Behavioral Neurostimulation","volume":"13","author":"Fellous","year":"2019","journal-title":"Front. Neurosci."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1038\/s41574-024-01025-4","article-title":"Thyroid nodules: diagnosis and management","volume":"20","author":"Grani","year":"2024","journal-title":"Nat. Rev. Endocrinol."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s13014-022-02035-0","article-title":"Explainable AI for CNN-based prostate tumor segmentation in multi-parametric MRI correlated to whole mount histopathology","volume":"17","author":"Gunashekar","year":"2022","journal-title":"Radiat. Oncol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1007\/s44196-023-00388-2","article-title":"Detecting thyroid disease using an optimized machine learning model based on differential evolution","volume":"17","author":"Gupta","year":"2024","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"ref4001","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1038\/s43856-026-01449-1","article-title":"Explainable deep learning framework incorporating medical knowledge for insulin titration in diabetes","volume":"6","author":"He","year":"2026","journal-title":"Commun. Med."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3192024","DOI":"10.1109\/access.2022.3192024","article-title":"Uncertainty-aware deep learning methods for robust diabetic retinopathy classification","volume":"10","author":"Jaskari","year":"2022","journal-title":"IEEE Access"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/s12020-025-04378-6","article-title":"Machine learning in endocrinology: current applications and future perspectives","volume":"90","author":"Kami\u0144ska","year":"2025","journal-title":"Endocrine"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s12020-023-03341-7","article-title":"Machine learning models for differential diagnosis of Cushing\u2019s disease and ectopic ACTH secretion syndrome","volume":"80","author":"Lyu","year":"2023","journal-title":"Endocrine"},{"key":"ref3001","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1016\/j.csbj.2023.01.043","article-title":"Deep learning facilitates multi-data type analysis and predictive biomarker discovery in Cancer precision medicine","volume":"21","author":"Mathema","year":"2023","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"15409","DOI":"10.1038\/s41598-023-42157-3","article-title":"Supervised machine learning to validate a novel scoring system for the prediction of disease remission of functional pituitary adenomas following transsphenoidal surgery","volume":"13","author":"McKevitt","year":"2023","journal-title":"Sci. Rep."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"673","DOI":"10.11591\/ijict.v14i2.pp673-683","article-title":"Advanced predictive models for thyroid disease comorbidities using machine learning and deep learning: a comprehensive review","volume":"14","author":"Mohammed","year":"2025","journal-title":"Int. J. Informat. Commun. Technol."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"18627","DOI":"10.1007\/s00521-024-10171-9","article-title":"PODBoost: an explainable AI model for polycystic ovarian syndrome detection using grey wolf-based feature selection approach","volume":"36","author":"Moral","year":"2024","journal-title":"Neural Comput. & Applic."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1097\/SLA.0000000000006480","article-title":"Machine learning-based algorithm for the early prediction of postoperative hypocalcemia risk after thyroidectomy","volume":"280","author":"Muller","year":"2024","journal-title":"Ann. Surg."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"314","DOI":"10.3390\/cancers15010314","article-title":"An explainable AI-enabled framework for interpreting pulmonary diseases from chest radiographs","volume":"15","author":"Naz","year":"2023","journal-title":"Cancer"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.21123\/bsj.2023.8544","article-title":"Exploring the challenges of diagnosing thyroid disease with imbalanced data and machine learning: a systematic literature review","volume":"21","author":"Saleh","year":"2024","journal-title":"Baghdad Sci. J."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.ceh.2025.01.002","article-title":"Enhancing thyroid disease prediction and comorbidity management through advanced machine learning frameworks","volume":"8","author":"Sanju","year":"2025","journal-title":"Clin. Epidemiol. Health"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"936","DOI":"10.3390\/genes14040936","article-title":"Unraveling the dysbiosis of vaginal microbiome to understand cervical cancer disease etiology\u2014an explainable AI approach","volume":"14","author":"Sekaran","year":"2023","journal-title":"Genes"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.jaut.2017.12.001","article-title":"Activation of thyroid antigen-reactive B cells in recent onset autoimmune thyroid disease patients","volume":"89","author":"Smith","year":"2018","journal-title":"J. Autoimmun."},{"key":"ref8001","doi-asserted-by":"publisher","first-page":"5934","DOI":"10.1038\/s41598-023-32518-3","article-title":"An interpretable and interactive deep learning algorithm for a clinically applicable retinal fundus diagnosis system by modelling finding-disease relationship","volume":"13","author":"Son","year":"2023","journal-title":"Sci. Rep."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1016\/j.ebiom.2019.03.041","article-title":"Down-regulation of microRNA-592 in obesity contributes to hyperglycemia and insulin resistance","volume":"42","author":"Song","year":"2019","journal-title":"EBioMedicine"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"108076","DOI":"10.1016\/j.compbiomed.2024.108076","article-title":"Explaining protein\u2013protein interactions with knowledge graph-based semantic similarity","volume":"170","author":"Sousa","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1973","DOI":"10.2337\/db20-1973-P","article-title":"Single-nuclei transcriptomics of human adipose tissue identify distinct adipocyte progenitor subpopulations in type 2 diabetes","volume":"69","author":"Strieder-Barboza","year":"2020","journal-title":"Diabetes"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e36556","DOI":"10.1016\/j.heliyon.2024.e36556","article-title":"Advancing thyroid care: an accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques","volume":"10","author":"Sutradhar","year":"2024","journal-title":"Heliyon"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"5998","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Informat. Proces. Syst."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1038\/s41591-023-02552-9","article-title":"Optimized glycemic control of type 2 diabetes with reinforcement learning: a proof-of-concept trial","volume":"29","author":"Wang","year":"2023","journal-title":"Nat. Med."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"19007","DOI":"10.1038\/s41598-023-46294-7","article-title":"Machine learning-based prediction models for parathyroid carcinoma using pre-surgery cognitive function and clinical features","volume":"13","author":"Wang","year":"2023","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1038\/s41746-025-01652-9","article-title":"Multimodal GPT model for assisting thyroid nodule diagnosis and management","volume":"8","author":"Yao","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref1001","doi-asserted-by":"publisher","first-page":"120114","DOI":"10.1016\/j.eswa.2023.120114","article-title":"Discovering topics and trends in the field of artificial intelligence: using LDA topic Modeling","volume":"225","author":"Yu","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e7065","DOI":"10.1002\/cam4.7065","article-title":"An automatic parathyroid recognition and segmentation model based on deep learning of near-infrared autofluorescence imaging","volume":"13","author":"Yu","year":"2024","journal-title":"Cancer Med."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"104412","DOI":"10.1016\/j.bspc.2022.104412","article-title":"Multi-point attention-based semi-supervised learning for diabetic retinopathy classification","volume":"80","author":"Zhang","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref2001","doi-asserted-by":"publisher","first-page":"700061","DOI":"10.3389\/fcell.2021.700061","article-title":"DeepGP: an integrated deep learning method for endocrine disease gene prediction using omics data","volume":"9","author":"Zhang","year":"2021","journal-title":"Front. Cell Dev. Biol."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41746-025-01455-y","article-title":"A deep learning based ultrasound diagnostic tool driven by 3D visualization of thyroid nodules","volume":"8","author":"Zhou","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref9001","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.future.2023.02.022","article-title":"A privacy-preserving logistic regression-based diagnosis scheme for digital healthcare","volume":"144","author":"Zhou","year":"2023","journal-title":"Futur. Gener. Comput. Syst."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1881082\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:31:15Z","timestamp":1782365475000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1881082\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":48,"alternative-id":["10.3389\/frai.2026.1881082"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1881082","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"article-number":"1881082"}}