National Institutes of Health 1K23MH141460-01A1

Measurement-Informed Machine Learning for Generalizable Suicide Risk Prediction in Youth

Award to University of California, San Diego to develop a machine learning model for predicting suicide risk in youth using biopsychosocial data and EHRs, with a focus on generalizability and subgroup accuracy.

Description

This project aims to develop a transparent, interpretable, generalizable, and developmentally sensitive machine learning model of suicide risk in youth, incorporating neurobiological, psychological, electronic health record (EHR)-derived, and social indicators. The study will assess and address measurement non-invariance in biopsychosocial predictors across subgroups, predict future suicidal thoughts and behaviors using interpretable machine learning techniques, and enhance model calibration and accuracy within relevant subpopulations with external validation.

View original record