Sequential data mining of infection patterns as predictors for onset of type 1 diabetes in genetically at-risk individuals

Abstract

Infections are implicated in the etiology of type 1 diabetes mellitus (T1DM); however, conflicting epidemiologic evidence makes designing effective strategies for presymptomatic screening and disease prevention difficult. Considering the temporality and combination in which infections occur may provide valuable insights into understanding disease etiology, but is rarely performed due to limited longitudinal datasets and insufficient analytical techniques. The objective of this work was to develop a robust computational approach to evaluate the temporality and combination of infections in presymptomatic T1DM. We present a sequential data mining pipeline that leverages routinely collected infectious disease data from a prospective cohort study to extract, interpret, and compare infection sequences. We then utilize this pipeline to assess risk for presymptomatic biomarkers of islet autoimmunity and clinical onset of T1DM. Overall, we identified 229 significant sequential rules that increased the risk for presymptomatic biomarkers of islet autoimmunity or clinical onset of T1DM. The risk for T1DM was significantly increased with single episode of sixth disease, specifically at 12 months. Multiple significant sequential rules involving varicella increased the risk for all presymptomatic biomarker-specific outcomes, while a single significant sequential rule involving parasites significantly increased risk for T1DM. Significant sequential rules involving respiratory illnesses were differentially represented among the presymptomatic biomarkers of islet autoimmunity and clinical onset of T1DM. Together, these findings provide the first insights into the timing and combination of infections in T1DM etiology, which may ultimately lead to personalized disease screening and prevention strategies. The sequential data mining pipeline developed in this work demonstrates how temporal data mining can be used to address clinically meaningful biomedical questions. This method can be adapted to other presymptomatic factors and clinical conditions using novel datasets, including electronic health records.