MetaboNet: Unified Dataset for Type 1 Diabetes Algorithm Development
Researchers have consolidated multiple publicly available Type 1 Diabetes (T1D) datasets into a unified resource called MetaboNet, addressing fragmentation and lack of standardization that hindered algorithm development. The dataset includes 3135 subjects and 1228 patient-years of overlapping continuous glucose monitoring (CGM) and insulin pump dosing data, with auxiliary information like carbohydrate intake and physical activity retained when available. This resource aims to improve comparability and generalizability of T1D algorithmic developments.
Key facts
- MetaboNet is the largest publicly available consolidated dataset for T1D management.
- It comprises 3135 subjects and 1228 patient-years of overlapping CGM and insulin data.
- Inclusion required both CGM data and corresponding insulin pump dosing records.
- Auxiliary information such as carbohydrate intake and physical activity was retained when present.
- The dataset addresses fragmentation and lack of standardization across existing T1D datasets.
- Current datasets differ substantially in structure and are time-consuming to access and process.
- The work aims to establish a unified and accessible data resource for T1D algorithm development.
- The dataset is described in arXiv paper 2601.11505.
Entities
Institutions
- arXiv