Voice acoustics as a biomarker for autism

Early identification of children on the autism spectrum is crucial for early intervention with long-term positive effects on symptoms and skills. The need for improved objective autism detection tools is emphasized by the poor diagnostic power in current tools. Here, we aim to evaluate the diagnostic power of genuine acoustic features of the voice in children with autism spectrum disorder (ASD) with respect to a heterogeneous control group (composed of neurotypical children and children with Developmental Language Disorder [DLD] and children with sensorineural hearing loss with Cochlear Implant [CI]). This retrospective diagnostic study was conducted at the University Child Psychiatry Center of Tours (France). A total of 108 children, including 38 diagnosed with ASD (8.5 ± 0.25 years), 24 typically developing (TD; 8.2 ± 0.32 years) children and 46 children with atypical development (DLD and CI; 7.9 ± 0.36 years) were enrolled in our studies. We applied a ROC (Receiving Operator Characteristic) supervised clustering algorithm combined with cross-validation to develop a diagnostic model that can differentially diagnose a child with unknown disorder. The acoustic properties of speech samples produced by children in the context of a nonword repetition task were examined. We showed that voice acoustics predicted the diagnosis of autism with an overall accuracy of 91% [CI95%, 90.40%-91.65%] against TD children, and of 85% [CI95%, 84.5%-86.6%] against an heterogenous group of non-autistic children. Accuracy reported here with multivariate analysis is higher than in previous studies. Our findings demonstrate that easy-to-measure voice acoustic parameters could be used as a diagnostic aid tool, specific of ASD.