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

Abstract

Type 1 diabetes mellitus (T1D) patients face daily difficulties in keeping their blood glucose levels within appropriate ranges. Several techniques and devices, such as flash glucose meters, have been developed to help T1D patients improve their quality of life. Most recently, the data collected via these devices is being used to train advanced artificial intelligence models to characterize the evolution of the disease and support its management. Data scarcity is the main challenge for generating these models, as most works use private or artificially generated datasets. For this reason, this work presents T1DiabetesGranada, an open under specific permission longitudinal dataset that not only provides continuous glucose levels, but also patient demographic and clinical information. The dataset includes 257 780 days of measurements spanning four years from 736 T1D patients from the province of Granada, Spain. This dataset advances beyond the state of the art as one the longest and largest open datasets of continuous glucose measurements, thus boosting the development of new artificial intelligence models for glucose level characterization and prediction.

Fig. 1

Distribution of the age of the patients at the start of the data collection (January 6th, 2018).

Fig. 2

Number of patients by number of days with blood glucose level measurements. The colors depict periods of one year. The mean number of days is represented by a vertical line.

Fig. 3

Number of patients and blood glucose level measurements by date.

Fig. 4

Data distribution of the blood glucose level measurements: (a) Overall; (b) By sex; and (c) By age.

Fig. 5

Percentage of blood glucose level measurements per level ranges and age ranges. Blood glucose level ranges are represented by colors and defined as: TBR-L2, time below range with level 2 hypoglycemia (<54 mg/dL); TBR-L1, time below range with level 1 hypoglycemia (54 mg/dL - 69 mg/dL); TIR, time in range (70 mg/dL - 180 mg/dL); TAR-L1, time above range with level 1 hyperglycemia (181 mg/dL - 250 mg/dL). TAR-L2: time above range with level 2 hyperglycemia (≥251 mg/dL).

Fig. 6

Distribution of the values of the most commonly measured biochemical parameters. The bars with lines do not have the same range breadth as the rest in each chart.

Fig. 7

Number of patients per most common diagnoses of diabetes mellitus complications or other diseases.

Fig. 8

Logarithmic distribution of the gaps of blood glucose level measurements.