{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:02:32Z","timestamp":1790226152114,"version":"4.1.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop, compare, and externally evaluate machine learning (ML) and Cox regression models for predicting fasting plasma glucose (FPG)-defined incident prediabetes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We performed a secondary analysis of a publicly available Chinese health-examination cohort and conducted an external comparative evaluation in a separate hospital-based cohort. The development cohort of adults with normal baseline fasting glucose was divided into training and internal validation sets. Candidate predictors were selected using least absolute shrinkage and selection operator (LASSO) regression. Six ML models and an initial proportional-hazards Cox model were compared using discrimination and threshold-based metrics. After identifying FPG nonproportionality, four Cox specifications were compared. Model selection considered fit, performance in the internal validation set and external cohort, complexity, and parsimony. The final model was evaluated at the primary 3-, 4-, and 5-year horizons using time-dependent area under the receiver operating characteristic curve (AUC), Brier scores, calibration, and decision curve analysis. SHapley Additive exPlanations (SHAP), sensitivity analyses, and an online calculator supported interpretation and implementation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 10, 592 participants, 1, 287 (12.2%) developed FPG-defined incident prediabetes over a mean follow-up of 3.05 years. LASSO retained 11 of 17 predictors. Random forest showed the highest apparent training performance, but its performance declined in the internal validation set and external cohort, whereas the initial Cox model demonstrated more consistent discrimination. FPG violated the proportional-hazards assumption. The extended Cox model incorporating FPG \u00d7 log(t\/3) (M2) had the lowest Akaike information criterion, accommodated the time-varying FPG effect, and performed comparably to more complex alternatives; it was therefore selected. M2 retained age, body mass index, diastolic blood pressure, FPG, and family history of diabetes. Its 3- and 4-year AUCs were 0.800 and 0.796 in training, 0.778 and 0.755 in internal validation, and 0.750 and 0.764 in the external cohort. Five-year performance was exploratory and less stable externally. SHAP identified FPG as the dominant contributor, and sensitivity analyses generally supported robustness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The final extended Cox model (M2) and online risk calculator may provide a practical framework for interpretable, individualized risk assessment of FPG-defined incident prediabetes, supporting early risk stratification and preventive risk-factor management using routinely available clinical indicators.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1862258","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T04:38:14Z","timestamp":1790224694000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and comparative evaluation of machine learning algorithms and Cox regression for predicting fasting plasma glucose-defined incident prediabetes: a longitudinal cohort study"],"prefix":"10.3389","volume":"17","author":[{"given":"Su","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changshun","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Toxicology and Cancer Biology, University of Kentucky","place":["Lexington, KY, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghan","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiqiu","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Cardiology, the Fifth Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"S49","DOI":"10.2337\/dc25-S002","article-title":"Diagnosis and classification of diabetes: Standards of care in diabetes-2025","volume":"48","year":"2025","journal-title":"Diabetes Care"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.4063","article-title":"Diagnosis and management of prediabetes: a review","volume":"329","author":"Echouffo-Tcheugui","year":"2023","journal-title":"JAMA"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2018.02.023","article-title":"IDF Diabetes Atlas: global estimates of diabetes prevalence for 2017 and projections for 2045","volume":"138","author":"Cho","year":"2018","journal-title":"Diabetes Res Clin Pract"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(12)60283-9","article-title":"Prediabetes: a high-risk state for diabetes development","volume":"379","author":"Tab\u00e1k","year":"2012","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.2337\/dca24-0012","article-title":"Associations of diabetes and prediabetes with mortality and life expectancy in China: a national study","volume":"47","author":"Tian","year":"2024","journal-title":"Diabetes Care"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1186\/s12933-023-02103-z","article-title":"Nonlinear relationship between untraditional lipid parameters and the risk of prediabetes: a large retrospective study based on Chinese adults","volume":"23","author":"Li","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artmed.2017.06.011","article-title":"Artificial intelligence in medicine AIME 2015","volume":"81","author":"Holmes","year":"2017","journal-title":"Artif Intell Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine, 2023","volume":"388","author":"Haug","year":"2023","journal-title":"N Engl J Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/6873891","article-title":"Identification of potential type II diabetes in a large-scale Chinese population using a systematic machine learning framework","volume":"2020","author":"Xue","year":"2020","journal-title":"J Diabetes Res"},{"key":"B11","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/1302811","article-title":"Methods to analyze time-to-event data: the Cox regression analysis","volume":"2021","author":"Abd ElHafeez","year":"2021","journal-title":"Oxid Med Cell Longev"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2018-021768","article-title":"Association of body mass index and age with incident diabetes in Chinese adults: a population-based cohort study","volume":"8","author":"Chen","year":"2018","journal-title":"BMJ Open"},{"key":"B14","doi-asserted-by":"publisher","first-page":"20410","DOI":"10.1038\/s41598-020-77220-w","article-title":"A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction","volume":"10","author":"Spooner","year":"2020","journal-title":"Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygeno.2012.04.003","article-title":"Random forests for genomic data analysis","volume":"99","author":"Chen","year":"2012","journal-title":"Genomics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"20881","DOI":"10.1038\/s41598-025-05876-3","article-title":"Survival analysis for sepsis patients: a machine learning approach to feature selection and predictive modeling","volume":"15","author":"Cai","year":"2025","journal-title":"Sci Rep"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6526","article-title":"A naive Bayes machine learning approach to risk prediction using censored, time-to-event data","volume":"34","author":"Wolfson","year":"2015","journal-title":"Stat Med"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2299291","article-title":"Cost-sensitive AdaBoost algorithm for ordinal regression based on extreme learning machine","volume":"44","author":"Riccardi","year":"2014","journal-title":"IEEE Trans Cybern"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.2196\/47652","article-title":"Privacy-preserving federated survival support vector machines for cross-institutional time-to-event analysis: algorithm development and validation","volume":"3","author":"Sp\u00e4th","year":"2024","journal-title":"JMIR AI"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.landig.2025.100916","article-title":"Evaluation of performance measures in predictive artificial intelligence models to support medical decisions: overview and guidance","volume":"7","author":"Van Calster","year":"2025","journal-title":"Lancet Digit Health"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105607","article-title":"Survival analysis for lung cancer patients: a comparison of Cox regression and machine learning models","volume":"191","author":"Germer","year":"2024","journal-title":"Int J Med Inform"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1177\/09622802241287707","article-title":"Graphical methods to illustrate the nature of the relation between a continuous variable and the outcome when using restricted cubic splines with a Cox proportional hazards model","volume":"34","author":"Austin","year":"2025","journal-title":"Stat Methods Med Res"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1177\/09622802241242325","article-title":"Methods for non-proportional hazards in clinical trials: a systematic review","volume":"33","author":"Bardo","year":"2024","journal-title":"Stat Methods Med Res"},{"key":"B24","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1186\/s12874-025-02608-z","article-title":"Restricted mean survival time approach versus time-varying coefficient Cox model for quantifying treatment effect when hazards are non-proportional","volume":"25","author":"Gu","year":"2025","journal-title":"BMC Med Res Methodol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078276","article-title":"Developing clinical prediction models: a step-by-step guide","volume":"386","author":"Efthimiou","year":"2024","journal-title":"BMJ"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-074819","article-title":"Evaluation of clinical prediction models (part 1): from development to external validation","volume":"384","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/sim.9717","article-title":"Pitfalls of the concordance index for survival outcomes","volume":"42","author":"Hartman","year":"2023","journal-title":"Stat Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1002\/bimj.202200302","article-title":"Stability of clinical prediction models developed using statistical or machine learning methods","volume":"65","author":"Riley","year":"2023","journal-title":"Biom J"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1177\/09622802231165001","article-title":"Imputation and missing indicators for handling missing data in the development and deployment of clinical prediction models: a simulation study","volume":"32","author":"Sisk","year":"2023","journal-title":"Stat Methods Med Res"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/sim.9666","article-title":"Two-phase designs with current status data","volume":"42","author":"Mao","year":"2023","journal-title":"Stat Med"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1080\/13685538.2023.2205510","article-title":"LASSO-based machine learning algorithm to predict the incidence of diabetes in different stages","volume":"26","author":"Ou","year":"2023","journal-title":"Aging Male"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad723","article-title":"survex: an R package for explaining machine learning survival models","volume":"39","author":"Spytek","year":"2023","journal-title":"Bioinformatics"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce-Bobadilla","year":"2024","journal-title":"Clin Transl Sci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"S238","DOI":"10.2337\/dc25-S010","article-title":"Cardiovascular disease and risk management: Standards of care in diabetes-2025","volume":"48","year":"2025","journal-title":"Diabetes Care"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/S2468-2667(24)00250-0","article-title":"Diabetes in China part 1: epidemiology and risk factors","volume":"9","author":"Xu","year":"2024","journal-title":"Lancet Public Health"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m2297","article-title":"Association between prediabetes and risk of all cause mortality and cardiovascular disease: updated meta-analysis","volume":"370","author":"Cai","year":"2020","journal-title":"BMJ"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.2337\/dci24-0029","article-title":"Pathophysiology and treatment of prediabetes and type 2 diabetes in youth","volume":"47","author":"Bacha","year":"2024","journal-title":"Diabetes Care"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.metabol.2021.154766","article-title":"Insulin resistance, cardiovascular stiffening and cardiovascular disease","volume":"119","author":"Hill","year":"2021","journal-title":"Metabolism"},{"key":"B39","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1186\/s12933-022-01729-9","article-title":"Insulin resistance mediates obesity-related risk of cardiovascular disease: a prospective cohort study","volume":"21","author":"Tian","year":"2022","journal-title":"Cardiovasc Diabetol"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1111\/jdi.13783","article-title":"Association of body mass index with risk of prediabetes in Chinese adults: a population-based cohort study","volume":"13","author":"Chai","year":"2022","journal-title":"J Diabetes Investig"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1172\/JCI43378","article-title":"Lipid-induced insulin resistance mediated by the proinflammatory receptor TLR4 requires saturated fatty acid-induced ceramide biosynthesis in mice","volume":"121","author":"Holland","year":"2011","journal-title":"J Clin Invest"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.2174\/1573402118666220321121421","article-title":"Impaired fasting glucose prevalence among hypolipidemic treatment-na\u00efve patients with hypertension","volume":"18","author":"Papadakis","year":"2022","journal-title":"Curr Hypertens Rev"},{"key":"B43","doi-asserted-by":"publisher","first-page":"17948","DOI":"10.1038\/s41598-024-68813-w","article-title":"Examination of nonlinear associations between pulse pressure index and incident prediabetes susceptibility: a 5-year retrospective cohort investigation","volume":"14","author":"Pan","year":"2024","journal-title":"Sci Rep"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1097\/MAJ.0b013e31824c7a12","article-title":"The impact of a family history of type 2 diabetes on insulin secretion and insulin sensitivity in individuals with varying glucose tolerance","volume":"345","author":"Li","year":"2013","journal-title":"Am J Med Sci"},{"key":"B45","doi-asserted-by":"publisher","first-page":"6968","DOI":"10.1038\/s41598-021-86327-7","article-title":"Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival","volume":"11","author":"Moncada-Torres","year":"2021","journal-title":"Sci Rep"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105218","article-title":"Use of wearables for monitoring cardiometabolic health: a systematic review","volume":"179","author":"Lee","year":"2023","journal-title":"Int J Med Inform"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1862258\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T04:38:31Z","timestamp":1790224711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1862258\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":46,"alternative-id":["10.3389\/fendo.2026.1862258"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1862258","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]},"article-number":"1862258"}}