Use of Machine Learning for Behavioral Distinction of Autism and ADHD

Friday, May 13, 2016: 5:30 PM-7:00 PM
Hall A (Baltimore Convention Center)
M. Duda1, R. Ma2, N. Haber2 and D. Wall3, (1)Department of Pediatrics, Stanford University, Stanford, CA, (2)Pediatrics, Stanford University, Stanford, CA, (3)Stanford University, Palo Alto, CA
Background: Though autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD) continue to rise in prevalence, together affecting >10% of today’s pediatric population, the methods of diagnosis remain subjective, cumbersome and time intensive.  Furthermore, considerable behavioral overlaps between the two disorders, including impulsivity and trouble with social interactions, can complicate differential diagnosis for clinicians. Methods to quickly and accurately assess risk for these, and other, developmental disorders are necessary to streamline the process of diagnosis and grant families access to much-needed therapies sooner.  

Objectives:  In light of our prior success in applying machine learning to gold-standard diagnostic tools distinguish ASD from non-ASD, we elected to apply similar methodology for the distinction of ASD and ADHD. The aims of this study were to determine 1) whether machine learning can be used to discern between autism and ADHD with high accuracy and 2) whether this distinction can be made using a small number of commonly measured behaviors.

Methods:  Using forward feature selection, as well as undersampling and ten-fold cross validation, we trained and tested six machine learning models on complete 65-item Social Responsiveness Scale (SRS) score sheets from 2925 individuals with either ASD (n = 2775) or ADHD (n = 150). 

Results: We found that only 6 of the 65 behaviors measured by the SRS were sufficient to distinguish ASD from ADHD with high accuracy (AUC = 0.964).

Conclusions:  These results support our previously stated hypotheses, providing a method for accurate classification of ASD and ADHD with a minimal set of behavioral features. This classification system shows promise for use as an electronically administered, caregiver-directed resource for preliminary risk evaluation and/or pre-clinical screening and triage that could help to speed the diagnosis of these disorders.