Predicting ASD diagnosis: Pattern classification and stratification reviewed

Abstract

Pattern classification (populations) and stratification (putting individuals into groups) are two approaches used in research on autism spectrum disorder (ASD), but translating them into clinical applicability is a challenge. How is ASD diagnosed, and how can it be predicted? One of the problems is the heterogeneity of ASD, another is that the initial diagnosis may not be as important as the trajectory, and the third is that regardless of the popularity of pattern classification, the people being treated are individuals, not populations.