AZT1D: A Real-World Dataset for Type 1 Diabetes
This dataset addresses a gap for researchers and clinicians in diabetes care by providing comprehensive data to support AI/ML applications, though it is incremental as it primarily offers new data rather than novel methods.
The authors tackled the scarcity of detailed real-world datasets for type 1 diabetes management by presenting AZT1D, a dataset from 25 individuals with T1D on automated insulin delivery systems, collected over 6 to 8 weeks per patient, which includes granular features like bolus insulin delivery details.
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.