{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T03:56:26Z","timestamp":1786420586014,"version":"3.56.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:00:00Z","timestamp":1770336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Most machine learning models for diabetes prediction rely on small, homogeneous datasets and fixed thresholds, producing binary outputs with limited clinical utility. These approaches lack generalizability, probabilistic awareness, and interpretability, which are essential for real-world healthcare adoption. We present Diabetes Risk via Explainable AI Modeling (D.R.E.A.M.), a framework for Type 2 diabetes mellitus (T2DM) risk prediction that delivers continuous, calibrated probabilities with transparent explanations. D.R.E.A.M. integrates two complementary datasets (PIMA and BRFSS 2015) after excluding gestational diabetes cases, applies clinically guided feature engineering and class balancing, and trains ensemble models (Random Forest, XGBoost, LightGBM). Decision thresholds are optimized using precision\u00e2\u20ac\u201crecall curve analysis rather than default cutoffs, enabling clinically meaningful stratification. Model interpretability is achieved through SHapley Additive exPlanations (SHAP), providing both global and patient-level insights. All models achieved Area Under the Curves above 0.83 and F1-scores of 0.78, with Random Forest offering the best balance of sensitivity (recall = 0.89 at an optimized threshold of 0.389) and interpretability. SHAP confirmed the contribution of both physiological and behavioral factors, including glucose, BMI, blood pressure, cholesterol, and physical activity. Accessible via a lightweight web interface, D.R.E.A.M. provides real-time, explainable risk scores to support personalized preventive strategies. In summary, D.R.E.A.M. advances beyond conventional post-hoc explainability by integrating calibrated probabilistic predictions, PRC-based thresholding, and direct clinician-facing deployment. This combination transforms it from a research prototype into a transparent and clinically actionable decision support system.<\/jats:p>","DOI":"10.1007\/s11042-026-21240-7","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:55:49Z","timestamp":1770375349000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["D.R.E.A.M: diabetes risk via explainable AI modeling"],"prefix":"10.1007","volume":"85","author":[{"given":"Domenico","family":"Rossi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessia","family":"Auriemma Citarella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiola","family":"De Marco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Di Biasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7648-8709","authenticated-orcid":false,"given":"Huiru","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genoveffa","family":"Tortora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"issue":"3","key":"21240_CR1","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.3390\/ijms26031094","volume":"26","author":"E M\u0142ynarska","year":"2025","unstructured":"M\u0142ynarska E, Czarnik W, Dzie\u017ca N, J\u0119draszak W, Majchrowicz G, Prusinowski F, Stabrawa M, Rysz J, Franczyk B (2025) Type 2 diabetes mellitus: new pathogenetic mechanisms, treatment and the most important complications. Int J Mol Sci 26(3):1094","journal-title":"Int J Mol Sci"},{"key":"21240_CR2","doi-asserted-by":"crossref","unstructured":"Batulwar PS, Anjankar A (2024) Individuals diagnosed with type 2 diabetes mellitus and the status of vitamin B12 deficiency: a review. Cureus 16(2)","DOI":"10.7759\/cureus.55103"},{"issue":"10","key":"21240_CR3","doi-asserted-by":"publisher","first-page":"3757","DOI":"10.1007\/s12325-024-02957-z","volume":"41","author":"P Kushner","year":"2024","unstructured":"Kushner P, Khunti K, Cebri\u00e1n A, Deed G (2024) Early identification and management of chronic kidney disease: a narrative review of the crucial role of primary care practitioners. Adv Ther 41(10):3757\u20133770","journal-title":"Adv Ther"},{"issue":"22","key":"21240_CR4","doi-asserted-by":"publisher","first-page":"16157","DOI":"10.1007\/s00521-022-07049-z","volume":"35","author":"V Chang","year":"2023","unstructured":"Chang V, Bailey J, Xu QA, Sun Z (2023) Pima Indians diabetes mellitus classification based on machine learning (ML) algorithms. Neural Comput Appl 35(22):16157\u201316173","journal-title":"Neural Comput Appl"},{"key":"21240_CR5","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.procs.2018.05.122","volume":"132","author":"D Sisodia","year":"2018","unstructured":"Sisodia D, Sisodia DS (2018) Prediction of diabetes using classification algorithms. Procedia Comput Sci 132:157\u2013164","journal-title":"Procedia Comput Sci"},{"issue":"2","key":"21240_CR6","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s13410-021-00969-x","volume":"42","author":"H Naz","year":"2022","unstructured":"Naz H, Ahuja S (2022) SMOTE-SMO-based expert system for type II diabetes detection using PIMA dataset. Int J Diabetes Dev Countries 42(2):245\u2013253","journal-title":"Int J Diabetes Dev Countries"},{"key":"21240_CR7","doi-asserted-by":"crossref","unstructured":"Germaine M, O\u2019Higgins AC, Egan B, Healy G (2025) Evaluation of machine learning models for early prediction of gestational diabetes using retrospective electronic health records from current and previous pregnancies. medRxiv, 2025\u201305","DOI":"10.1101\/2025.05.12.25327431"},{"issue":"2","key":"21240_CR8","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/s00521-024-10437-2","volume":"37","author":"E \u015eahin","year":"2025","unstructured":"\u015eahin E, Arslan NN, \u00d6zdemir D (2025) Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning. Neural Comput Appl 37(2):859\u2013965","journal-title":"Neural Comput Appl"},{"issue":"2","key":"21240_CR9","doi-asserted-by":"publisher","first-page":"95","DOI":"10.4258\/hir.2016.22.2.95","volume":"22","author":"MA Jahani","year":"2016","unstructured":"Jahani MA, Mahdavi MR (2016) Comparison of predictive models for the early diagnosis of diabetes. Healthcare Inform Res 22(2):95\u2013101","journal-title":"Healthcare Inform Res"},{"issue":"5","key":"21240_CR10","first-page":"2341","volume":"27","author":"K-H Chang","year":"2023","unstructured":"Chang K-H, Chen L-C, Chen C-Y (2023) e-diagnosis system for diabetes prediction using machine learning and SHAP. Soft Comput 27(5):2341\u20132356","journal-title":"Soft Comput"},{"key":"21240_CR11","doi-asserted-by":"publisher","unstructured":"Rossi D, Citarella AA, De\u00a0Marco F, Di\u00a0Biasi L, Tortora G (2024) Comparative analysis of diabetes diagnosis: We-LSTM networks and WizardLM-powered diabetalk chatbot. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). pp 6859\u20136866. https:\/\/doi.org\/10.1109\/BIBM62325.2024.10821742","DOI":"10.1109\/BIBM62325.2024.10821742"},{"key":"21240_CR12","unstructured":"Guo C, Pleiss G, Sun Y, Weinberger KQ (2017) On calibration of modern neural networks. In: International conference on machine learning. PMLR, pp 1321\u20131330"},{"issue":"3","key":"21240_CR13","doi-asserted-by":"publisher","first-page":"0118432","DOI":"10.1371\/journal.pone.0118432","volume":"10","author":"T Saito","year":"2015","unstructured":"Saito T, Rehmsmeier M (2015) The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3):0118432","journal-title":"PLoS ONE"},{"key":"21240_CR14","doi-asserted-by":"publisher","first-page":"101421","DOI":"10.37349\/eemd.2025.101421","volume":"2","author":"E Basaran","year":"2025","unstructured":"Basaran E, Aktas G (2025) Waist-to-height ratio as a novel marker of metabolic syndrome in patients with type 2 diabetes mellitus. Explor Endocr Metab Dis 2:101421","journal-title":"Explor Endocr Metab Dis"},{"issue":"2","key":"21240_CR15","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1111\/jdi.14343","volume":"16","author":"A Mansoori","year":"2025","unstructured":"Mansoori A, Nosrati M, Dorchin M, Mohammadyari F, Derakhshan-Nezhad E, Ferns G, Esmaily H, Ghayour-Mobarhan M (2025) A novel index for diagnosis of type 2 diabetes mellitus: cholesterol, high density lipoprotein, and glucose (CHG) index. J Diabetes Investig 16(2):309\u2013314","journal-title":"J Diabetes Investig"},{"issue":"3","key":"21240_CR16","doi-asserted-by":"publisher","first-page":"318","DOI":"10.2337\/diacare.15.3.318","volume":"15","author":"RA DeFronzo","year":"1992","unstructured":"DeFronzo RA, Bonadonna RC, Ferrannini E (1992) Pathogenesis of NIDDM: a balanced overview. Diabetes Care 15(3):318\u2013368","journal-title":"Diabetes Care"},{"issue":"1","key":"21240_CR17","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1152\/ajpendo.00366.2002","volume":"284","author":"AM Chang","year":"2003","unstructured":"Chang AM, Halter JB (2003) Aging and insulin secretion. Am J Physiol-Endocrinol Metab 284(1):7\u201312","journal-title":"Am J Physiol-Endocrinol Metab"},{"issue":"7121","key":"21240_CR18","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1038\/nature05482","volume":"444","author":"SE Kahn","year":"2006","unstructured":"Kahn SE, Hull RL, Utzschneider KM (2006) Mechanisms linking obesity to insulin resistance and type 2 diabetes. Nature 444(7121):840\u2013846","journal-title":"Nature"},{"issue":"4","key":"21240_CR19","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1056\/NEJM199807233390404","volume":"339","author":"SM Haffner","year":"1998","unstructured":"Haffner SM, Lehto S, R\u00f6nnemaa T, Py\u00f6r\u00e4l\u00e4 K, Laakso M (1998) Mortality from coronary heart disease in subjects with type 2 diabetes and in nondiabetic subjects with and without prior myocardial infarction. N Engl J Med 339(4):229\u2013234","journal-title":"N Engl J Med"},{"issue":"2","key":"21240_CR20","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1210\/jc.2006-0513","volume":"92","author":"SM Grundy","year":"2007","unstructured":"Grundy SM (2007) Metabolic syndrome: a multiplex cardiovascular risk factor. J Clin Endocrinol Metab 92(2):399\u2013404","journal-title":"J Clin Endocrinol Metab"},{"key":"21240_CR21","doi-asserted-by":"crossref","unstructured":"Islam MR, Kowser S, Chowdhury AI, Shama S, Lamyea MMH (2025) Early prediction of liver disease using ensemble machine learning models and explainable AI techniques. Biomed Mater Devices, 1\u201338","DOI":"10.1007\/s44174-025-00410-5"},{"key":"21240_CR22","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","volume":"114","author":"M Belgiu","year":"2016","unstructured":"Belgiu M, Dr\u0103gu\u0163 L (2016) Random forest in remote sensing: a review of applications and future directions. ISPRS J Photogramm Remote Sens 114:24\u201331","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"21240_CR23","doi-asserted-by":"publisher","first-page":"1659362","DOI":"10.3389\/frai.2025.1659362","volume":"8","author":"T Jin","year":"2025","unstructured":"Jin T, Halili A (2025) Correction: predicting the risk of depression in older adults with disability using machine learning: an analysis based on CHARLS data. Front Artif Intell 8:1659362","journal-title":"Front Artif Intell"},{"issue":"1","key":"21240_CR24","doi-asserted-by":"publisher","first-page":"67363","DOI":"10.2196\/67363","volume":"4","author":"MA Roshani","year":"2025","unstructured":"Roshani MA, Zhou X, Qiang Y, Suresh S, Hicks S, Sethuraman U, Zhu D (2025) Generative large language model\u2013powered conversational AI App for personalized risk assessment: case study in COVID-19. JMIR AI 4(1):67363","journal-title":"JMIR AI"},{"key":"21240_CR25","unstructured":"Kurunthachalam A (2025) Hybrid XGBoost-LightGBM model for Bayesian optimization-based predictive analytics and personalised healthcare in cloud computing"},{"issue":"2","key":"21240_CR26","first-page":"101364","volume":"18","author":"HE Sadig","year":"2025","unstructured":"Sadig HE, Kamal M, Rehman M, Habadi MI, Alnagar DK, Yusuf M, Mohammed MOM, Alqasem OA, Meraou M (2025) Advanced time complexity analysis for real-time COVID-19 prediction in Saudi Arabia using LightGBM and XGBoost. J Radiat Res Appl Sci 18(2):101364","journal-title":"J Radiat Res Appl Sci"},{"key":"21240_CR27","doi-asserted-by":"publisher","unstructured":"Scilletta S, Di\u00a0Marco M, Miano N, Capuccio S, Musmeci M, Bosco G, Di\u00a0Giacomo\u00a0Barbagallo F, Marted\u00ec M, Rocca F, Vitale A, Scicali R, Piro S, Di\u00a0Pino A (2025) Cardiovascular risk profile in subjects with diabetes: is score2-diabetes reliable? Cardiovasc Diabetol 24. https:\/\/doi.org\/10.1186\/s12933-025-02769-7","DOI":"10.1186\/s12933-025-02769-7"},{"key":"21240_CR28","doi-asserted-by":"crossref","unstructured":"Moin EE, Seewald NJ, Halpern SD (2025) Development and validation of a simple model to predict patient height. medRxiv, 2025\u201303","DOI":"10.1101\/2025.03.12.25323846"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21240-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21240-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21240-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:55:52Z","timestamp":1770375352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21240-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,6]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["21240"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21240-7","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,6]]},"assertion":[{"value":"1 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"There are no conflicts of interest to declare","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"145"}}