The goal of the LabWAS workgroup is to leverage clinical lab tests stored in EHRs to understand the relationship between genetic risk for psychiatric disorders and quantitative physiological measurements. At Vanderbilt, we developed a pipeline to clean and analyze thousands of lab traits stored in EHRs, QualityLab and LabWAS. We conducted proof-of-principle analyses at Vanderbilt and MGB demonstrating cardiovascular disease polygenic scores associated with known risk factors using the cleaned lab values.
The goal of the PRS and Clinical Outcomes workgroup is to explore the associations between polygenic risk scores (PRS) for various psychiatric conditions (e.g., bipolar, schizophrenia, major depression disorder) and healthcare utilization. Analyses are performed at Geisinger, Vanderbilt, and MGB.
We aim to use clinical characteristics of individuals with a bipolar disorder (BD) diagnosis to identify undiagnosed cases and individuals at high predicted risk for being a case. At three participating sites (VUMC, MGB, GHS), we will derive risk prediction models for BD using several machine-learning approaches (Naïve Bayes, Random Forest, XGBoost).
We will examine whether the incorporation of polygenic risk scores (PRS) can enhance the performance of electronic health records (EHR)-based risk prediction models for psychiatric disorders.