Improved Low-Glucose Predictive Alerts Based on Sustained Hypoglycemia: Model Development and Validation Study

Abstract

Background Predictive alerts for impending hypoglycemic events enable persons with type 1 diabetes to take preventive actions and avoid serious consequences. Objective This study aimed to develop a prediction model for hypoglycemic events with a low false alert rate, high sensitivity and specificity, and good generalizability to new patients and time periods. Methods Performance improvement by focusing on sustained hypoglycemic events, defined as glucose values less than 70 mg/dL for at least 15 minutes, was explored. Two different modeling approaches were considered: (1) a classification-based method to directly predict sustained hypoglycemic events, and (2) a regression-based prediction of glucose at multiple time points in the prediction horizon and subsequent inference of sustained hypoglycemia. To address the generalizability and robustness of the model, two different validation mechanisms were considered: (1) patient-based validation (model performance was evaluated on new patients), and (2) time-based validation (model performance was evaluated on new time periods). Results This study utilized data from 110 patients over 30-90 days comprising 1.6 million continuous glucose monitoring values under normal living conditions. The model accurately predicted sustained events with >97% sensitivity and specificity for both 30- and 60-minute prediction horizons. The false alert rate was kept to <25%. The results were consistent across patient- and time-based validation strategies. Conclusions Providing alerts focused on sustained events instead of all hypoglycemic events reduces the false alert rate and improves sensitivity and specificity. It also results in models that have better generalizability to new patients and time periods.

Explainable machine learning for real-time hypoglycaemia and hyperglycaemia prediction and personalised control recommendations

“…Sensitivity and specificity are evaluated from dichotomising model predictions at probability P=0.5. Again, we find a clear performance increase for our XGBoost model, in-keeping with the high performance of decision tree based methods [40] and commercial hybrid loop systems [41].…”

Development and validation of a machine learning model for classification of next glucose measurement in hospitalized patients

“…This limitation is similar to previous findings that demonstrated a high false alarm rates despite high sensitivity and specificity due to class imbalance. 37 In previous research, the high hypoglycemic false alarm rate was reduced by increasing specificity by excluding any hypoglycemic event that was transient. Since we did not use CGM data, we were unable to analyze the effects of transient hypoglycemic events on model performance.…”

Systemic inflammation as a biomarker of seizure propensity and a target for treatment to reduce seizure propensity

“…We are not aware of any report of efforts to predict seizure occurrence based on the concentration of any blood component. Consequently, the most appropriate model for doing so would seem to come from the literature about predicting sustained hypoglycemia based on blood glucose levels collected continuously by an in situ sensor 188,189 . In essence, machine‐learning algorithms would determine the magnitude or slope of concentration changes of the inflammation biomarker that best predicts/anticipates the next seizure 190 …”