AZT1D: A Real-World Dataset for Type 1 Diabetes

TL;DR

AZT1D is a comprehensive real-world dataset for type 1 diabetes, including detailed patient data over several weeks, enabling advanced AI research for personalized treatment and glucose management.

Contribution

The paper introduces AZT1D, a detailed, publicly available dataset with granular insulin and glucose data, filling a critical gap for AI research in T1D management.

Findings

Dataset includes continuous glucose monitoring data.

Provides detailed insulin administration records.

Supports AI applications for personalized T1D care.

Abstract

High quality real world datasets are essential for advancing data driven approaches in type 1 diabetes (T1D) management, including personalized therapy design, digital twin systems, and glucose prediction models. However, progress in this area has been limited by the scarcity of publicly available datasets that offer detailed and comprehensive patient data. To address this gap, we present AZT1D, a dataset containing data collected from 25 individuals with T1D on automated insulin delivery (AID) systems. AZT1D includes continuous glucose monitoring (CGM) data, insulin pump and insulin administration data, carbohydrate intake, and device mode (regular, sleep, and exercise) obtained over 6 to 8 weeks for each patient. Notably, the dataset provides granular details on bolus insulin delivery (i.e., total dose, bolus type, correction specific amounts) features that are rarely found in existing datasets. By offering rich, naturalistic data, AZT1D supports a wide range of artificial intelligence and machine learning applications aimed at improving clinical decision making and individualized care in T1D.