A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX)

Elliott C. Pryor; Marc D. Breton; Anas El Fathi

cs.LGApr 13, 2026

A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX)

Authors: Elliott C. Pryor, Marc D. Breton, Anas El Fathi

Organizations: University of Virginia, Center for Diabetes Technology

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

Figures & tables

Key	Units	Description
unique_id		Unique identifier for the subject
cgm	mg/dL	CGM values
bolus	U	Insulin boluses (meal or correction)
basal_rate	U/h	Basal insulin delivery rate
		Assumed constant infusion at provided
		rate between samples

Table 1: Key definitions used in DIAX format.

Figure 1: Example conversion workflow. Raw data is acquired from the original source. Then the matching script from GitHub can be used to convert to DIAX format, which can be used for any downstream task.

Panel of Figure 2 — Figure 2: Example visualization of DCLP3 data. Left shows comparison of AGP for two weeks generated with the call DIAX.plotCompare . Right shows outcomes over time generated with the call DIAX.plotOutcomes .

Continuous Glucose Monitoring

See all 16 papers

Glucose-ML: A collection of longitudinal diabetes datasets for development of robust AI solutions
Jul 18, 2025Temiloluwa Prioleau, Baiying Lu, Yanjun CuiForecasting Benchmarks Blood Glucose Forecasting
Department of Computer Science Emory University Atlanta, GA 30322 · Department of Computer Science Dartmouth College Hanover, NH 03755
GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes
Jul 23, 2026Davide Marelli, Giorgia Rigamonti, Mirko Paolo Barbato +1Type 1 Diabetes Time Series Forecasting
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milano 20126, Italy
Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling
Mar 12, 2026Sayantan Kumar, Jeremy C. WeissClinical Information Extraction Document Information Extraction
National Library of Medicine, Bethesda, Maryland, USA

Jul 18, 2025J/K move · Enter open · S save

Glucose-ML: A collection of longitudinal diabetes datasets for development of robust AI solutions

Temiloluwa Prioleau, Baiying Lu, Yanjun Cui

Department of Computer Science Emory University Atlanta, GA 30322 · Department of Computer Science Dartmouth College Hanover, NH 03755

Forecasting Benchmarks Blood Glucose Forecasting Clinical Prediction ML Reproducibility Wearable Health Monitoring Continuous Glucose Monitoring+1

Open paper AskPDF arXiv

Artificial intelligence (AI) algorithms are a critical part of state-of-the-art digital health technology for diabetes management. Yet, access to large high-quality datasets is creating barriers that impede development of robust AI solutions. To accelerate development of transparent, reproducible, and robust AI solutions, we present Glucose-ML, a collection of 10 publicly available diabetes datasets, released within the last 7 years (i.e., 2018 - 2025). The Glucose-ML collection comprises over 300,000 days of continuous glucose monitor (CGM) data with a total of 38 million glucose samples collected from 2500+ people across 4 countries. Participants include persons living with type 1 diabetes, type 2 diabetes, prediabetes, and no diabetes. To support researchers and innovators with using this rich collection of diabetes datasets, we present a comparative analysis to guide algorithm developers with data selection. Additionally, we conduct a case study for the task of blood glucose prediction - one of the most common AI tasks within the field. Through this case study, we provide a benchmark for short-term blood glucose prediction across all 10 publicly available diabetes datasets within the Glucose-ML collection. We show that the same algorithm can have significantly different prediction results when developed/evaluated with different datasets. Findings from this study are then used to inform recommendations for developing robust AI solutions within the diabetes or broader health domain. We provide direct links to each longitudinal diabetes dataset and openly provide our code.

Abstract

Continuous Glucose Monitoring

Explore similar work

Glucose-ML: A collection of longitudinal diabetes datasets for development of robust AI solutions

GlucoTune: A Unified Framework for Blood Glucose Preprocessing, Forecasting, and Benchmarking in Diabetes

Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling