Mental Health Crises in Youth With IDDs

Overview

This study is an unmatched, case-control study of 150 youth (Ages 7-17) with a parent reported Intellectual Developmental Disability (IDD) who present to Rady Children's Hospital Emergency Department with a Mental Health Crisis (MHC). Rady Children's Institute for Genomic Medicine (RCIGM) will collect biological samples (such as blood) of these participants to study their genomes, medical and psychiatric profiles to better understand specific characteristics that may predispose them to MHC's. The 150 youth will be compared to historical, publicly available cohorts of youth with IDD's

Approximately 7 million youth in the US have intellectual and developmental disabilities (IDDs) and about 10% of youth with IDDs are admitted to hospitals due to a mental health crisis (MHC) each year. With insufficient community services to support youth with IDDs and less than half of US mental health facilities providing services for them, emergency departments (EDs) have boarding rates for children with IDDs 2-3 times higher than peers without IDDs, part of a national youth mental health crisis. There is a critical need to identify youth with IDDs at risk for MHCs prior to onset. Machine-learning based electronic health record (EHR) analysis and whole genome sequencing (WGS) will be used to identify biopsychosocial and genomic risk factors that put youth with IDDs at risk for MHCs so that at-risk patients can be identified early and improved models of psychiatric care can be developed. Demographic, biomedical, socioeconomic, and service use data will be extracted from Rady Children's Hospital San Diego (RCHSD) EHR for 150 youth with IDDs presenting to the ED for MHCs. This experimental group will be compared to two historical groups of youth from the RCHSD EHR: 1)\~4000 youth with IDDs and psychiatric comorbidities but no history of MHCs and 2) \~4000 youth with IDDs without any psychiatric history. A machine learning-based network model will be used to classify psychiatric outcomes for youth with IDDs and perform leave-one-out cross validation to estimate the performance of these models and calculate metrics of classification performance. WGS will be completed for the cohort of 150 youth and neuropsychiatric polygenic scores (PGS) will be derived and their effect sizes compared to two groups of youth with IDDs from the Simons Simplex Collection: 1) \~50 youth with IDDs and severe psychiatric comorbidities and 2) \~1000 youth with IDDs and minimal or no psychiatric comorbidities. The rate of pathogenic rare variants will also be compared across cohorts. By applying machine learning methods to EHR data leveraging WGS, a combination of factors will be identified that predict psychiatric outcomes in youth with IDDs with high accuracy to allow for earlier intervention.