Transfer learning with randomized controlled trial data for postprandial glucose prediction

Abstract

In recent years, numerous methods have been introduced to predict glucose levels using machine-learning techniques on patients' daily behavioral and continuous glucose data. Nevertheless, a definitive consensus remains elusive regarding modeling the combined effects of diet and exercise for optimal glucose prediction. A notable challenge is the propensity for observational patient datasets from uncontrolled environments to overfit due to skewed feature distributions of target behaviors; for instance, diabetic patients seldom engage in high-intensity exercise post-meal. In this study, we introduce a unique Bayesian transfer learning framework using randomized controlled trial (RCT) data, primarily targeting postprandial glucose prediction. Initially, we gathered balanced training data from RCTs on healthy participants by randomizing behavioral conditions. Subsequently, we pretrained the model's parameter distribution using RCT data from the healthy cohort. This pretrained distribution was then adjusted, transferred, and utilized to determine the model parameters for each patient. Our framework's efficacy was appraised using data from 68 GDM patients in uncontrolled settings. The evaluation underscored the enhanced performance attained through our framework. Furthermore, when modeling the joint impact of diet and exercise, the synergetic model proved more precise than its additive counterpart.