A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX)
Elliott C. Pryor, Marc D. Breton, Anas El Fathi
TLDR
DIAX is a new standardized JSON format unifying diabetes time-series data to improve interoperability and reproducibility for research and machine learning.
Key contributions
- Introduces DIAX, a standardized JSON format for unifying diabetes time-series data (CGM, insulin, meals).
- Enhances interoperability, reproducibility, and extensibility for diabetes research and machine learning applications.
- Provides an open-source repository with tools for data conversion, visualization, and cross-format compatibility.
- Supports major diabetes datasets, encompassing over 10 million patient-hours of data.
Why it matters
Inconsistent data formats across diabetes devices impede critical research and machine learning efforts. DIAX addresses this by providing a unified, standardized format. This will accelerate data sharing, integration, and analysis, fostering advancements in diabetes management.
Original Abstract
Diabetes devices, including Continuous Glucose Monitoring (CGM), Smart Insulin Pens, and Automated Insulin Delivery systems, generate rich time-series data widely used in research and machine learning. However, inconsistent data formats across sources hinder sharing, integration, and analysis. We present DIAX (DIAbetes eXchange), a standardized JSON-based format for unifying diabetes time-series data, including CGM, insulin, and meal signals. DIAX promotes interoperability, reproducibility, and extensibility, particularly for machine learning applications. An open-source repository provides tools for dataset conversion, cross-format compatibility, visualization, and community contributions. DIAX is a translational resource, not a data host, ensuring flexibility without imposing data-sharing constraints. Currently, DIAX is compatible with other standardization efforts and supports major datasets (DCLP3, DCLP5, IOBP2, PEDAP, T1Dexi, Loop), totaling over 10 million patient-hours of data. https://github.com/Center-for-Diabetes-Technology/DIAX
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.