Machine Learning Prediction of Persistent Adverse Mental Health Outcomes for Autistic Children: Leveraging Social Determinants of Health from Clinical Data

The multimethod study will use EHR data from Children's Hospital Los Angeles (CHLA) and the University of Florida Health System (UF Health). It involves three main steps: (1) identifying ecological- and individual-level SDoH factors within EHRs using natural language processing (NLP) to extract individual-level factors from clinical notes; (2) building machine learning risk prediction models for persistent adverse mental health outcomes, investigating the additive effect of SDoH compared to demographic/clinical characteristics; and (3) using a qualitative design to explore clinician perspectives on utilizing SDoH within EHRs in clinical care and gathering clinician response to the prediction model to create action steps for both sites. Stakeholder input will be elicited throughout the study from a Community Advisory Board.