Identification of type 1 diabetes risk phenotypes using an outcome‑guided clustering analysis – published online 06/08/2024

Lu You, Lauric A. Ferrat, Richard A. Oram, Hemang M. Parikh, Andrea K. Steck, Jeffrey Krischer, Maria J. Redondo, the Type 1 Diabetes TrialNet Study Group

Individuals at risk of type 1 diabetes represent a heterogeneous population. In this issue, You et al (https://doi.org/10.1007/s00125-024-06246-w) aim to better understand the heterogeneity of this population by identifying clusters of individuals with distinct characteristics and varying levels of risk. Using an outcome-guided clustering approach, the authors identified six clusters using demographic, metabolic, immunological and genetic markers using a dataset from the TrialNet Pathway to Prevention study. The clustering results illustrate how different combinations and levels of these risk factors can contribute to the risk of type 1 diabetes. The results also suggest that clusters with similar risk levels may exhibit distinct characteristics, which further highlights the heterogeneity within this population. The authors conclude that stratifying risk using the identified clusters may contribute to improved risk prediction in type 1 diabetes.