Integrating genomic variants and developmental milestones to predict cognitive and adaptive outcomes in autistic children
Preprint
Abstract
Although the first signs of autism are often observed as early as 18-36 months of age, there is a broad uncertainty regarding future development, and clinicians lack predictive tools to identify those who will later be diagnosed with co-occurring intellectual disability (ID). Here, we developed predictive models of ID in autistic children (n=5,633 from three cohorts), integrating different classes of genetic variants alongside developmental milestones. The integrated model yielded an AUC ROC=0.65, with this predictive performance cross-validated and generalised across cohorts. Positive predictive values reached up to 55%, accurately identifying 10% of ID cases. The ability to stratify the probabilities of ID using genetic variants was up to twofold greater in individuals with delayed milestones compared to those with typical development. These findings underscore the potential of models in neurodevelopmental medicine that integrate genomics and clinical observations to predict outcomes and target interventions.Keywords
All Related Versions
- Published version: JAMA Pediatrics, 179 (6), 655.
This publication has 91 references indexed in Scilit:
- Developmental Variability in Autism Across 17 000 Autistic Individuals and 4000 Siblings Without an Autism DiagnosisJAMA Pediatrics, 2022
- Comparing Copy Number Variations in a Danish Case Cohort of Individuals With Psychiatric DisordersJAMA Psychiatry, 2021
- Prediction, Not Association, Paves the Road to Precision MedicineJAMA Psychiatry, 2021
- From Basic Science to Clinical Application of Polygenic Risk ScoresJAMA Psychiatry, 2021
- Developmental Predictors of Cognitive and Adaptive Outcomes in Genetic Subtypes of Autism Spectrum DisorderAutism Research, 2020
- Defining Positive Outcomes in More and Less Cognitively Able Autistic AdultsAutism Research, 2020
- Establishment of Best Practices for Evidence for PredictionJAMA Psychiatry, 2020
- Predictive Accuracy of a Polygenic Risk Score–Enhanced Prediction Model vs a Clinical Risk Score for Coronary Artery DiseaseJAMA, 2020
- Measuring and Estimating the Effect Sizes of Copy Number Variants on General Intelligence in Community-Based SamplesJAMA Psychiatry, 2018
- Global Prevalence of Autism and Other Pervasive Developmental DisordersAutism Research, 2012