{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:35Z","timestamp":1785545015115,"version":"3.56.0"},"reference-count":31,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Diabetes"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Diabetic ketoacidosis represents a significant and potentially life-threatening complication of diabetes, predominantly observed in individuals with type 1 diabetes (T1D). Studies have documented suboptimal adherence to diabetes management among children and adolescents, as evidenced by deficient ketone monitoring practices.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The aim of the study was to explore the potential for prediction of elevated ketone bodies from continuous glucose monitoring (CGM) and insulin data in pediatric and adult patients with T1D using a closed-loop system.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Participants used the Dexcom G6 CGM system and the iLet Bionic Pancreas system for insulin administration for up to 13 weeks. We used supervised binary classification machine learning, incorporating feature engineering to identify elevated ketone bodies (>0.6 mmol\/L). Features were derived from CGM, insulin delivery data, and self-monitoring of blood glucose to develop an extreme gradient boosting-based prediction model. A total of 259 participants aged 6-79 years with over 49,000 days of full-time monitoring were included in the study.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Among the participants, 1768 ketone samples were eligible for modeling, including 383 event samples with elevated ketone bodies (\u22650.6 mmol\/L). Insulin, self-monitoring of blood glucose, and current glucose measurements provided discriminative information on elevated ketone bodies (receiver operating characteristic area under the curve [ROC-AUC] 0.64\u20100.69). The CGM-derived features exhibited stronger discrimination (ROC-AUC 0.75\u20100.76). Integration of all feature types resulted in an ROC-AUC estimate of 0.82 (SD 0.01) and a precision recall-AUC of 0.53 (SD 0.03).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n CGM and insulin data present a valuable avenue for early prediction of patients at risk of elevated ketone bodies. Furthermore, our findings indicate the potential application of such predictive models in both pediatric and adult populations with T1D.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/67867","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T14:16:51Z","timestamp":1744294611000},"page":"e67867-e67867","source":"Crossref","is-referenced-by-count":3,"title":["Early Detection of Elevated Ketone Bodies in Type 1 Diabetes Using Insulin and Glucose Dynamics Across Age Groups: Model Development Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3484-7571","authenticated-orcid":false,"given":"Simon","family":"Cichosz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4278-0397","authenticated-orcid":false,"given":"Clara","family":"Bender","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"396","DOI":"10.7861\/clinmed.2019-0284","article-title":"Diabetic ketoacidosis: update on management","volume":"19","author":"Evans","journal-title":"Clin Med (Lond)"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2019.107797","article-title":"Defining and characterising diabetic ketoacidosis in adults","volume":"155","author":"Dhatariya","journal-title":"Diabetes Res Clin Pract"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"801","DOI":"10.3390\/endocrines3040066","article-title":"Diabetic ketoacidosis management: updates and challenges for specific patient population","volume":"3","author":"El-Remessy","journal-title":"Endocrines"},{"issue":"7","key":"R4","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1111\/pedi.12711","article-title":"Continuous glucose monitoring and glycemic control among youth with type 1 diabetes: international comparison from the T1D Exchange and DPV Initiative","volume":"19","author":"DeSalvo","journal-title":"Pediatr Diabetes"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1111\/apa.14931","article-title":"Adherence to insulin pump treatment declines with increasing age in adolescents with type 1 diabetes mellitus","volume":"109","author":"Spaans","journal-title":"Acta Paediatr"},{"issue":"6","key":"R6","doi-asserted-by":"publisher","DOI":"10.1136\/bmjdrc-2023-003662","article-title":"Awareness and knowledge of diabetic ketoacidosis in people with type 1 diabetes: a cross-sectional, multicenter survey","volume":"11","author":"Hepprich","journal-title":"BMJ Open Diabetes Res Care"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"e38","DOI":"10.2337\/dc16-2620","article-title":"Poor adherence to ketone testing in patients with type 1 diabetes","volume":"40","author":"Albanese-O\u2019Neill","journal-title":"Diabetes Care"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2021.679484","article-title":"Benefits and challenges of current closed-loop technologies in children and young people with type 1 diabetes","volume":"9","author":"Fuchs","journal-title":"Front Pediatr"},{"issue":"12","key":"R9","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1001\/jamapediatrics.2021.3965","article-title":"Effect of a hybrid closed-loop system on glycemic and psychosocial outcomes in children and adolescents with type 1 diabetes: a randomized clinical trial","volume":"175","author":"Abraham","journal-title":"JAMA Pediatr"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","first-page":"628","DOI":"10.2337\/dc22-1971","article-title":"Impact of advanced hybrid closed loop on youth with high-risk type 1 diabetes using multiple daily injections","volume":"46","author":"Boucsein","journal-title":"Diabetes Care"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/S2213-8587(21)00289-8","article-title":"Opportunities and challenges in closed-loop systems in type 1 diabetes","volume":"10","author":"Wilson","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"6","key":"R12","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1177\/19322968241280386","article-title":"Time to moderate and severe hyperglycemia and ketonemia following an insulin pump occlusion","volume":"18","author":"Klonoff","journal-title":"J Diabetes Sci Technol"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1089\/dia.2023.0531","article-title":"Development of machine learning models for the identification of elevated ketone bodies during hyperglycemia in patients with type 1 diabetes","volume":"26","author":"Lebech Cichosz","journal-title":"Diabetes Technol Ther"},{"issue":"13","key":"R14","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1056\/NEJMOA2205225\/SUPPL_FILE\/NEJMOA2205225_DATA-SHARING.PDF","article-title":"Multicenter, randomized trial of a bionic pancreas in type 1 diabetes","volume":"387","author":"Russell","journal-title":"N Engl J Med"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1900\/RDS.2016.13.217","article-title":"Blood ketones: measurement, interpretation, limitations, and utility in the management of diabetic ketoacidosis","volume":"13","author":"Dhatariya","journal-title":"Rev Diabet Stud"},{"key":"R16","unstructured":"Alice Z Amanda C . Feature engineering for machine learning: principles and techniques for data. O\u2019Reilly Media, Inc; 2018. ISBN: 9781491953242"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Chen T Guestrin C . XGBoost: A scalable tree boosting system. Presented at: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Aug 13-17, 2016:785-794; San Francisco, CA. 2016.[doi: 10.1145\/2939672.2939785]","DOI":"10.1145\/2939672.2939785"},{"issue":"10","key":"R18","doi-asserted-by":"publisher","first-page":"e516","DOI":"10.1016\/S2589-7500(20)30217-X","article-title":"Clinical features of COVID-19 mortality: development and validation of a clinical prediction model","volume":"2","author":"Yadaw","journal-title":"Lancet Digit Health"},{"issue":"12","key":"R19","doi-asserted-by":"publisher","first-page":"104441","DOI":"10.1016\/j.jstrokecerebrovasdis.2019.104441","article-title":"Extreme gradient boosting model has a better performance in predicting the risk of 90-day readmissions in patients with ischaemic stroke","volume":"28","author":"Xu","journal-title":"J Stroke Cerebrovasc Dis"},{"issue":"6","key":"R20","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1109\/TCBB.2019.2911071","article-title":"XGBoost model for chronic kidney disease diagnosis","volume":"17","author":"Ogunleye","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"7","key":"R21","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1089\/dia.2023.0532","article-title":"Development and validation of a machine learning model to predict weekly risk of hypoglycemia in patients with type 1 diabetes based on continuous glucose monitoring","volume":"26","author":"Lebech Cichosz","journal-title":"Diabetes Technol Ther"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/095281300146272","article-title":"Distribution-balanced stratified cross-validation for accuracy estimation","volume":"12","author":"Zeng","journal-title":"J Exp Theor Artif Intell"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/s0001-2998(78)80014-2","article-title":"Basic principles of ROC analysis","volume":"8","author":"Metz","journal-title":"Semin Nucl Med"},{"key":"R24","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. arXiV. Preprint posted online onNov25, 2017. [doi: 10.48550\/arXiv.1705.07874]"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.1111\/j.1399-5448.2009.00569.x","article-title":"Diabetic ketoacidosis in children and adolescents with diabetes","volume":"10 Suppl 12","author":"Wolfsdorf","journal-title":"Pediatr Diabetes"},{"issue":"5","key":"R26","doi-asserted-by":"publisher","DOI":"10.2196\/11030","article-title":"Data-Driven blood glucose pattern classification and anomalies detection: machine-learning applications in type 1 diabetes","volume":"21","author":"Woldaregay","journal-title":"J Med Internet Res"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.07.007","article-title":"Data-Driven modeling and prediction of blood glucose dynamics: machine learning applications in type 1 diabetes","volume":"98","author":"Woldaregay","journal-title":"Artif Intell Med"},{"issue":"5","key":"R28","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1177\/19322968211015206","article-title":"Classification of gastroparesis from glycemic variability in type 1 diabetes: a proof-of-concept study","volume":"16","author":"Cichosz","journal-title":"J Diabetes Sci Technol"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.3389\/fcdhc.2022.1066744","article-title":"Hypoglycemia event prediction from CGM using ensemble learning","volume":"3","author":"Fleischer","journal-title":"Front Clin Diabetes Healthc"},{"issue":"1","key":"R30","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1177\/1932296814549830","article-title":"Combining information of autonomic modulation and CGM measurements enables prediction and improves detection of spontaneous hypoglycemic events","volume":"9","author":"Cichosz","journal-title":"J Diabetes Sci Technol"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104865","article-title":"Penalty weighted glucose prediction models could lead to better clinically usage","volume":"138","author":"Cichosz","journal-title":"Comput Biol Med"}],"container-title":["JMIR Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/diabetes.jmir.org\/2025\/1\/e67867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:27:33Z","timestamp":1785536853000},"score":1,"resource":{"primary":{"URL":"https:\/\/diabetes.jmir.org\/2025\/1\/e67867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,10]]},"references-count":31,"URL":"https:\/\/doi.org\/10.2196\/67867","relation":{},"ISSN":["2371-4379"],"issn-type":[{"value":"2371-4379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,10]]},"article-number":"v10i5e67867"}}