{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:06:53Z","timestamp":1784099213855,"version":"3.55.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Glucagon-like peptide-1 receptor agonists (GLP-1 RAs) are widely used for the management of type 2 diabetes mellitus and obesity; however, substantial inter-individual variability in glycemic and weight loss outcomes remains. This study aimed to develop and validate machine learning (ML) models to predict glycemic control and weight loss outcomes following GLP-1 RA initiation using real-world data and to identify key features associated with treatment response.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We conducted a retrospective cohort study using data from the All of Us Research Program. Adult participants initiating GLP-1 RA therapy with available baseline and follow-up measurements were included. Two cohorts were constructed: a glycemic control cohort (\n                      <jats:italic>n<\/jats:italic>\n                      = 3,975) and a weight loss outcome cohort (\n                      <jats:italic>n<\/jats:italic>\n                      = 11,420). Glycemic control was defined as hemoglobin A1c (HbA1c) &amp;lt;7% at follow-up, and weight improvement was defined as achieving a body mass index (BMI) &amp;lt;30 kg\/m\u00b2. Multiple ML models, including logistic regression, random forest (RF), extreme gradient boosting (XGBoost), support vector machine, neural network, LightGBM, and CatBoost, were developed using 10-fold cross-validation. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and precision\u2013recall curves. SHapley Additive exPlanations (SHAP) were used to improve model interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For weight loss outcome prediction, ensemble models demonstrated superior performance, with RF and XGBoost achieving the highest discrimination (AUC \u2248 0.94) and accuracy (0.89\u20130.90). For glycemic control prediction, RF and XGBoost achieved modest performance (accuracy \u2248 0.73; AUC \u2248 0.79). SHAP analysis identified baseline BMI and body weight as the most influential features of weight improvement, while duration of diabetes, baseline HbA1c, and use of sulfonylureas or insulin were among the most important features of glycemic control.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Machine learning models, particularly tree-based ensemble methods, demonstrated strong potential for predicting treatment response to GLP-1 RA therapy. Integration of explainable ML approaches with real-world data may support personalized treatment strategies, and facilitate identification of patients most likely to benefit from GLP-1 RA therapy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1861563","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:11:17Z","timestamp":1784095877000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning algorithms for predicting glycemic control and weight loss outcomes in GLP-1 receptor agonist users"],"prefix":"10.3389","volume":"9","author":[{"given":"Tadesse M.","family":"Abegaz","sequence":"first","affiliation":[{"name":"School of Pharmacy, University of Texas at El Paso","place":["El Paso, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Frietze","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of Texas at El Paso","place":["El Paso, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1186\/s12967-025-06308-6","article-title":"Artificial intelligence-driven translational medicine: a machine learning framework for predicting disease outcomes and optimizing patient-centric care","volume":"23","author":"Abualigah","year":"2025","journal-title":"J. Transl. Med."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.3390\/electronics13163192","article-title":"Comparison of machine learning models for predicting interstitial glucose using smart watch and food log","volume":"13","author":"Ali","year":"2024","journal-title":"Electronics"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1186\/s12909-023-04698-z","article-title":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice","volume":"23","author":"Alowais","year":"2023","journal-title":"BMC Med. Educ."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"S128","DOI":"10.2337\/dc25-S006","article-title":"6. Glycemic goals and hypoglycemia: standards of care in diabetes-2025","volume":"48","author":"Elsayed","year":"2025","journal-title":"Diabetes Care"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1056\/NEJMsr1809937","article-title":"The \u201call of us\u201d research program","volume":"381","author":"AoURP","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple imputation by chained equations: what is it and how does it work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"20661","DOI":"10.1038\/s41598-023-47930-y","article-title":"Development and validation of a weight-loss predictor to assist weight loss management","volume":"13","author":"Biehl","year":"2023","journal-title":"Sci. Rep."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/j.2040-4603.2019.tb00055.x","article-title":"Contribution of adipose tissue inflammation to the development of type 2 diabetes mellitus","volume":"9","author":"Burhans","year":"2019","journal-title":"Compr. Physiol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s12911-025-03309-9","article-title":"Development and validation of a machine learning model for real-time blood glucose prediction for ICU patients","volume":"26","author":"Cai","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/nu17081391","article-title":"Predicting weight loss success after gastric sleeve surgery: a machine learning-based approach","volume":"17","author":"Casas Dom\u00ednguez","year":"2025","journal-title":"Nutrients"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1097\/HRP.0000000000000271","article-title":"Substance use disorders in global mental health delivery: epidemiology, treatment gap, and implementation of evidence-based treatments","volume":"28","author":"Connery","year":"2020","journal-title":"Harv. Rev. Psychiatry"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/S2213-8587(22)00340-0","article-title":"Pharmacogenomics of GLP-1 receptor agonists: a genome-wide analysis of observational data and large randomised controlled trials","volume":"11","author":"Dawed","year":"2023","journal-title":"Lancet Diabetes Endocrinol."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1016\/j.pcd.2022.10.005","article-title":"Determinants of response to the glucagon-like peptide-1 receptor agonists in a type 2 diabetes population in the real-world","volume":"16","author":"Franch-Nadal","year":"2022","journal-title":"Prim. Care Diabetes"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1061507","DOI":"10.3389\/fendo.2022.1061507","article-title":"Implementation of five machine learning methods to predict the 52-week blood glucose level in patients with type 2 diabetes","volume":"13","author":"Fu","year":"2023","journal-title":"Front. Endocrinol."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1016\/j.ajcnut.2024.09.003","article-title":"Prediction of individual weight loss using supervised learning: findings from the CALERIETM 2 study","volume":"120","author":"Glasbrenner","year":"2024","journal-title":"Am. J. Clin. Nutr."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"16080","DOI":"10.3390\/ijerph192316080","article-title":"Using tree-based machine learning for health studies: literature review and case series","volume":"19","author":"Hu","year":"2022","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref17","author":"Insulin","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1038\/s41586-023-06957-x","article-title":"Genomic data in the All of Us Research Program","volume":"627","year":"2024","journal-title":"Nature"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"20031","DOI":"10.1038\/s41598-025-96097-1","article-title":"Time to achieve optimal glycemic control and its determinants among diabetes mellitus patients receiving treatment: a retrospective study","volume":"15","author":"Kassie","year":"2025","journal-title":"Sci. Rep."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"100148","DOI":"10.1016\/j.cmpbup.2024.100148","article-title":"Artificial intelligence for clinical prediction: exploring key domains and essential functions","volume":"5","author":"Khalifa","year":"2024","journal-title":"Computer Methods Programs Biomedicine Update."},{"key":"ref21","first-page":"4765","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e1608","DOI":"10.1002\/mpr.1608","article-title":"A tutorial on conducting genome-wide association studies: quality control and statistical analysis","volume":"27","author":"Marees","year":"2018","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.3390\/biomedicines12061175","article-title":"Machine learning model in obesity to predict weight loss one year after bariatric surgery: a pilot study","volume":"12","author":"Nadal","year":"2024","journal-title":"Biomedicine"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1111\/cob.12128","article-title":"Predictors of weight-loss response with glucagon-like peptide-1 receptor agonist treatment among adolescents with severe obesity","volume":"6","author":"Nathan","year":"2016","journal-title":"Clinical obesity."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"55","DOI":"10.12688\/f1000research.13723.2","article-title":"Response heterogeneity: challenges for personalised medicine and big data approaches in psychiatry and chronic pain","volume":"7","author":"Norbury","year":"2018","journal-title":"F1000Res."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","article-title":"Evaluation metrics and statistical tests for machine learning","volume":"14","author":"Rainio","year":"2024","journal-title":"Sci. Rep."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"455","DOI":"10.3390\/medicina56090455","article-title":"Comparison of conventional statistical methods with machine learning in medicine: diagnosis, drug development, and treatment","volume":"56","author":"Rajula","year":"2020","journal-title":"Medicina"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"100570","DOI":"10.1016\/j.patter.2022.100570","article-title":"The All of Us Research Program: data quality, utility, and diversity","volume":"3","author":"Ramirez","year":"2022","journal-title":"Patterns."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"100686","DOI":"10.1016\/j.obmed.2026.100686","article-title":"Revolutionizing obesity treatment: the emerging role of GLP-1 receptor agonists and next-generation pharmacotherapies","volume":"60","author":"Rao","year":"2026","journal-title":"Obesity Medicine."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1038\/s41746-024-01299-y","article-title":"A machine-learned model for predicting weight loss success using weight change features early in treatment","volume":"7","author":"Shahabi","year":"2024","journal-title":"NPJ digital medicine."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e089477","DOI":"10.1136\/bmjopen-2024-089477","article-title":"Factors associated with weight loss response to GLP-1 analogues for obesity treatment: a retrospective cohort analysis","volume":"15","author":"Squire","year":"2025","journal-title":"BMJ Open"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"8985","DOI":"10.3390\/ijms21238985","article-title":"Obesity-related changes in high-density lipoprotein metabolism and function","volume":"21","author":"Stadler","year":"2020","journal-title":"Int. J. Mol. Sci."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"afae201","DOI":"10.1093\/ageing\/afae201","article-title":"New horizons in prediction modelling using machine learning in older people\u2019s healthcare research","volume":"53","author":"Stahl","year":"2024","journal-title":"Age Ageing"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1002\/oby.21404","article-title":"Effects of clinically significant weight loss with exercise training on insulin resistance and cardiometabolic adaptations","volume":"24","author":"Swift","year":"2016","journal-title":"Obesity"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"449","DOI":"10.3945\/ajcn.114.091520","article-title":"Predicting successful long-term weight loss from short-term weight-loss outcomes: new insights from a dynamic energy balance model (the POUNDS lost study)","volume":"101","author":"Thomas","year":"2015","journal-title":"Am. J. Clin. Nutr."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e0253125","DOI":"10.1371\/journal.pone.0253125","article-title":"Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: the Maastricht study","volume":"16","author":"Van Doorn","year":"2021","journal-title":"PLoS One"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/BF02913083","article-title":"Effect of increasing duration of diabetes mellitus type 2 on glycated hemoglobin and insulin sensitivity","volume":"21","author":"Verma","year":"2006","journal-title":"Indian J. Clin. Biochem."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1674308","DOI":"10.3389\/fendo.2025.1674308","article-title":"Predictive factors of body weight loss in patients with type 2 diabetes treated with GLP-1 receptor agonists: a 52-week prospective real-life study","volume":"16","author":"Vozza","year":"2025","journal-title":"Front. Endocrinol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"292","DOI":"10.2337\/dc24-1678","article-title":"Efficacy of GLP-1 receptor agonists on weight loss, BMI, and waist circumference for patients with obesity or overweight: a systematic review, meta-analysis, and meta-regression of 47 randomized controlled trials","volume":"48","author":"Wong","year":"2025","journal-title":"Diabetes Care"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1038\/s41392-024-01931-z","article-title":"Glucagon-like peptide-1 receptor: mechanisms and advances in therapy","volume":"9","author":"Zheng","year":"2024","journal-title":"Signal Transduct. Target. Ther."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1861563\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:11:18Z","timestamp":1784095878000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1861563\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":40,"alternative-id":["10.3389\/frai.2026.1861563"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1861563","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1861563"}}