{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T01:09:34Z","timestamp":1787620174347,"version":"build-2736575974"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:00:00Z","timestamp":1780876800000},"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>Obesity is a multifactorial chronic disease whose worldwide prevalence in adults has more than doubled since 1990, demanding a shift from reactive treatment towards early, personalised prevention. Artificial intelligence (AI) provides a methodological pathway for this shift by integrating heterogeneous, longitudinal evidence\u2014genomic, metabolomic, electronic health record (EHR), wearable Internet-of-Things (IoT), behavioural, and social-environmental\u2014and by translating that evidence into individualised, time-varying risk estimates. Yet the field is fragmented: most existing tools are unimodal, validated on narrow cohorts, opaque to clinicians, and disconnected from the workflows that would render their predictions actionable. In this Perspective we propose an explicit multimodal, risk-stratified framework that links five data layers to a continuous dynamic risk score R(t), defined as a weighted, time-varying aggregation of clinical, anthropometric, behavioural, psychosocial and pharmacological domains. R(t) drives an A\/B\/C tiering policy that allocates monitoring intensity and intervention modality proportional to risk, and feeds a metabolic\u2013behavioural digital-twin loop in which counterfactual interventions are tested in silico before deployment. We argue that three technical commitments are non-negotiable for translation: (i) cross-modal fusion architectures that respect informative missingness, (ii) explainable, equity-audited risk scoring, and (iii) a five-stage validation pipeline anchored in TRIPOD-AI, decision-curve analysis and post-market drift surveillance. We discuss how this framework reframes long-standing concerns\u2014black-box opacity, demographic bias, real-world fragility\u2014as design constraints rather than afterthoughts, and outline an actionable research agenda for clinically deployable, equitable AI in obesity prevention.<\/jats:p>","DOI":"10.3389\/frai.2026.1865219","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:17:47Z","timestamp":1780935467000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A multimodal, risk-stratified framework for AI-driven early risk prediction and personalised prevention in obesity"],"prefix":"10.3389","volume":"9","author":[{"given":"Suning","family":"Zhao","sequence":"first","affiliation":[{"name":"Alfred E. Mann School of Pharmacy and Pharmaceutical Sciences, University of Southern California","place":["Los Angeles, CA, United States"]},{"name":"Macau Society for Health Economics","place":["Macao, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chonin","family":"Cheang","sequence":"additional","affiliation":[{"name":"Macau Society for Health Economics","place":["Macao, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Macau Society for Health Economics","place":["Macao, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengioi","family":"Mio","sequence":"additional","affiliation":[{"name":"Macau Society for Health Economics","place":["Macao, Macao SAR, China"]},{"name":"Macau Yinkui Hospital","place":["Macao, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sintong","family":"Che","sequence":"additional","affiliation":[{"name":"Second Clinical Medical College, Nanjing Medical University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiian","family":"Kuok","sequence":"additional","affiliation":[{"name":"Macau Society for Health Economics","place":["Macao, Macao SAR, China"]},{"name":"Macau Yinkui Hospital","place":["Macao, Macao SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","first-page":"e40589","DOI":"10.2196\/40589","article-title":"Applications of artificial intelligence to obesity research: scoping review of methodologies","volume":"24","author":"An","year":"2022","journal-title":"J. Med. Internet Res."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"100165","DOI":"10.1016\/j.obpill.2025.100165","article-title":"Leveraging diagnosis and biometric data from the all of us research program to uncover disparities in obesity diagnosis","volume":"13","author":"Arseniev-Koehler","year":"2025","journal-title":"Obesity Pillars"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"396","DOI":"10.3390\/diagnostics15030396","article-title":"Harnessing artificial intelligence in obesity research and management: a comprehensive review","volume":"15","author":"Azmi","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"100065","DOI":"10.1016\/j.obpill.2023.100065","article-title":"Artificial intelligence and obesity management: An obesity medicine association (OMA) clinical practice statement (CPS) 2023","volume":"6","author":"Bays","year":"2023","journal-title":"Obesity Pillars"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.3390\/medicina61081403","article-title":"Barriers and facilitators to artificial intelligence implementation in diabetes management from healthcare workers' perspective: a scoping review","volume":"61","author":"Cangelosi","year":"2025","journal-title":"Medicina (Kaunas)"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"582","DOI":"10.37765\/ajmc.2022.89261","article-title":"Improving risk stratification using AI and social determinants of health","volume":"28","author":"Carroll","year":"2022","journal-title":"Am. J. Manag. Care"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e46036","DOI":"10.2196\/46036","article-title":"Effectiveness of an artificial intelligence-assisted app for improving eating behaviors: mixed methods evaluation","volume":"26","author":"Chew","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"107029","DOI":"10.1016\/j.cct.2022.107029","article-title":"Using artificial intelligence to optimize delivery of weight loss treatment: protocol for an efficacy and cost-effectiveness trial","volume":"124","author":"Forman","year":"2023","journal-title":"Contemp. Clin. Trials"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3506719","article-title":"Obesity prediction with EHR data: a deep learning approach with interpretable elements","volume":"3","author":"Gupta","year":"2022","journal-title":"ACM Transactions on Computing for Healthcare"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e48633","DOI":"10.2196\/48633","article-title":"Barriers to and facilitators of artificial intelligence adoption in health care: scoping review","volume":"11","author":"Hassan","year":"2024","journal-title":"JMIR Hum. Factors"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"4397","DOI":"10.1007\/s12325-022-02265-4","article-title":"The potential role of digital health in obesity care","volume":"39","author":"Hinchliffe","year":"2022","journal-title":"Adv. Ther."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"358","DOI":"10.3390\/medicina61020358","article-title":"The role of artificial intelligence in obesity risk prediction and management: approaches, insights, and recommendations","volume":"61","author":"Huang","year":"2025","journal-title":"Medicina (Kaunas)"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1643180","DOI":"10.3389\/fpubh.2025.1643180","article-title":"Algorithmic bias in public health AI: a silent threat to equity in low-resource settings","volume":"13","author":"Joseph","year":"2025","journal-title":"Front. Public Health"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"394","DOI":"10.7570\/jomes25035","article-title":"Multimodal and multidimensional artificial intelligence Technology in Obesity","volume":"34","author":"Lee","year":"2025","journal-title":"J. Obesity & Metabolic Syndrome"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1038\/s41366-024-01679-0","article-title":"Prospective prediction of childhood body mass index trajectories using multi-task Gaussian processes","volume":"49","author":"Leroy","year":"2025","journal-title":"Int. J. Obesity (London)"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2695","DOI":"10.3390\/nu17162695","article-title":"Integrating precision medicine and digital health in personalized weight management: the central role of nutrition","volume":"17","author":"Liu","year":"2025","journal-title":"Nutrients"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"CAT.25.0016","DOI":"10.1056\/CAT.25.0016","article-title":"Type 2 diabetes pharmacotherapy de-escalation through AI-enabled lifestyle modifications: a randomized clinical trial","volume":"6","author":"Pantalone","year":"2025","journal-title":"NEJM Catal. Innov. Care Deliv."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1431246","DOI":"10.3389\/fdgth.2025.1431246","article-title":"Privacy, ethics, transparency, and accountability in AI systems for wearable devices","volume":"7","author":"Radanliev","year":"2025","journal-title":"Front. Digital Health"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e70140","DOI":"10.2196\/70140","article-title":"Deep phenotyping of obesity: electronic health record-based temporal modeling study","volume":"27","author":"Ruan","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"ooaf076","DOI":"10.1093\/jamiaopen\/ooaf076","article-title":"A community-based approach to ethical decision-making in artificial intelligence for health care","volume":"8","author":"Senghor","year":"2025","journal-title":"JAMIA Open"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"25478","DOI":"10.1038\/s41598-024-76584-7","article-title":"One-year outcomes of a digital twin intervention for type 2 diabetes: a retrospective real-world study","volume":"14","author":"Shamanna","year":"2024","journal-title":"Sci. Rep."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41514-025-00211-6","article-title":"Optimizing metabolic health with digital twins","volume":"11","author":"Su","year":"2025","journal-title":"NPJ Aging"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1002\/bjs.10557","article-title":"Long-term follow-up after bariatric surgery in a national cohort","volume":"104","author":"Thereaux","year":"2017","journal-title":"Br. J. Surg."},{"key":"ref25","volume-title":"Obesity and Overweight\u2014Fact Sheet","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e69220","DOI":"10.2196\/69220","article-title":"Development of machine learning-based risk prediction models to predict rapid weight gain in infants: analysis of seven cohorts","volume":"11","author":"Zheng","year":"2025","journal-title":"JMIR Public Health Surveill."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1865219\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:17:47Z","timestamp":1780935467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1865219\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,8]]},"references-count":26,"alternative-id":["10.3389\/frai.2026.1865219"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1865219","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,8]]},"article-number":"1865219"}}