JMIR Publications

ABSTRACT

Background:

Diabetic ketoacidosis (DKA) 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, evidenced by deficient ketone monitoring practices.

Objective:

To explore the potential for prediction of elevated ketone bodies from Continuous Glucose Monitoring (CGM) and insulin data in pediatric and adult patients with type 1 diabetes using a closed-loop system.

Methods:

Participants utilized the Dexcom G6 CGM system and the iLet Bionic Pancreas system for insulin administration for up to 13 weeks. We employed supervised binary classification machine learning, incorporating feature engineering, to identify heightened levels of ketone bodies (>0.6 mmol/L). Features were derived from CGM, insulin delivery data, and self-monitoring of blood glucose (SMBG) to develop an XGBoost-based prediction model. A total of 259 participants aged between 6 and 79 years, with over 49,000 days of full-time monitoring, were included in the study.

Results:

Among the participants, 1,768 ketone samples were eligible for modeling, including 383 event samples with ketone levels ≥ 0.6 mmol/L. Insulin, SMBG, and current glucose measurements provided discriminative information on elevated ketone bodies (ROC-AUC 0.64-0.69). CGM-derived features exhibited stronger discrimination (ROC-AUC 0.75-0.76). Integration of all feature types resulted in an ROC-AUC estimate of 0.82 (SD; 0.01) and a PR-AUC of 0.53 (SD; 0.03).

Conclusions:

CGM and insulin data present a valuable avenue for early prediction of patients at risk of developing diabetic ketoacidosis (DKA). Furthermore, our findings indicate the potential application of such predictive models in both pediatric and adult populations with type 1 diabetes.