{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T18:49:03Z","timestamp":1791830943649,"version":"4.3.4"},"reference-count":63,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Early diagnosis of diabetes is essential for early interventions to slow the progression of dysglycemia and its comorbidities. However, among individuals with diabetes, about 23% were unaware of their condition.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to investigate the potential use of automated machine learning (AutoML) models and self-reported data in detecting undiagnosed diabetes among US adults.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Individual-level data, including biochemical tests for diabetes, demographic characteristics, family history of diabetes, anthropometric measures, dietary intakes, health behaviors, and chronic conditions, were retrieved from the National Health and Nutrition Examination Survey, 1999\u20102020. Undiagnosed diabetes was defined as having no prior self-reported diagnosis but meeting diagnostic criteria for elevated hemoglobin A\n 1c<\/jats:sub>\n , fasting plasma glucose, or 2-hour plasma glucose. The H2O AutoML framework, which allows for automated hyperparameter tuning, model selection, and ensemble learning, was used to automate the machine learning workflow. For comparative analysis, 4 traditional machine learning models\u2014logistic regression, support vector machines, random forest, and extreme gradient boosting\u2014were implemented. Model performance was evaluated using the area under the receiver operating characteristic curve.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The study included 11,815 participants aged 20 years and older, comprising 2256 patients with undiagnosed diabetes and 9559 without diabetes. The average age was 59.76 (SD 15.0) years for participants with undiagnosed diabetes and 46.78 (SD 17.2) years for those without diabetes. The AutoML model demonstrated superior performance compared with the 4 traditional machine learning models. The trained AutoML model achieved an area under the receiver operating characteristic curve of 0.909 (95% CI 0.897-0.921) in the test set. The model demonstrated a sensitivity of 70.26%, specificity of 90.46%, positive predictive value of 64.10%, and negative predictive value of 92.61% for identifying undiagnosed diabetes from nondiabetes.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n To our knowledge, this study is the first to utilize the AutoML model for detecting undiagnosed diabetes in US adults. The model\u2019s strong performance and applicability to the broader US population make it a promising tool for large-scale diabetes screening efforts.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/68260","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T23:00:08Z","timestamp":1753225208000},"page":"e68260-e68260","source":"Crossref","is-referenced-by-count":4,"title":["Use of Automated Machine Learning to Detect Undiagnosed Diabetes in US Adults: Development and Validation Study"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8364-3698","authenticated-orcid":false,"given":"Jianxiu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4849-5650","authenticated-orcid":false,"given":"Fred","family":"Ssewamala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9632-0209","authenticated-orcid":false,"given":"Ruopeng","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1205-0369","authenticated-orcid":false,"given":"Mengmeng","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"issue":"18","key":"R1","doi-asserted-by":"publisher","first-page":"1829","DOI":"10.1001\/jama.2021.5469","article-title":"The leading causes of death in the US for 2020","volume":"325","author":"Ahmad","journal-title":"JAMA"},{"key":"R2","unstructured":"Statistics about diabetes. American Diabetes Association. URL: https:\/\/diabetes.org\/about-diabetes\/statistics\/about-diabetes [Accessed 27-01-2025]"},{"key":"R3","unstructured":"Diabetes statistics. National Institute of Diabetes and Digestive and Kidney Diseases. URL: https:\/\/www.niddk.nih.gov\/health-information\/health-statistics\/diabetes-statistics [Accessed 27-01-2025]"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.diabres.2013.11.001","article-title":"Global estimates of undiagnosed diabetes in adults","volume":"103","author":"Beagley","journal-title":"Diabetes Res Clin Pract"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"116","DOI":"10.2337\/diaclin.29.3.116","article-title":"Microvascular and macrovascular complications of diabetes","volume":"29","author":"Fowler","journal-title":"Clin Diabetes"},{"issue":"11","key":"R6","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.2522\/ptj.20080020","article-title":"Epidemiology of diabetes and diabetes-related complications","volume":"88","author":"Deshpande","journal-title":"Phys Ther"},{"issue":"7","key":"R7","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.41409","article-title":"Self-care practices and their role in the control of diabetes: a narrative review","volume":"15","author":"Ahmad","journal-title":"Cureus"},{"issue":"5","key":"R8","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.3160","article-title":"Reach and use of diabetes prevention services in the United States, 2016-2017","volume":"2","author":"Ali","journal-title":"JAMA Netw Open"},{"issue":"10","key":"R9","doi-asserted-by":"publisher","first-page":"681","DOI":"10.7326\/M14-0019","article-title":"A cascade of care for diabetes in the United States: visualizing the gaps","volume":"161","author":"Ali","journal-title":"Ann Intern Med"},{"issue":"9702","key":"R10","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1016\/S0140-6736(09)61457-4","article-title":"10-year follow-up of diabetes incidence and weight loss in the Diabetes Prevention Program Outcomes Study","volume":"374","author":"Diabetes Prevention Program Research Group","journal-title":"Lancet"},{"issue":"8","key":"R11","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1001\/jama.2021.12531","article-title":"Screening for prediabetes and type 2 diabetes: US Preventive Services Task Force recommendation statement","volume":"326","author":"US Preventive Services Task Force","journal-title":"JAMA"},{"issue":"Supplement_1","key":"R12","doi-asserted-by":"publisher","first-page":"S17","DOI":"10.2337\/dc22-S002","article-title":"Classification and diagnosis of diabetes: standards of medical care in diabetes\u20142022","volume":"45","author":"American Diabetes Association Professional Practice Committee","journal-title":"Diabetes Care"},{"issue":"4","key":"R13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0125249","article-title":"Receipt of glucose testing and performance of two US diabetes screening guidelines, 2007-2012","volume":"10","author":"Bullard","journal-title":"PLoS ONE"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2023.110572","article-title":"Impact of changes in diabetes screening guidelines on testing eligibility and potential yield among adults without diagnosed diabetes in the United States","volume":"197","author":"Ali","journal-title":"Diabetes Res Clin Pract"},{"issue":"5","key":"R15","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.2337\/diacare.28.5.1187","article-title":"Use of the diabetes risk score for opportunistic screening of undiagnosed diabetes and impaired glucose tolerance: the IGLOO (Impaired Glucose Tolerance and Long-Term Outcomes Observational) study","volume":"28","author":"Franciosi","journal-title":"Diabetes Care"},{"issue":"8","key":"R16","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.2337\/dc11-2347","article-title":"A simple screening score for diabetes for the Korean population: development, validation, and comparison with other scores","volume":"35","author":"Lee","journal-title":"Diabetes Care"},{"issue":"11","key":"R17","doi-asserted-by":"publisher","first-page":"775","DOI":"10.7326\/0003-4819-151-11-200912010-00005","article-title":"Development and validation of a patient self-assessment score for diabetes risk","volume":"151","author":"Bang","journal-title":"Ann Intern Med"},{"issue":"3","key":"R18","doi-asserted-by":"publisher","first-page":"382","DOI":"10.2337\/diacare.18.3.382","article-title":"A new and simple questionnaire to identify people at increased risk for undiagnosed diabetes","volume":"18","author":"Herman","journal-title":"Diabetes Care"},{"issue":"5","key":"R19","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.2337\/dc07-1150","article-title":"Diabetes risk calculator: a simple tool for detecting undiagnosed diabetes and pre-diabetes","volume":"31","author":"Heikes","journal-title":"Diabetes Care"},{"issue":"11","key":"R20","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.2337\/diacare.24.11.1899","article-title":"Performance of recommended screening tests for undiagnosed diabetes and dysglycemia","volume":"24","author":"Rolka","journal-title":"Diabetes Care"},{"issue":"3","key":"R21","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.diabres.2014.01.008","article-title":"How diabetes risk assessment tools are implemented in practice: a systematic review","volume":"104","author":"Dhippayom","journal-title":"Diabetes Res Clin Pract"},{"issue":"5","key":"R22","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-0940-7","article-title":"Accurate diabetes risk stratification using machine learning: role of missing value and outliers","volume":"42","author":"Maniruzzaman","journal-title":"J Med Syst"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2989857","article-title":"Diabetes prediction using ensembling of different machine learning classifiers","volume":"8","author":"Hasan","journal-title":"IEEE Access"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.05.122","article-title":"Prediction of diabetes using classification algorithms","volume":"132","author":"Sisodia","journal-title":"Procedia Comput Sci"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1590\/1516-3180.2016.0309010217","article-title":"Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study","volume":"135","author":"Olivera","journal-title":"Sao Paulo Med J"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"421","DOI":"10.3390\/app10010421","article-title":"A deep learning model for estimation of patients with undiagnosed diabetes","volume":"10","author":"Ryu","journal-title":"Appl Sci (Basel)"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-40170-0","article-title":"Comparisons of the prediction models for undiagnosed diabetes between machine learning versus traditional statistical methods","volume":"13","author":"Choi","journal-title":"Sci Rep"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2016.12.005","article-title":"Machine learning and data mining methods in diabetes research","volume":"15","author":"Kavakiotis","journal-title":"Comput Struct Biotechnol J"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-10-16","article-title":"Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes","volume":"10","author":"Yu","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/diabetology5010001","article-title":"A comparative analysis of machine learning models for the detection of undiagnosed diabetes patients","volume":"5","author":"Cichosz","journal-title":"Diabetology"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101822","article-title":"Automated machine learning: review of the state-of-the-art and opportunities for healthcare","volume":"104","author":"Waring","journal-title":"Artif Intell Med"},{"issue":"2","key":"R32","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae031","article-title":"Evaluating automated machine learning platforms for use in healthcare","volume":"7","author":"Scott","journal-title":"JAMIA Open"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s13721-016-0125-6","article-title":"A review of automatic selection methods for machine learning algorithms and hyper-parameter values","volume":"5","author":"Luo","journal-title":"Netw Model Anal Health Inform Bioinforma"},{"issue":"184","key":"R34","first-page":"1","author":"Chen","journal-title":"Vital Health Stat 2"},{"issue":"159","key":"R35","first-page":"1","volume":"2","author":"Mirel","journal-title":"Vital Health Stat 2"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.2196\/52508","article-title":"Consolidated Reporting Guidelines for Prognostic and Diagnostic Machine Learning Models (CREMLS)","volume":"26","author":"El Emam","journal-title":"J Med Internet Res"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.2196\/48763","article-title":"Consolidated reporting guidelines for prognostic and diagnostic machine learning modeling studies: development and validation","volume":"25","author":"Klement","journal-title":"J Med Internet Res"},{"issue":"Supplement_1","key":"R38","doi-asserted-by":"publisher","first-page":"S20","DOI":"10.2337\/dc24-S002","article-title":"Diagnosis and classification of diabetes: standards of care in diabetes\u20142024","volume":"47","author":"ElSayed","journal-title":"Diabetes Care"},{"key":"R39","unstructured":"NHANES 2005-2006 data documentation, codebook, and frequencies. Centers for Disease Control and Prevention. URL: https:\/\/wwwn.cdc.gov\/Nchs\/Nhanes\/2005-2006\/PAQIAF_D.htm [Accessed 27-01-2025]"},{"key":"R40","unstructured":"LeDell E Poirier S . H2O AutoML: scalable automatic machine learning. Presented at: 7th ICML Workshop on Automated Machine Learning. Jul 18, 2020.URL: https:\/\/www.automl.org\/wp-content\/uploads\/2020\/07\/AutoML_2020_paper_61.pdf [Accessed 27-01-2025]"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-Sampling Technique","volume":"16","author":"Chawla","journal-title":"J Artif Intell Res"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-14-106","article-title":"SMOTE for high-dimensional class-imbalanced data","volume":"14","author":"Blagus","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"R43","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.eprac.2023.02.001","article-title":"American Association of Clinical Endocrinology consensus statement: comprehensive type 2 diabetes management algorithm 2023 update","volume":"29","author":"Samson","journal-title":"Endocr Pract"},{"key":"R44","unstructured":"Code of federal regulations. US Department of Health and Human Services. URL: https:\/\/www.ecfr.gov\/current\/title-45\/subtitle-A\/subchapter-A\/part-46\/subpart-A\/section-46.104 [Accessed 30-9-2024]"},{"issue":"4","key":"R45","doi-asserted-by":"publisher","first-page":"673","DOI":"10.2215\/CJN.07891109","article-title":"Prevalence of chronic kidney disease in US adults with undiagnosed diabetes or prediabetes","volume":"5","author":"Plantinga","journal-title":"Clin J Am Soc Nephrol"},{"issue":"2","key":"R46","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.amepre.2013.02.026","article-title":"Utility of the U.S. Preventive Services Task Force criteria for diabetes screening","volume":"45","author":"Casagrande","journal-title":"Am J Prev Med"},{"issue":"1","key":"R47","first-page":"24","volume":"164","author":"Young","journal-title":"CMAJ"},{"issue":"12","key":"R48","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1016\/s0002-9149(00)01244-3","article-title":"Clinical impact of borderline and undiagnosed diabetes mellitus in patients with coronary artery disease","volume":"86","author":"Tenenbaum","journal-title":"Am J Cardiol"},{"issue":"8","key":"R49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1001\/jama.2021.9883","article-title":"Trends in prevalence of diabetes and control of risk factors in diabetes among US adults, 1999-2018","volume":"326","author":"Wang","journal-title":"JAMA"},{"key":"R50","doi-asserted-by":"publisher","DOI":"10.1007\/s44174-023-00063-2","article-title":"Drawbacks of artificial intelligence and their potential solutions in the healthcare sector","volume":"8 2023","author":"Khan","journal-title":"Biomed Mater Devices"},{"issue":"4","key":"R51","doi-asserted-by":"publisher","first-page":"291","DOI":"10.2174\/1389202922666210705124359","article-title":"Machine learning in healthcare","volume":"22","author":"Habehh","journal-title":"Curr Genomics"},{"issue":"1","key":"R52","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-022-00300-2","article-title":"Benchmarking AutoML frameworks for disease prediction using medical claims","volume":"15","author":"A Romero","journal-title":"BioData Min"},{"key":"R53","doi-asserted-by":"publisher","DOI":"10.1111\/ijlh.13537","article-title":"Machine learning in health care and laboratory medicine: general overview of supervised learning and Auto-ML","volume":"43 Suppl 1","author":"Rashidi","journal-title":"Int J Lab Hematol"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1259958","article-title":"AutoML accurately predicts endovascular mechanical thrombectomy in acute large vessel ischemic stroke","volume":"14","author":"Raj","journal-title":"Front Neurol"},{"issue":"1","key":"R55","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8","article-title":"MedMNIST v2\u2014a large-scale lightweight benchmark for 2D and 3D biomedical image classification","volume":"10","author":"Yang","journal-title":"Sci Data"},{"issue":"18","key":"R56","doi-asserted-by":"publisher","first-page":"13484","DOI":"10.3390\/su151813484","article-title":"The application of AutoML techniques in diabetes diagnosis: current approaches, performance, and future directions","volume":"15","author":"Zhuhadar","journal-title":"Sustainability"},{"key":"R57","doi-asserted-by":"publisher","DOI":"10.3233\/SHTI220779","article-title":"Customized and automated machine learning-based models for diabetes type 2 classification","volume":"295","author":"Mohsen","journal-title":"Stud Health Technol Inform"},{"key":"R58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3102399","article-title":"A comparative performance analysis of data resampling methods on imbalance medical data","volume":"9","author":"Khushi","journal-title":"IEEE Access"},{"key":"R59","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-publhealth-090419-102644","article-title":"Prediabetes and what it means: the epidemiological evidence","volume":"42","author":"Echouffo-Tcheugui","journal-title":"Annu Rev Public Health"},{"issue":"2","key":"R60","doi-asserted-by":"publisher","first-page":"241","DOI":"10.2337\/db16-0806","article-title":"Differentiation of diabetes by pathophysiology, natural history, and prognosis","volume":"66","author":"Skyler","journal-title":"Diabetes"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.2196\/50201","article-title":"Applying machine learning techniques to implementation science","volume":"16","author":"Huguet","journal-title":"Online J Public Health Inform"},{"issue":"3","key":"R62","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00592-x","article-title":"Machine learning: algorithms, real-world applications and research directions","volume":"2","author":"Sarker","journal-title":"SN Comput Sci"},{"issue":"1","key":"R63","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00992-8","article-title":"Transparency of artificial intelligence\/machine learning-enabled medical devices","volume":"7","author":"Shick","journal-title":"NPJ Digit Med"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e68260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:54:53Z","timestamp":1782842093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e68260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":63,"URL":"https:\/\/doi.org\/10.2196\/68260","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"article-number":"v4i18e68260"}}