Stratifying Risk for Onset of Type 1 Diabetes Using Islet Autoantibody Trajectory Clustering

By Sejal Mistry, Ramkiran Gouripeddi, Vandana Raman, Julio C. Facelli

Department of Biomedical Informatics, Center for Clinical and Translational Science, Division of Pediatric Endocrinology, Department of Pediatrics University of Utah

Aims/Hypothesis:

Islet autoantibodies can be detected prior to the onset of type 1 diabetes and are important tools for disease screening. Current risk models rely on positivity status of islet autoantibodies alone. This work aimed to determine if a data-driven model incorporating characteristics of islet autoantibody development, including timing, type, and titer, could stratify risk for type 1 diabetes onset. 

Methods:

Glutamic acid decarboxylase (GADA), tyrosine phosphatase islet antigen-2 (IA-2A), and insulin (IAA) islet autoantibodies were obtained for 1,415 children enrolled in The Environmental Determinants of Diabetes in the Young study. Unsupervised machine learning algorithms were trained to identify clusters of autoantibody development based on islet autoantibody timing, type, and titer. 

Results:

We identified 2 – 4 clusters in each year cohort that differed by autoantibody timing, titer, and type. During the first 3 years of life, risk for type 1 diabetes was driven by membership in clusters with high titers of all three autoantibodies. Type 1 diabetes risk transitioned to type-specific titers during ages 4 – 8, as clusters with high titers of IA-2A showed faster progression to diabetes compared to high titers of GADA. The importance of high GADA titers decreased during ages 9 – 12, with clusters containing high titers of IA-2A alone or both GADA and IA-2A demonstrating increased risk. 

Conclusions/Interpretation:

This unsupervised machine learning approach provides a novel tool for stratifying type 1 diabetes risk using multiple autoantibody characteristics. Overall, this work supports incorporation of islet autoantibody timing, type, and titer in risk stratification models for etiologic studies, prevention trials, and disease screening.

System Status

Cluster Utilization