{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T17:06:27Z","timestamp":1781715987090,"version":"3.54.5"},"reference-count":21,"publisher":"American Diabetes Association","issue":"6","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.diabetesjournals.org\/journals\/pages\/license"}],"funder":[{"DOI":"10.13039\/100009633","name":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","doi-asserted-by":"publisher","award":["U01 DK106993"],"award-info":[{"award-number":["U01 DK106993"]}],"id":[{"id":"10.13039\/100009633","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Breakthrough T1D"},{"DOI":"10.13039\/100000060","name":"National Institute of Allergy and Infectious Diseases","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["diabetesjournals.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:sec>\n                    <jats:title\/>\n                    <jats:p>An inflection point (IP) marking accelerated \u03b2-cell decline occurs \u223c1\u20132 years before type 1 diabetes diagnosis. Precisely determining this timing could optimize clinical intervention. We developed machine learning models to predict proximity to the inferred metabolic IP using oral glucose tolerance test (OGTT) data from islet autoantibody-positive individuals in the TrialNet Pathway to Prevention study. OGTTs were retrospectively labeled by estimating time to the IP using thresholds from 1.2 to 1.6 years. Models were trained on engineered glucose and C-peptide dynamics, slopes, and composite indices, with feature selection by recursive feature elimination (RFE). Classifiers included support vector machines (SVM), random forests, and gradient boosting; a Cox proportional hazards model was also applied to estimate visit-level time to diagnosis and derive time-to-IP predictions. External validation was performed in the independent Diabetes Prevention Trial\u2013Type 1 cohort. The best-performing model\u2014SVM with RFE at the 1.4-year threshold\u2014achieved an area under the curve of 0.77 (95% CI 0.72\u20130.82). The Cox model provided complementary numeric estimates of time to diagnosis and time to IP, sensitive to the cohort-level lead time offset (\u0394). These findings show that machine learning and survival analysis can support early metabolic shift detection, enabling timely risk stratification and personalized monitoring in at-risk individuals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Article Highlights<\/jats:title>\n                    <jats:p>We undertook this study to improve early identification of the metabolic inflection point (IP) preceding clinical type 1 diabetes in autoantibody-positive individuals. We aimed to develop and validate machine learning models using oral glucose tolerance test\u2013derived dynamic features to detect proximity to the IP. A support vector machine trained on TrialNet Pathway to Prevention and tested on Diabetes Prevention Trial\u2013Type 1 achieved an area under the curve of 0.77 at 1.4 years prior to diagnosis, with strong calibration and interpretability. Additionally, a Cox proportional hazards model provided numeric estimates of time to IP, offering complementary predictions. These results can support earlier intervention and timely monitoring through personalized oral glucose tolerance test\u2013based risk stratification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2337\/db25-0961","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:56:56Z","timestamp":1774018616000},"page":"901-910","update-policy":"https:\/\/doi.org\/10.2337\/ada-journal-policies","source":"Crossref","is-referenced-by-count":1,"title":["Predicting the Timing of the Metabolic Inflection Point in Type 1 Diabetes Progression Using Machine Learning and Survival Analysis Models"],"prefix":"10.2337","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3138-1964","authenticated-orcid":false,"given":"Eslam","family":"Montaser","sequence":"first","affiliation":[{"name":"Division of Endocrinology and Metabolism, Indiana University School of Medicine 1 , Indianapolis, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7204-8367","authenticated-orcid":false,"given":"Jay M.","family":"Sosenko","sequence":"additional","affiliation":[{"name":"Division of Endocrinology, University of Miami 2 , Miami, FL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0102-0030","authenticated-orcid":false,"given":"Heba M.","family":"Ismail","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Indiana University School of Medicine 3 , Indianapolis, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1167","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"2026061712471946200_B1","doi-asserted-by":"crossref","first-page":"1964","DOI":"10.2337\/dc15-1419","article-title":"Staging presymptomatic type 1 diabetes: a scientific statement of JDRF, the Endocrine Society, and the American Diabetes Association","volume":"38","author":"Insel","year":"2015","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B2","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1001\/jama.2013.6285","article-title":"Seroconversion to multiple islet autoantibodies and risk of progression to diabetes in children","volume":"309","author":"Ziegler","year":"2013","journal-title":"JAMA"},{"key":"2026061712471946200_B3","doi-asserted-by":"crossref","first-page":"2264","DOI":"10.2337\/dc22-0167","article-title":"the transition from a compensatory increase to a decrease in C-peptide during the progression to type 1 diabetes and its relation to risk","volume":"45","author":"Ismail","year":"2022","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B4","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.jaut.2018.01.006","article-title":"Predicting progression to diabetes in islet autoantibody positive children","volume":"90","author":"Steck","year":"2018","journal-title":"J Autoimmun"},{"key":"2026061712471946200_B5","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1210\/clinem\/dgad472","article-title":"OGTT metrics surpass continuous glucose monitoring data for T1D prediction in multiple-autoantibody-positive individuals","volume":"109","author":"Ylescupidez","year":"2023","journal-title":"J Clin Endocrinol Metab"},{"key":"2026061712471946200_B6","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1210\/jc.2004-1133","article-title":"\u03b2-Cell function in subjects spanning the range from normal glucose tolerance to overt diabetes: a new analysis","volume":"90","author":"Ferrannini","year":"2005","journal-title":"J Clin Endocrinol Metab"},{"key":"2026061712471946200_B7","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1111\/dom.13982","article-title":"Early and late C-peptide responses during oral glucose tolerance testing are oppositely predictive of type 1 diabetes in autoantibody-positive individuals","volume":"22","author":"Ismail","year":"2020","journal-title":"Diabetes Obes Metab"},{"key":"2026061712471946200_B8","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.2337\/db11-1660","article-title":"The metabolic progression to type 1 diabetes as indicated by serial oral glucose tolerance testing in the Diabetes Prevention Trial-type 1","volume":"61","author":"Sosenko","year":"2012","journal-title":"Diabetes"},{"key":"2026061712471946200_B9","doi-asserted-by":"crossref","first-page":"643","DOI":"10.2337\/diacare.29.03.06.dc05-1006","article-title":"Patterns of metabolic progression to type 1 diabetes in the Diabetes Prevention Trial-Type 1","volume":"29","author":"Sosenko","year":"2006","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B10","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.2337\/dc21-0226","article-title":"Time to peak glucose and peak C-peptide during the progression to type 1 diabetes in the Diabetes Prevention Trial and TrialNet cohorts","volume":"44","author":"Voss","year":"2021","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B11","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1177\/19322968231209302","article-title":"Predicting the risk of developing type 1 diabetes using a one-week continuous glucose monitoring home test with classification enhanced by machine learning: an exploratory study","volume":"18","author":"Montaser","year":"2024","journal-title":"J Diabetes Sci Technol"},{"key":"2026061712471946200_B12","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1089\/dia.2023.0064","article-title":"Predicting immunological risk for stage 1 and stage 2 diabetes using a 1-week CGM home test, nocturnal glucose increments, and standardized liquid mixed meal breakfasts, with classification enhanced by machine learning","volume":"25","author":"Montaser","year":"2023","journal-title":"Diabetes Technol Ther"},{"key":"2026061712471946200_B13","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1089\/dia.2024.0496","article-title":"Enhancing type 1 diabetes immunological risk prediction with continuous glucose monitoring and genetic profiling","volume":"27","author":"Montaser","year":"2025","journal-title":"Diabetes Technol Ther"},{"key":"2026061712471946200_B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J Stat Soft"},{"key":"2026061712471946200_B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied Predictive Modeling.","author":"Kuhn","year":"2013"},{"key":"2026061712471946200_B16","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1136\/bmj.300.6719.230","article-title":"Analysis of serial measurements in medical research","volume":"300","author":"Matthews","year":"1990","journal-title":"BMJ"},{"key":"2026061712471946200_B17","doi-asserted-by":"crossref","first-page":"271","DOI":"10.2337\/dc14-1813","article-title":"A new approach for diagnosing type 1 diabetes in autoantibody-positive individuals based on prediction and natural history","volume":"38","author":"Sosenko","year":"2015","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B18","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1097\/MED.0000000000000267","article-title":"Staging the progression to type 1 diabetes with prediagnostic markers","volume":"23","author":"Sosenko","year":"2016","journal-title":"Curr Opin Endocrinol Diabetes Obes"},{"key":"2026061712471946200_B19","doi-asserted-by":"crossref","first-page":"2668","DOI":"10.2337\/dc20-0701","article-title":"The pathological evolution of glucose response curves during the progression to type 1 diabetes in the TrialNet Pathway to Prevention study","volume":"43","author":"Ismail","year":"2020","journal-title":"Diabetes Care"},{"key":"2026061712471946200_B20","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1210\/clinem\/dgae379","article-title":"Novel detection and progression markers for diabetes based on continuous glucose monitoring data dynamics","volume":"110","author":"Montaser","year":"2024","journal-title":"J Clin Endocrinol Metab"},{"key":"2026061712471946200_B21","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1177\/19322968251333441","article-title":"The use of continuous glucose monitoring to diagnose stage 2 type 1 diabetes","volume":"19","author":"Mader","year":"2025","journal-title":"J Diabetes Sci Technol"}],"container-title":["Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/diabetesjournals.org\/diabetes\/article-pdf\/75\/6\/901\/859549\/db250961.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/diabetesjournals.org\/diabetes\/article-pdf\/75\/6\/901\/859549\/db250961.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:47:25Z","timestamp":1781714845000},"score":1,"resource":{"primary":{"URL":"https:\/\/diabetesjournals.org\/diabetes\/article\/75\/6\/901\/164615\/Predicting-the-Timing-of-the-Metabolic-Inflection"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":21,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3,20]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.2337\/db25-0961","relation":{},"ISSN":["0012-1797","1939-327X"],"issn-type":[{"value":"0012-1797","type":"print"},{"value":"1939-327X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]}}}