Can polygenic scores enhance the predictive performance of clinical risk models for suicide attempts in a psychiatric emergency room setting? (Preprint)

BACKGROUND Despite growing interest in the clinical translation of polygenic risk scores (PRS), it remains uncertain to what extent genomic information can enhance the prediction of psychiatric outcomes beyond the data collected during clinical visits alone. OBJECTIVE To assess the clinical utility of incorporating PRS into a suicide risk prediction model trained on electronic health records (EHR) and patient-reported surveys among patients admitted to the emergency department (ED). METHODS Study participants were recruited from the psychiatric ED at Massachusetts General Hospital. We identified 333 adult patients of European ancestry who had high-quality genotype data available through their participation in the Mass General Brigham (MGB) Biobank. Multiple psychiatric PRS were added to a previously validated suicide prediction model in a prospective cohort enrolled between February 4, 2015, and March 13, 2017. Data analysis was performed from July 11, 2022 to August 31, 2023. Suicide attempt was defined using diagnostic codes from longitudinal EHR combined with 6-month follow-up surveys. The clinical risk score for suicide attempt was calculated from an ensemble model trained using an EHR-based suicide risk score and a brief survey, and subsequently used to define the baseline model. We generated PRS for depression, bipolar disorder, schizophrenia, suicide attempt, and externalizing traits using PRS-CS for European ancestry participants. Model performance was evaluated using area under the receiver operator curve (AUC), area under the precision-recall curve (AUPRC), and positive predictive values (PPVs). RESULTS Of the 333 patients (178 [53.5%] male; mean age [SD], 36.8 [13.6] years; 333 [100.0%] non-Hispanic, 324 [97.3%] self-reported White), 28 [8.4%] had a suicide attempt within 6 months. Adding either schizophrenia PRS or all PRS to the baseline model resulted in the numerically highest discrimination (AUC = 0.86 [95% CI: 0.73 - 0.99]) compared to the baseline model (AUC = 0.84 [95% Cl: 0.70 - 0.98]). However, the numerical improvement in model performance was not statistically significant. CONCLUSIONS In this study, incorporating genomic information into clinical prediction models for suicide attempt did not improve patient stratification. Larger studies that include more diverse ancestries are required to validate whether the inclusion of psychiatric PRS in clinical prediction models can enhance the stratification of patients at risk of suicide attempts.