{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T06:14:46Z","timestamp":1788243286880,"version":"build-2803163510"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004728","name":"VIT University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004728","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>The prediction of whether a diabetic patient will return to the hospital within 30 days is a very difficult clinical situation to navigate. Predicting the chance of a 30- day readmission depends on a wide range of patient-specific risk factors and the variability in how individual patients respond to medication prescribed for them. Traditional machine-learning models are capable of finding patterns in electronic medical records but are typically unable to provide a clear picture of the physiological interactions between the patient and their prescribed drug(s). One way to predict the likelihood of diabetes-related rehospitalization is using a combination of machine-learning risk factors and physiologically based pharmacokinetics (PBPK). An optimized version of the XG Boost machine-learning algorithm was trained on a large in-patient dataset (approximately 100,000 patient encounters) and achieved a predictive model with an area under the receiver operating characteristic curve (AUC) of 0.68 with a recall of 0.60 at clinically meaningful cut-offs. These findings are similar to what has been previously reported in the literature (0.60\u20130.70) for diabetes-related rehospitalization risk and support the utility of the XG Boost algorithm as a reliable clinical screening tool. Concurrently, multiple PBPK simulations were run to assess the effects chronic renal or hepatic impairments have on PBPK; results show renal impairment results in the highest systemic drug exposures. Predictive risk and simulated exposure will be integrated to yield a patient-specific risk\/exposure phenotype and enable clinically meaningful stratification into actionable subgroups. Through this new method, it becomes possible to discern pharmacological vs. non-pharmacological contributors to readmission risk, thus facilitating targeted intervention strategies such as dose modulation, enhanced monitoring, and coordinated care. This work's value lies not in improving prediction accuracy by just a few points, but rather in a new approach to converting static risk prediction into a clinically actionable decision support system based on physiology. The proposed Digital Twin framework offers a scalable path to personalized post-discharge patient management and provides the basis for furthering the implementation of precision medicine in the field of digital health.<\/jats:p>","DOI":"10.3389\/fdgth.2026.1867505","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:32:55Z","timestamp":1788240775000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A hybrid ML-PBPK digital twin framework for clinically interpretable readmission risk and drug exposure stratification in diabetes"],"prefix":"10.3389","volume":"8","author":[{"given":"Nihaal","family":"Ahmed.K","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jafar Ali","family":"Ibrahim Syed Masood","sequence":"additional","affiliation":[{"name":"Department of Quantum AI, School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"289","DOI":"10.53730\/ijhs.v8n3.15189","article-title":"Predicting hospital readmissions in diabetes patients: a comparative study of machine learning models","volume":"8","author":"Gandra","year":"2024","journal-title":"Int J Health Sci (Qassim)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/14604582231164694","article-title":"Early prediction of 30- and 14-day all-cause unplanned readmissions","volume":"29","author":"Lin","year":"2023","journal-title":"Health Informatics J"},{"key":"B3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.21037\/jmai-24-70","article-title":"Comparison of machine learning models for predicting 30-day readmission rates for patients with diabetes","volume":"7","author":"Liu","year":"2024","journal-title":"J Med Artif Intell"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1302338","DOI":"10.3389\/fdgth.2023.1302338","article-title":"Digital patient twins for personalized therapeutics and pharmaceutical manufacturing","volume":"5","author":"Fischer","year":"2024","journal-title":"Front Digit Health"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1686415","DOI":"10.3389\/fphar.2025.1686415","article-title":"A digital twin of glimepiride for personalized and stratified diabetes treatment","volume":"16","author":"Elias","year":"2025","journal-title":"Front Pharmacol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e0249594","DOI":"10.1371\/journal.pone.0249594","article-title":"Physiologically based metformin pharmacokinetics model of mice and scale-up to humans for the estimation of concentrations in various tissues","volume":"16","author":"Zake","year":"2021","journal-title":"PLoS One"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1007\/s40262-023-01310-x","article-title":"Bridging the worlds of pharmacometrics and machine learning","volume":"62","author":"Stankevi\u010di\u016bt\u0117","year":"2023","journal-title":"Clin Pharmacokinet"},{"key":"B8","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1186\/s40537-025-01280-w","article-title":"Digital twins in healthcare: a review of AI-powered practical applications across health domains","volume":"12","author":"Elgammal","year":"2025","journal-title":"J Big Data"},{"key":"B9","doi-asserted-by":"publisher","first-page":"895556","DOI":"10.3389\/fphar.2022.895556","article-title":"Application of physiologically based pharmacokinetic modeling in preclinical studies: a feasible strategy to practice the principles of 3Rs","volume":"13","author":"Yuan","year":"2022","journal-title":"Front Pharmacol"},{"key":"B10","doi-asserted-by":"crossref","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"Hager","year":"2024","journal-title":"Nat Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1208\/ps060106","article-title":"Physiologically based pharmacokinetics in drug development and regulatory science: a workshop report (Georgetown University, Washington, DC, May 29\u201330, 2002)","volume":"6","author":"Rowland","year":"2004","journal-title":"AAPS PharmSci"},{"key":"B12","first-page":"358","article-title":"DT4PCP: a digital twin framework for personalized care planning applied to type 2 diabetes management","author":"Russo","year":"2025"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.3390\/jcm12062094","article-title":"Human digital twin for personalized elderly type 2 diabetes management","volume":"12","author":"Thamotharan","year":"2023","journal-title":"J Clin Med"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1336050","DOI":"10.3389\/fdgth.2024.1336050","article-title":"A framework towards digital twins for type 2 diabetes","volume":"6","author":"Zhang","year":"2024","journal-title":"Front Digit Health"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e0328848","DOI":"10.1371\/journal.pone.0328848","article-title":"Predicting 30-day hospital readmissions using ClinicalT5 with structured and unstructured electronic health records","volume":"20","author":"Pandey","year":"2025","journal-title":"PLoS One"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.32604\/cmes.2025.058821","article-title":"Predictive analytics for diabetic patient care: leveraging AI to forecast readmission and hospital stays","volume":"143","author":"Albahli","year":"2025","journal-title":"Comput Model Eng Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/s41746-020-0249-z","article-title":"Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence","volume":"3","author":"Hilton","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"65","DOI":"10.17932\/IAU.ABMYOD.2006.005\/abmyod_v20i71005","article-title":"Simulation of physiological parameters for homeostatic maintenance: the role of digital twin technology","volume":"20","author":"Odaba\u015fi","year":"2006","journal-title":"Anadolu bil Meslek Y\u00fcksekokulu Dergisi"},{"key":"B19","doi-asserted-by":"publisher","first-page":"108321","DOI":"10.1016\/j.compbiomed.2024.108321","article-title":"Predictive analytics for cardiovascular patient readmission and mortality: an explainable approach","volume":"174","author":"Huberts","year":"2024","journal-title":"Comput Biol Med"},{"key":"B20","author":"Roquemen-Echeverri","year":""},{"key":"B21","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.1007\/s40262-025-01547-8","article-title":"Methodological techniques used in machine learning to support individualized drug dosing regimens based on pharmacokinetic data: a scoping review","volume":"64","author":"Methaneethorn","year":"2025","journal-title":"Clin Pharmacokinet"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1407994","DOI":"10.3389\/fsysb.2024.1407994","article-title":"The rise of scientific machine learning: a perspective on combining mechanistic modelling with machine learning for systems biology","volume":"4","author":"Noordijk","year":"2024","journal-title":"Front Syst Biol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"759","DOI":"10.3389\/fphar.2020.00759","article-title":"Artificial intelligence and machine learning applied at the point of care","volume":"11","author":"Angehrn","year":"2020","journal-title":"Front Pharmacol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"121796","DOI":"10.1016\/j.eswa.2023.121796","article-title":"IDoser: improving individualized dosing policies with clinical practice and machine learning","volume":"238","author":"Correa","year":"2024","journal-title":"Expert Syst Appl"},{"key":"B25","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1186\/s13000-025-01686-3","article-title":"Fostering trust and interpretability: integrating explainable AI (XAI) with machine learning for enhanced disease prediction and decision transparency","volume":"20","author":"Agrawal","year":"2025","journal-title":"Diagn Pathol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s00701-024-05892-8","article-title":"A critical moment in machine learning in medicine: on reproducible and interpretable learning","volume":"166","author":"Ciobanu-Caraus","year":"2024","journal-title":"Acta Neurochir (Wien)"},{"key":"B27","volume-title":"Development of Physiologically Based Pharmacokinetics Model for Prediction of Drug Disposition in Diabetic Patients","author":"Alqahtani","year":"2022"},{"key":"B28","doi-asserted-by":"publisher","first-page":"298","DOI":"10.29304\/jqcsm.2024.16.41805","article-title":"Hybrid models in diabetes prediction","volume":"16","author":"Zaid","year":"2024","journal-title":"J Al-Qadisiyah Comput Sci Math"},{"key":"B29","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.ifacol.2024.10.014","article-title":"Modeling principles for a physiology-based whole-body model of human metabolism","volume":"58","author":"Blicher","year":"2024","journal-title":"IFAC-PapersOnLine"},{"key":"B30","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1002\/cpt.3289","article-title":"Dose optimization informed by PBPK modeling: state-of-the art and future","volume":"116","author":"Rowland Yeo","year":"2024","journal-title":"Clin Pharmacol Ther"},{"key":"B31","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/cpt.1826","article-title":"Predicting inpatient medication orders from electronic health record data","volume":"108","author":"Rough","year":"2020","journal-title":"Clin Pharmacol Ther"},{"key":"B32","doi-asserted-by":"publisher","first-page":"19269","DOI":"10.1038\/s41598-024-64223-0","article-title":"Physiologically-based pharmacokinetic\/pharmacodynamic modeling of meropenem in critically ill patients","volume":"14","author":"Yang","year":"2024","journal-title":"Sci Rep"},{"key":"B33","doi-asserted-by":"publisher","first-page":"571","DOI":"10.3389\/fphar.2020.00571","article-title":"Broader implications of modeling and simulation (M&S) tools in pharmacotherapeutic decisions: a cautionary optimism","volume":"11","author":"Chaturvedula","year":"2020","journal-title":"Front Pharmacol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1111\/cts.12490","article-title":"Precision dosing: public health need, proposed framework, and anticipated impact","volume":"10","author":"Gonzalez","year":"2017","journal-title":"Clin Transl Sci"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.c1292c54","article-title":"Resolving the credibility crisis: recommendations for improving predictive algorithms for clinical utility","volume":"5","author":"Ruberg","year":"2023","journal-title":"Harv Data Sci Rev"},{"key":"B36","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.therap.2025.09.006","article-title":"Digital pharmacological twins: bridging multi-scale modelling and artificial intelligence for precision medicine: the DIGPHAT consortium","volume":"81","author":"Woillard","year":"2026","journal-title":"Therapies"},{"key":"B37","doi-asserted-by":"publisher","first-page":"29057","DOI":"10.1038\/s41598-025-14355-8","article-title":"A hybrid reinforcement learning and knowledge graph framework for financial risk optimization in healthcare systems","volume":"15","author":"Uddin","year":"2025","journal-title":"Sci Rep"},{"key":"B38","doi-asserted-by":"publisher","first-page":"e229","DOI":"10.37765\/ajmc.2023.89409","article-title":"Predicting hospital readmission in medicaid patients with diabetes using administrative and claims data","volume":"29","author":"Yun","year":"2023","journal-title":"Am J Manag Care"},{"key":"B39","doi-asserted-by":"publisher","first-page":"109413","DOI":"10.1016\/j.compchemeng.2025.109413","article-title":"Dynamic hybrid modeling: incremental identification and model predictive control","volume":"204","author":"Caspari","year":"2026","journal-title":"Comput Chem Eng"},{"key":"B40","doi-asserted-by":"publisher","first-page":"e1010988","DOI":"10.1371\/journal.pcbi.1010988","article-title":"Bridging the gap between mechanistic biological models and machine learning surrogates","volume":"19","author":"Gherman","year":"2023","journal-title":"PLoS Comput Biol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"ooac063","DOI":"10.1093\/jamiaopen\/ooac063","article-title":"Bias or biology? Importance of model interpretation in machine learning studies from electronic health records","volume":"5","author":"Momenzadeh","year":"2022","journal-title":"JAMIA Open"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/toxsci\/kfac101","article-title":"Machine learning and artificial intelligence in physiologically based pharmacokinetic modeling","volume":"191","author":"Chou","year":"2023","journal-title":"Toxicol Sci"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1380685","DOI":"10.3389\/fsysb.2024.1380685","article-title":"Coupling quantitative systems pharmacology modelling to machine learning and artificial intelligence for drug development: its pAIns and gAIns","volume":"4","author":"Folguera-Blasco","year":"2024","journal-title":"Front Syst Biol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.3390\/jpm13101522","article-title":"Digital twins in healthcare: methodological challenges and opportunities","volume":"13","author":"Meijer","year":"2023","journal-title":"J Pers Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/BigData66926.2025.11402599","article-title":"Predictive modeling and explainable AI for veterinary safety profiles, residue assessment, and health outcomes using real-world data and physicochemical properties","author":"Sholehrasa","year":"2025","journal-title":"IEEE Big Data 2025 (conference)"},{"key":"B46","doi-asserted-by":"publisher","first-page":"e031981","DOI":"10.1161\/JAHA.123.031981","article-title":"Building digital twins for cardiovascular health: from principles to clinical impact","volume":"13","author":"Sel","year":"2024","journal-title":"J Am Heart Assoc"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.01488","article-title":"Digital twin generators for disease modeling","author":"Alam","year":"2024"},{"key":"B48","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1038\/s41746-025-02004-3","article-title":"Large language models forecast patient health trajectories enabling digital twins","volume":"8","author":"Makarov","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B49","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13073-025-01435-7","article-title":"Digital twins as global learning health and disease models for preventive and personalized medicine","volume":"17","author":"Li","year":"2025","journal-title":"Genome Med"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1007\/s11095-023-03538-5","article-title":"Physiologically-based pharmacokinetic modeling of PAXLOVID\u2122 with first-order absorption kinetics","volume":"40","author":"Sagawa","year":"2023","journal-title":"Pharm Res"},{"key":"B51","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/s41746-024-01402-3","article-title":"Challenges and opportunities for digital twins in precision medicine from a complex systems perspective","volume":"8","author":"De Domenico","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1050579","DOI":"10.3389\/fcdhc.2022.1050579","article-title":"Clinical risk factors and social needs of 30-day readmission among patients with diabetes: a retrospective study of the Deep South","volume":"3","author":"McDaniel","year":"2022","journal-title":"Front Clin Diabetes Healthc"},{"key":"B53","first-page":"607","article-title":"Interpretable mechanistic representations for meal-level glycemic control in the wild","author":"Wang","year":"2023","journal-title":"Proc Mach Learn Res"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1867505\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:32:57Z","timestamp":1788240777000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1867505\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":53,"alternative-id":["10.3389\/fdgth.2026.1867505"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1867505","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,1]]},"article-number":"1867505"}}