GluPredKit: Development and User Evaluation of a Standardization Software for Blood Glucose Prediction

Abstract

Blood glucose prediction is an important component of biomedical technology for managing diabetes with automated insulin delivery systems. Machine learning algorithms hold the potential to advance this technology. However, the lack of standardized methodologies impedes direct comparisons of emerging algorithms. The purpose of this study is to address this challenge by developing a software platform designed to standardize the training, testing and comparison of blood glucose prediction algorithms. First, we design and implement the software guided by the current literature. To ensure the platform's user-friendliness, we conducted preliminary testing and a user study. In this study, four participants interacted with the software and provided feedback through the System Usability Scale (SUS) and open-ended questions. The result of the study was the software GluPredKit, which features a modular, open-source architecture, complemented by a command-line interface, comprehensive documentation, and a video tutorial to enhance usability. The user study indicates that GluPredKit offers high usability, facilitating comparisons between different algorithms. Future directions include continuously enhancing the software based on user feedback. We also invite community contributions to further expand GluPredKit with state-of-the-art components and foster a collaborative effort in standardizing blood glucose prediction research.