Official websites use .gov
A
.gov
website belongs to an official government organization in the
United States.
Secure .gov websites use HTTPS
A
lock
(
) or
https://
means you’ve safely connected to the .gov website. Share sensitive
information only on official, secure websites.
PubMed ID:
36446887
Public Release Type:
Journal
Publication Year: 2023
Affiliation: 1 Department of Biomedical Informatics, University of Utah, Salt Lake City, UT, USA
2 Clinical and Translational Science Institute, University of Utah, Salt Lake City, UT, USA
3 Division of Pediatric Endocrinology, Department of Pediatrics, University of Utah, Salt Lake City, UT, USA
DOI:
https://doi.org/10.1007/s00125-022-05843-x
Authors:
Mistry S,
Gouripeddi R,
Raman V,
Facelli JC
Request IDs:
23177
Studies:
The Environmental Determinants of Diabetes in the Young
Objective: To determine if a data-driven model incorporating timing, type, and titer of islet autoantibody development could stratify risk for type 1 diabetes. Research Design and Methods: Glutamic acid decarboxylase (GAD), tyrosine phosphatase islet antigen-2 (IA2A), 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. The risk for type 1 diabetes across each cluster was evaluated using time-to-event analysis. Results: 38 clusters across 12 years of life that differed by autoantibody timing, titer, and type were identified. During the first 3 years, risk for type 1 diabetes was driven by membership in clusters with high titers of all three autoantibodies (1-year risk: 20.87–56.25%, 5-year risk: 67.73–69.19%). Type 1 diabetes risk transitioned to type-specific titers during ages 4 – 8, as clusters with high titers of IA2A (1-year risk: 20.88–28.93%, 5-year risk: 62.73–78.78%) showed faster progression to diabetes compared to high titers of GAD (1-year risk: 4.38–6.11%, 5-year risk: 25.06–31.44%). The importance of high GAD titers decreased during ages 9 – 12, with clusters containing high titers of IA2A alone (1-year risk: 14.82–30.93%) or both GAD and IA2A (1-year risk: 8.27–25.0%) demonstrating increased risk. Conclusions: These findings suggest that data-driven models incorporating the timing, type, and titer of islet autoantibodies can stratify risk for type 1 diabetes, ultimately informing enrollment strategies for etiologic studies, prevention trials, and disease screening.
