Description
Nocturnal hypoglycemia is a serious complication of insulin-treated diabetes, which commonly goes undetected. Continuous glucose monitoring (CGM) devices have enabled prediction of impending nocturnal hypoglycemia, however, prior efforts have been limited to a short prediction horizon (~ 30 minutes). To this end, a nocturnal hypoglycemia prediction model with a 6-hour horizon (midnight-6 am) was developed using a random forest machine- learning model based on data from 10,000 users with more than 1 million nights of CGM data. The model demonstrated an overall nighttime hypoglycemia prediction performance of ROC AUC = 0.84, with AUC = 0.90 for early night (midnight-3 am) and AUC = 0.75 for late night (prediction at midnight, looking at 3-6 am window). While instabilities and the absence of late-night blood glucose patterns introduce predictability challenges, this 6-hour horizon model demonstrates good performance in predicting nocturnal hypoglycemia. Additional study and specific patient-specific features will provide refinements that further ensure safe overnight management of glycemia.
Learning Objective: How continious glucose monitoring data from diabities patients under free-living conditions can lead to prediction of impending adverse event of hypoglecima and what are the challanges in doing so.
Authors:
Long Vu (Presenter)
IBM
Sarah KEFAYATI, IBM
Tsuyoshi Ide, IBM
Venkata (Raju) Pavuluri, IBM
Gretchen Jackson, IBM
Lisa Latts, IBM
Yuxiang Zhong, Medtronic
Pratik Agrawal, Medtronic
Yuan-Chi Chang, IBM
Presentation Materials: