King's College London

Research portal

Prediction of Autism at 3 Years from Behavioural and Developmental Measures in High-Risk Infants: A Longitudinal Cross-Domain Classifier Analysis

Research output: Contribution to journalArticle

G. Bussu, E. J.H. Jones, T. Charman, M. H. Johnson, J. K. Buitelaar, The Basis Team, S. Baron-Cohen, R. Bedford, P. Bolton, A. Blasi, S. Chandler, C. Cheung, K. Davies, M. Elsabbagh, J. Fernandes, I. Gammer, H. Garwood, T. Gliga, J. Guiraud, K. Hudry & 11 others M. H. Johnson, M. Liew, S. Lloyd-Fox, H. Maris, L. O’Hara, G. Pasco, A. Pickles, H. Ribeiro, E. Salomone, L. Tucker, A. Volein

Original languageEnglish
Pages (from-to)1-16
Number of pages16
JournalJournal of Autism and Developmental Disorders
Early online date16 Feb 2018
Publication statusE-pub ahead of print - 16 Feb 2018


King's Authors


We integrated multiple behavioural and developmental measures from multiple time-points using machine learning to improve early prediction of individual Autism Spectrum Disorder (ASD) outcome. We examined Mullen Scales of Early Learning, Vineland Adaptive Behavior Scales, and early ASD symptoms between 8 and 36 months in high-risk siblings (HR; n = 161) and low-risk controls (LR; n = 71). Longitudinally, LR and HR-Typical showed higher developmental level and functioning, and fewer ASD symptoms than HR-Atypical and HR-ASD. At 8 months, machine learning classified HR-ASD at chance level, and broader atypical development with 69.2% Area Under the Curve (AUC). At 14 months, ASD and broader atypical development were classified with approximately 71% AUC. Thus, prediction of ASD was only possible with moderate accuracy at 14 months.

Download statistics

No data available

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454