JMIR Publications

ABSTRACT

Objective:

This study aims to develop a prediction model for hypoglycemic events with low false alert rate, high sensitivity and specificity, and good generalizability to new patients and time periods. Research Design and

Methods:

Performance improvement by focusing on sustained hypoglycemic events, defined as glucose values less than 70 mg/dL for at least 15 minutes, are explored. Two different modeling approaches are considered: (1) Classification based method to directly predict sustained hypoglycemic events, (2) Regression based prediction of glucose at multiple time points in the prediction horizon and subsequent inference of sustained hypoglycemia. To address generalizability and robustness of the model, two different validation mechanisms were considered: (a) Patient-based validation (model performance was evaluated on new patients), and (b) Time-based validation (model performance was evaluated on new time period).

Results:

This study utilized data from 110 patients over 30-90 days comprising 1.6 million CGM 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 false alert rate, and improves sensitivity and specificity. It also results in models that have better generalizability to new patients and time periods.