MetaboNet: The Largest Publicly Available Consolidated Dataset for Type 1 Diabetes Management

TL;DR

MetaboNet tackles fragmentation in Type 1 Diabetes datasets by harmonizing 21 sources into a single resource with a standardized 5-minute sampling grid, totaling 3135 subjects and 1228 patient-years of CGM and insulin data, plus optional meal and activity information. The authors provide a public subset for immediate use and a Data Use Agreement–restricted subset with automated pipelines that convert external data into the MetaboNet format, enabling consistent benchmarking and cross-study analyses. They demonstrate population-level applicability and data-driven algorithm development, including a 30-minute glycemic-prediction benchmark and analyses of relationships between glycemic metrics across diverse subgroups. Overall, MetaboNet aims to improve generalizability and reproducibility in T1D research by reducing dataset biases and accelerating algorithm development through large-scale, heterogeneous data.

Abstract

Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D management datasets. Current datasets differ substantially in structure and are time-consuming to access and process, which impedes data integration and reduces the comparability and generalizability of algorithmic developments. This work aims to establish a unified and accessible data resource for T1D algorithm development. Multiple publicly available T1D datasets were consolidated into a unified resource, termed the MetaboNet dataset. Inclusion required the availability of both continuous glucose monitoring (CGM) data and corresponding insulin pump dosing records. Additionally, auxiliary information such as reported carbohydrate intake and physical activity was retained when present. The MetaboNet dataset comprises 3135 subjects and 1228 patient-years of overlapping CGM and insulin data, making it substantially larger than existing standalone benchmark datasets. The resource is distributed as a fully public subset available for immediate download at https://metabo-net.org/ , and with a Data Use Agreement (DUA)-restricted subset accessible through their respective application processes. For the datasets in the latter subset, processing pipelines are provided to automatically convert the data into the standardized MetaboNet format. A consolidated public dataset for T1D research is presented, and the access pathways for both its unrestricted and DUA-governed components are described. The resulting dataset covers a broad range of glycemic profiles and demographics and thus can yield more generalizable algorithmic performance than individual datasets.

Figures (12)

• Figure 1: Overview of the scale of MetaboNet 2026, compared with the T1DEXI dataset after preprocessing according to the study’s inclusion criteria. The green portion represents publicly available data, orange indicates datasets governed by data use agreements (DUAs), and blue corresponds to the combined public and DUA-protected datasets. Patient-years of CGM and insulin data are defined as periods during which continuous glucose monitoring and insulin dosing are recorded.
• Figure 2: Subject-level feature availability across the MetaboNet dataset. Each bar represents the number of subjects for which at least one non-missing value is available for the corresponding feature. This figure includes a subset of features, while the full list of available features is provided on the MetaboNet website MetaboNetNDDataDictionary.
• Figure 3: Demographic distribution of the dataset. The top panels show the proportion of individuals by gender (left) and ethnicity (right), with the majority identifying as female and white, respectively, and a notable fraction in the “unknown” category for both attributes. The bottom panel displays the age and age of diagnosis distributions.
• Figure 4: Scatter plot showing the relationship between height (x-axis) and weight (y-axis). Each point represents one subject in the full dataset, with point colour indicating the individual’s BMI category.
• Figure 5: Scatter plot showing the relationship between height (x-axis) and weight (y-axis). Each point represents one subject in the full dataset, with point colour indicating the individual’s BMI category.