Research
We are committed to open research that brings state of the art technology to patients sooner
MetaboNet
The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management. This work aims to establish a unified and accessible data resource for insulin dependent Diabetes algorithm development.
MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes
A standardized benchmark for glucose-forecasting models built on MetaboNet, developed in collaboration with Stanford.
Harmonizing Diabetes Management Datasets
Establishing a common data format for high frequency metabolic data.
GluPredKit: Development and User Evaluation of a Standardization Software for Blood Glucose Prediction
This study explores usability of GluPredKit, Open Source Software designed to standardize the training, testing, and comparison of blood glucose prediction algorithms.
GluPredKit: A Python Package for Blood Glucose Prediction and Evaluation
GluPredKit addresses common issues in applied ML for blood glucose prediction by creating a standardized pipeline for blood glucose prediction research.