DiaTrend: A dataset from advanced diabetes technology to enable development of novel analytic solutions

Abstract

Objective digital data is scarce yet needed in many domains to enable research that can transform the standard of healthcare. While data from consumer-grade wearables and smartphones is more accessible, there is critical need for similar data from clinical-grade devices used by patients with a diagnosed condition. The prevalence of wearable medical devices in the diabetes domain sets the stage for unique research and development within this field and beyond. However, the scarcity of open-source datasets presents a major barrier to progress. To facilitate broader research on diabetes-relevant problems and accelerate development of robust computational solutions, we provide the DiaTrend dataset. The DiaTrend dataset is composed of intensive longitudinal data from wearable medical devices, including a total of 27,561 days of continuous glucose monitor data and 8,220 days of insulin pump data from 54 patients with diabetes. This dataset is useful for developing novel analytic solutions that can reduce the disease burden for people living with diabetes and increase knowledge on chronic condition management in outpatient settings.

T1DiabetesGranada: a longitudinal multi-modal dataset of type 1 diabetes mellitus

“…However, these four datasets are characterized by a relatively small sample size and short study duration. Very recently, a contribution has been made towards increasing the study duration: “DiaTrend” 23 , a public dataset collecting real CGM data during an average of 510 days from 54 T1D patients.…”

Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management

“…This omission poses a significant challenge when attempting to model and gain a deeper understanding of the role of these variables in the glucose regulatory system. Notable examples of open-source datasets incorporating multiple physiological variables include the OhioT1DM dataset [13] , and the more recent DiaTrend dataset [14] . Nevertheless, there is still a shortage of studies utilizing variables beyond glucose and insulin levels and attempting to determine their predictive capabilities, if any, for glucose prediction tasks in both healthy individuals and those with diabetes.…”