{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:03:10Z","timestamp":1787022190085,"version":"build-2736575974"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Bio and Medical Technology Development Program of the National Research Foundation (NRF) funded by the Korean government","award":["RS-2023-00262002"],"award-info":[{"award-number":["RS-2023-00262002"]}]},{"name":"National Institute of Health","award":["2022-ER1102-02"],"award-info":[{"award-number":["2022-ER1102-02"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Patients with type 2 diabetes mellitus (T2DM) prone to acute diabetic complications are at high risk for emergency department (ED) visits, which often precede hospitalization and mortality. Identifying these high-risk phenotypes before deterioration is critical for preventative care. We developed machine learning (ML) models using large-scale, real-world electronic medical records, including prescription data, to predict the possibility of ED visits in patients with T2DM and support proactive interventions in primary care settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We analyzed the electronic health record data of five independent institutions, creating a comprehensive dataset of 220,720 patients. The data included dynamic clinical parameters such as vital signs, laboratory results, and prescription histories. The cohort was randomly split into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009176,576) and a test set (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200944,144). The primary outcome was the first ED visit. We developed multiple ML models using an automated ML framework and optimized them using hyperparameter tuning of the training set. Model performances were evaluated using the area under the receiver operating characteristic (AUROC) curve, and feature importance was analyzed using SHAP values to ensure interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the screened population, 49,770 (22.6%) experienced at least one ED visit, distributed proportionally across the training and test datasets. The CatBoost model demonstrated superior predictive performance, achieving an AUROC of 0.87 (95% CI, 0.862\u20130.871) on the test dataset. The model identified modifiable risk factors as key predictors; Diastolic blood pressure was the most significant variable, followed by serum creatinine and systolic blood pressure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This ML-based predictive model can accurately identify high-risk patients with T2DM who are likely to visit the ED based on readily available clinical variables. By enabling healthcare providers to shift from reactive treatment to proactive risk management, it has the potential to reduce the burden of ED visits due to acute complications in T2DM.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0352342","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:25:48Z","timestamp":1783617948000},"page":"e0352342","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Machine learning for predicting emergency department visits in patients with type 2 diabetes: A real-world, multi-institutional study"],"prefix":"10.1371","volume":"21","author":[{"given":"Sunyoung","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunji","family":"Sang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2009-386X","authenticated-orcid":true,"given":"Jaeyu","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Selin","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun-Hee","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong Hwa","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dae Jung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9305-4686","authenticated-orcid":true,"given":"Chang-Won","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae Sun","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You-Cheol","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunjung","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zio","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyejin","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Keon","family":"Yon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0119-5818","authenticated-orcid":true,"given":"Sang Youl","family":"Rhee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"issue":"10467","key":"pone.0352342.ref001","doi-asserted-by":"crossref","first-page":"2077","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","author":"NCD Risk Factor Collaboration (NCD-RisC)","year":"2024","journal-title":"Lancet"},{"issue":"1","key":"pone.0352342.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40138-012-0007-x","article-title":"Diabetes in the emergency department and hospital: acute care of diabetes patients","volume":"1","author":"W Ford","year":"2013","journal-title":"Curr Emerg Hosp Med Rep"},{"issue":"2","key":"pone.0352342.ref003","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0317653","article-title":"Magnitude, risk factors and economic impacts of diabetic emergencies in developing countries: a systematic review","volume":"20","author":"HK Haile","year":"2025","journal-title":"PLoS One"},{"issue":"5","key":"pone.0352342.ref004","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.2337\/dc19-2449","article-title":"Trends in emergency department visits and inpatient admissions for hyperglycemic crises in adults with diabetes in the U.S., 2006-2015","volume":"43","author":"SR Benoit","year":"2020","journal-title":"Diabetes Care"},{"issue":"3","key":"pone.0352342.ref005","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.mcna.2016.12.011","article-title":"Management of hyperglycemic crises: diabetic ketoacidosis and hyperglycemic hyperosmolar state","volume":"101","author":"M Fayfman","year":"2017","journal-title":"Med Clin North Am"},{"key":"pone.0352342.ref006","doi-asserted-by":"crossref","DOI":"10.15620\/cdc:134505","volume-title":"Emergency department visit rates by adults with diabetes: United States, 2020\u20132021","author":"L Santo","year":"2023"},{"issue":"5","key":"pone.0352342.ref007","doi-asserted-by":"crossref","first-page":"917","DOI":"10.2337\/dci18-0007","article-title":"Economic costs of diabetes in the U.S. in 2017","volume":"41","author":"American Diabetes Association","year":"2018","journal-title":"Diabetes Care"},{"key":"pone.0352342.ref008","author":"LN McEwen","year":"2021","journal-title":"Health care utilization and costs of diabetes"},{"issue":"4","key":"pone.0352342.ref009","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1097\/MLR.0000000000001501","article-title":"Reducing emergency department visits among patients with diabetes by embedding clinical pharmacists in the primary care teams","volume":"59","author":"G Moreno","year":"2021","journal-title":"Med Care"},{"issue":"20","key":"pone.0352342.ref010","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"RC Deo","year":"2015","journal-title":"Circulation"},{"issue":"1","key":"pone.0352342.ref011","doi-asserted-by":"crossref","first-page":"37","DOI":"10.3390\/info15010037","article-title":"Parametric and nonparametric machine learning techniques for increasing power system reliability: a review","volume":"15","author":"F Imam","year":"2024","journal-title":"Information"},{"issue":"4","key":"pone.0352342.ref012","doi-asserted-by":"crossref","first-page":"291","DOI":"10.2174\/1389202922666210705124359","article-title":"Machine learning in healthcare","volume":"22","author":"H Habehh","year":"2021","journal-title":"Curr Genomics"},{"key":"pone.0352342.ref013","doi-asserted-by":"crossref","DOI":"10.1109\/ICAECT54875.2022.9808019","volume-title":"Descriptive and predictive analytics on electronic health records using machine learning","author":"V Anandi","year":"2022"},{"issue":"5","key":"pone.0352342.ref014","first-page":"1889","article-title":"Ethnic and sex differences in the distributions of body mass index and waist circumference among adults: a binationally representative study in South Korea and the United States","volume":"27","author":"S Eum","year":"2023","journal-title":"Eur Rev Med Pharmacol Sci"},{"key":"pone.0352342.ref015","doi-asserted-by":"crossref","first-page":"102691","DOI":"10.1016\/j.jmp.2022.102691","article-title":"Hold-out strategy for selecting learning models: application to categorization subjected to presentation orders","volume":"109","author":"G Mezzadri","year":"2022","journal-title":"J Math Psychol"},{"issue":"1","key":"pone.0352342.ref016","first-page":"43","article-title":"AutoML: examining existing software implementations and determining the overall internal structure of solutions","volume":"73","author":"IA Popova","year":"2023","journal-title":"Proc Inst Syst Anal Russ Acad Sci"},{"key":"pone.0352342.ref017","article-title":"Machine learning-based prediction of suicidal thinking in adolescents by derivation and validation in 3 independent worldwide cohorts: algorithm development and validation study","volume":"26","author":"H Kim","year":"2024","journal-title":"J Med Internet Res"},{"key":"pone.0352342.ref018","article-title":"Machine learning-based prediction of suicidality in adolescents with allergic rhinitis: derivation and validation in 2 independent nationwide cohorts","volume":"26","author":"H Lee","year":"2024","journal-title":"J Med Internet Res"},{"key":"pone.0352342.ref019","unstructured":"Mota B, editor. Automated machine learning and explainable. Distributed Computing and Artificial Intelligence, 21st International Conference. Springer Nature; 2025."},{"key":"pone.0352342.ref020","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, Koyama M, editors. Optuna: a next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2019.","DOI":"10.1145\/3292500.3330701"},{"issue":"3","key":"pone.0352342.ref021","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1002\/bimj.200710415","article-title":"Youden Index and optimal cut-point estimated from observations affected by a lower limit of detection","volume":"50","author":"MD Ruopp","year":"2008","journal-title":"Biom J"},{"issue":"5","key":"pone.0352342.ref022","doi-asserted-by":"crossref","DOI":"10.1111\/obr.13714","article-title":"Efficacy of information and communication technology interventions for the management of diabetes mellitus: an umbrella review and evidence map","volume":"25","author":"S Park","year":"2024","journal-title":"Obes Rev"},{"issue":"3","key":"pone.0352342.ref023","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics"},{"issue":"1","key":"pone.0352342.ref024","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1097\/EDE.0b013e3181c30fb2","article-title":"Assessing the performance of prediction models: a framework for traditional and novel measures","volume":"21","author":"EW Steyerberg","year":"2010","journal-title":"Epidemiology"},{"issue":"1","key":"pone.0352342.ref025","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative","year":"2019","journal-title":"BMC Med"},{"issue":"8","key":"pone.0352342.ref026","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1016\/j.jclinepi.2009.11.009","article-title":"Use of Brier score to assess binary predictions","volume":"63","author":"K Rufibach","year":"2010","journal-title":"J Clin Epidemiol"},{"issue":"6","key":"pone.0352342.ref027","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"AJ Vickers","year":"2006","journal-title":"Med Decis Making"},{"issue":"6","key":"pone.0352342.ref028","doi-asserted-by":"crossref","first-page":"3317","DOI":"10.3390\/ijerph18063317","article-title":"Prediction of type 2 diabetes based on machine learning algorithm","volume":"18","author":"HM Deberneh","year":"2021","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"pone.0352342.ref029","doi-asserted-by":"crossref","DOI":"10.1186\/s41231-021-00096-z","article-title":"Predictive model and feature importance for early detection of type II diabetes mellitus","volume":"6","author":"E Adua","year":"2021","journal-title":"Transl Med Commun"},{"issue":"1","key":"pone.0352342.ref030","doi-asserted-by":"crossref","first-page":"3688","DOI":"10.1186\/s12889-025-24953-w","article-title":"Leveraging XGBoost and explainable AI for accurate prediction of type 2 diabetes","volume":"25","author":"Z Rafie","year":"2025","journal-title":"BMC Public Health"},{"issue":"1","key":"pone.0352342.ref031","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s12911-025-03333-9","article-title":"Explainable extratreeclassifier model for early detection of type 2 diabetes: evidence from the PERSIAN Dena Cohort","volume":"26","author":"M Ghaderzadeh","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"issue":"3","key":"pone.0352342.ref032","first-page":"121","article-title":"Filter-based feature selection for type II diabetes prediction","volume":"6","author":"M Ghaderzadeh","year":"2025","journal-title":"J Clin Care Skills"},{"issue":"13","key":"pone.0352342.ref033","doi-asserted-by":"crossref","first-page":"5925","DOI":"10.3390\/app14135925","article-title":"integrating shapley values into machine learning techniques for enhanced predictions of hospital admissions","volume":"14","author":"G Feretzakis","year":"2024","journal-title":"Appl Sci"},{"issue":"10","key":"pone.0352342.ref034","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1001\/jamainternmed.2017.3844","article-title":"Development and validation of a tool to identify patients with type 2 diabetes at high risk of hypoglycemia-related emergency department or hospital use","volume":"177","author":"AJ Karter","year":"2017","journal-title":"JAMA Intern Med"},{"key":"pone.0352342.ref035","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1186\/1472-6963-10-338","article-title":"Use of an electronic administrative database to identify older community dwelling adults at high-risk for hospitalization or emergency department visits: the elders risk assessment index","volume":"10","author":"SJ Crane","year":"2010","journal-title":"BMC Health Serv Res"},{"issue":"13","key":"pone.0352342.ref036","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1001\/archinte.168.13.1416","article-title":"Development and validation of a model for predicting emergency admissions over the next year (PEONY): a UK historical cohort study","volume":"168","author":"PT Donnan","year":"2008","journal-title":"Arch Intern Med"},{"issue":"8","key":"pone.0352342.ref037","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2013-003482","article-title":"Predicting risk of emergency admission to hospital using primary care data: derivation and validation of QAdmissions score","volume":"3","author":"J Hippisley-Cox","year":"2013","journal-title":"BMJ Open"},{"issue":"1","key":"pone.0352342.ref038","doi-asserted-by":"crossref","first-page":"38","DOI":"10.3803\/EnM.2016.31.1.38","article-title":"How to establish clinical prediction models","volume":"31","author":"YH Lee","year":"2016","journal-title":"Endocrinol Metab (Seoul)"},{"key":"pone.0352342.ref039","doi-asserted-by":"crossref","DOI":"10.2196\/50437","article-title":"Considerations for quality control monitoring of machine learning models in clinical practice","volume":"12","author":"L Faust","year":"2024","journal-title":"JMIR Med Inform"},{"issue":"1","key":"pone.0352342.ref040","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.ekir.2023.10.019","article-title":"Clinical decision support tools in the electronic medical record","volume":"9","author":"M Alexiuk","year":"2023","journal-title":"Kidney Int Rep"},{"key":"pone.0352342.ref041","doi-asserted-by":"crossref","DOI":"10.2196\/44065","article-title":"Integrating clinical decision support into electronic health record systems using a novel platform (EvidencePoint): developmental study","volume":"7","author":"J Solomon","year":"2023","journal-title":"JMIR Form Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:25:55Z","timestamp":1783617955000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0352342"}},"subtitle":[],"editor":[{"given":"Marwan Salih","family":"Al-Nimer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":41,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0352342","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]}}}