{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:49:32Z","timestamp":1782103772394,"version":"3.54.5"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"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>Background<\/jats:title>\n                    <jats:p>T2DM readmission risk factors may evolve across time windows, but this dynamic remains poorly understood.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort study developed nine machine learning models to predict 30-day, 60-day, and 365-day readmission in 12,041 T2DM patients (with an additional 2,007 patients used for temporal validation of the 30-day and 60-day models). Feature selection was performed using LASSO and Boruta. SHAP analysis was used for interpretability, with temporal validation performed for short- and medium-term models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ANN achieved the highest AUROC for 30-day and 60-day predictions. Random forest showed competitive performance for 365-day prediction. SHAP analysis revealed a dynamic evolution: age dominated the 30-day window; length of hospital stay and inflammatory markers (SII, SIRI) emerged as key predictors in the 60-day window; and diabetes-specific chronic complications dominated the 365-day window.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Model selection should be time window-specific: ANN for short\/medium-term, random forest for long-term prediction. Risk factors shift from acute vulnerability to inflammatory burden and then to chronic complications, supporting dynamic risk monitoring in T2DM patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1827506","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:36:05Z","timestamp":1782102965000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic evolution of readmission risk factors across short-, medium-, and long-term horizons in type 2 diabetes: a machine learning-based predictive modeling study with SHAP interpretability"],"prefix":"10.3389","volume":"17","author":[{"given":"Lei","family":"Li","sequence":"first","affiliation":[{"name":"Department of Endocrinology, The First Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Endocrinology, The First Affiliated Hospital of Xinjiang Medical University","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.2337\/dci23-0085","article-title":"Economic costs of diabetes in the U.S. in 2022","volume":"47","author":"Parker","year":"2024","journal-title":"Diabetes Care"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.metabol.2024.155999","article-title":"Global burden of metabolic diseases, 1990-2021","volume":"160","author":"Zhang","year":"2024","journal-title":"Metabolism"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-025-06556-7","article-title":"Prevalence of youth type 2 diabetes in global Indigenous populations: a systematic review","volume":"69","author":"Papadimos","year":"2026","journal-title":"Diabetologia"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(23)01301-6","article-title":"Global, regional, and national burden of diabetes from 1990 to 2021, with projections of prevalence to 2050: a systematic analysis for the Global Burden of Disease Study 2021","volume":"402","year":"2023","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/s0140-6736(24)02317-1","article-title":"Worldwide trends in diabetes prevalence and treatment from 1990 to 2022: a pooled analysis of 1108 population-representative studies with 141 million participants","volume":"404","year":"2024","journal-title":"Lancet"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1501690","article-title":"Global burden of type 2 diabetes mellitus from 1990 to 2021, with projections of prevalence to 2044: a systematic analysis across SDI levels for the global burden of disease study 2021","volume":"15","author":"He","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s12325-015-0223-3","article-title":"Type 2 diabetes mellitus patients' healthcare costs related to inpatient hospitalizations: a retrospective administrative claims database study","volume":"32","author":"Saundankar","year":"2015","journal-title":"Adv Ther"},{"key":"B8","article-title":"Idf Diabetes Atlas","year":"2025"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eprac.2021.03.013","article-title":"Patient understanding of discharge instructions for home diabetes self-management and risk for hospital readmission and emergency department visits","volume":"27","author":"Pinkhasova","year":"2021","journal-title":"Endocrine Practice: Off J Am Coll Endocrinol Am Assoc Clin Endocrinologists"},{"key":"B10","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s12911-021-01423-y","article-title":"The 30-days hospital readmission risk in diabetic patients: predictive modeling with machine learning classifiers","volume":"21","author":"Shang","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"B11","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s11892-015-0584-7","article-title":"Hospital readmission of patients with diabetes","volume":"15","author":"Rubin","year":"2015","journal-title":"Curr Diabetes Rep"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2020.108363","article-title":"The effectiveness of in-hospital interventions on reducing hospital length of stay and readmission of patients with type 2 diabetes mellitus: a systematic review","volume":"174","author":"Chakraborty","year":"2021","journal-title":"Diabetes Res Clin Pract"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-012-2229-8","article-title":"Hospital performance measures and 30-day readmission rates","volume":"28","author":"Stefan","year":"2013","journal-title":"J Gen Intern Med"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1186\/s13098-023-01212-9","article-title":"Hypoglycemia in patients with type 2 diabetes mellitus during hospitalization: associated factors and prognostic value","volume":"15","author":"Gonz\u00e1lez-Vidal","year":"2023","journal-title":"Diabetol Metab Syndr"},{"key":"B15","doi-asserted-by":"publisher","first-page":"742","DOI":"10.3390\/jcm13030742","article-title":"Prognostic implications of type 2 diabetes mellitus in heart failure with mildly reduced ejection fraction","volume":"13","author":"Schupp","year":"2024","journal-title":"J Clin Med"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2019.3806","article-title":"Patient perceptions of diabetes guideline frameworks for individualizing glycemic targets","volume":"179","author":"Schoenborn","year":"2019","journal-title":"JAMA Intern Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1186\/s12902-023-01515-y","article-title":"Glycemic control and associated factors among type 2 diabetes mellitus patients: a cross-sectional study of Azar cohort population","volume":"23","author":"Dinavari","year":"2023","journal-title":"BMC Endocr Disord"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2016-011060","article-title":"Utility of models to predict 28-day or 30-day unplanned hospital readmissions: an updated systematic review","volume":"6","author":"Zhou","year":"2016","journal-title":"BMJ Open"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/tcbb.2021.3089682","article-title":"Predictive modeling of hospital readmission: challenges and solutions","volume":"19","author":"Wang","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201901989","article-title":"Integrating artificial intelligence and nanotechnology for precision cancer medicine","volume":"32","author":"Adir","year":"2020","journal-title":"Adv Mater"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1185\/03007995.2014.981632","article-title":"Predictors of 30 day hospital readmission in patients with type 2 diabetes: a retrospective, case-control, database study","volume":"31","author":"Eby","year":"2015","journal-title":"Curr Med Res Opin"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1080\/03007995.2017.1330258","article-title":"Predictors of all-cause 30\u2009day readmission among Medicare patients with type 2 diabetes","volume":"33","author":"Collins","year":"2017","journal-title":"Curr Med Res Opin"},{"key":"B23","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1186\/s12859-023-05465-z","article-title":"Prediction of diabetes disease using an ensemble of machine learning multi-classifier models","volume":"24","author":"Abnoosian","year":"2023","journal-title":"BMC Bioinf"},{"key":"B24","doi-asserted-by":"publisher","first-page":"14240","DOI":"10.1038\/s41598-019-50751-7","article-title":"High glucose variability increases 30-day readmission rates in patients with type 2 diabetes hospitalized in department of surgery","volume":"9","author":"Hsieh","year":"2019","journal-title":"Sci Rep"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1155\/jdr\/3148242","article-title":"Derivation and validation of prediction models for prolonged length of stay and 30-day readmission in elderly patients with type 2 diabetes mellitus: a multicenter study","volume":"2025","author":"Tan","year":"2025","journal-title":"J Diabetes Res"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1534516","article-title":"Development and validation of a risk prediction model for 30-day readmission in elderly type 2 diabetes patients complicated with heart failure: a multicenter, retrospective study","volume":"16","author":"He","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.2147\/ppa.S544443","article-title":"Medication adherence interventions among people living with diabetes: a systematic review","volume":"19","author":"Wang","year":"2025","journal-title":"Patient Prefer Adherence"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0347672","article-title":"A hybrid BiLSTM and rule-based system for integrated diabetes prediction and personalized guidance","volume":"21","author":"Saleem","year":"2026","journal-title":"PloS One"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0121569","article-title":"Applying a novel combination of techniques to develop a predictive model for diabetes complications","volume":"10","author":"Sangi","year":"2015","journal-title":"PloS One"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.1c00160","article-title":"GHOST: Adjusting the decision threshold to handle imbalanced data in machine learning","volume":"61","author":"Esposito","year":"2021","journal-title":"J Chem Inf Model"},{"key":"B31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.2174\/0115733998279869231227091944","article-title":"Hyperglycemic memory\": Observational evidence to experimental inference","volume":"21","author":"Ahmadi","year":"2025","journal-title":"Curr Diabetes Rev"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/8458472","article-title":"Perturbed biochemical pathways and associated oxidative stress lead to vascular dysfunctions in diabetic retinopathy","volume":"2019","author":"Mahajan","year":"2019","journal-title":"Oxid Med Cell Longevity"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1007\/s00592-014-0701-0","article-title":"Regularity of follow-up, glycemic burden, and risk of microvascular complications in patients with type 2 diabetes: a 9-year follow-up study","volume":"52","author":"Anjana","year":"2015","journal-title":"Acta Diabetol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2025.1673159","article-title":"Machine learning-based prediction model for 30-day readmission risk in elderly patients with type 2 diabetes mellitus and heart failure: a retrospective cohort study with SHAP interpretability analysis","volume":"12","author":"Wang","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.26.5.1421","article-title":"Multiple hospitalizations for patients with diabetes","volume":"26","author":"Jiang","year":"2003","journal-title":"Diabetes Care"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdiacomp.2014.02.009","article-title":"Frequency and causes of hospitalization in older compared to younger adults with type 2 diabetes in the United States: a retrospective, claims-based analysis","volume":"28","author":"Fu","year":"2014","journal-title":"J Diabetes Complications"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1089\/pop.2014.0116","article-title":"30-day readmission among elderly Medicare beneficiaries with type 2 diabetes","volume":"18","author":"Raval","year":"2015","journal-title":"Popul Health Manag"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2024-004167","article-title":"Predictors of readmission and mortality in adults with diabetes or stress hyperglycemia after initial hospitalization for COVID-19","volume":"12","author":"Chaugule","year":"2024","journal-title":"BMJ Open Diabetes Res Care"},{"key":"B39","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1186\/s12872-025-05168-8","article-title":"Systemic inflammatory response index and in-hospital mortality in diabetic heart failure patients: evidence from MIMIC-IV","volume":"25","author":"Zhang","year":"2025","journal-title":"BMC Cardiovasc Disord"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14093155","article-title":"Modifiable and non-modifiable risk factors and vascular damage progression in type 2 diabetes: a primary care analysis","volume":"14","author":"Fabris","year":"2025","journal-title":"JCM"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1827506\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T04:36:12Z","timestamp":1782102972000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1827506\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":40,"alternative-id":["10.3389\/fendo.2026.1827506"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1827506","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]},"article-number":"1827506"}}