Abstract / Summary
Preterm birth is a syndrome that is triggered by diverse biological pathways and presents with many comorbid diseases. Although twin studies reveal a substantial heritable component, the genetic mechanisms of preterm birth remain poorly understood. We hypothesize that refining the preterm birth phenotype will reveal sub-phenotypes associated with distinct genetic risk factors and potential treatments. We leverage rich longitudinal data from electronic health records (EHRs) from nearly 60,000 individuals from two clinical sites to uncover sub-phenotypes of preterm birth. We apply tensor decomposition to comorbidities and their occurrence with respect to delivery for a pregnancy cohort with both preterm and not-preterm deliveries. We uncover latent factors (LFs) that capture coherent combinations of comorbidities (e.g., metabolic, inflammatory, and mental health conditions) and temporal trajectories of preterm and term births. Similar LFs are discovered between the two sites, underscoring their interpretability. Machine learning models trained on LFs accurately predict preterm birth and perform comparably to models trained on the full EHR data. Integrating genome-wide genotyping for >2,200 individuals, we find robust associations of preterm birth risk with high polygenic burden for cardiometabolic traits (cardiovascular disease, type 2 diabetes, and body mass index). Using mediation analysis, we find that specific LFs transmit part of this genetic risk to preterm birth. For example, a LF for hypertensive disorders of pregnancy mediates the effect of polygenic risk for cardiometabolic traits on preterm birth. In summary, our study integrates latent phenotypes discovered from large EHR datasets with genetic data to predict preterm birth risk, uncover phenotypic signatures that differentially associate with genetic risk for comorbidities, and delineate the mechanisms underlying the heterogeneity of this complex trait.