On the Predictability of non-CGM Diabetes Data for Personalized Recommendation
This work addresses personalized diabetes management for patients without continuous monitoring, but it is incremental with limited impact.
The study tackled blood glucose prediction using non-CGM data from 9 patients, achieving marginal performance improvements through post-prediction methods to handle noise.
With continuous glucose monitoring (CGM), data-driven models on blood glucose prediction have been shown to be effective in related work. However, such (CGM) systems are not always available, e.g., for a patient at home. In this work, we conduct a study on 9 patients and examine the online predictability of data-driven (aka. machine learning) based models on patient-level blood glucose prediction; with measurements are taken only periodically (i.e., after several hours). To this end, we propose several post-prediction methods to account for the noise nature of these data, that marginally improves the performance of the end system.