Machine learning and genomics – way forward for early identification and outcomes in autism?

Abstract

Autism is a heterogeneous condition diagnosed in 1-2% of children worldwide. Early identification followed with support has been shown to lead to better outcomes. Genetic factors are the main drivers in autism etiology and hundreds of genes and genomic loci are shown to be associated with the condition. In this talk, I will explore the intersection of machine learning and genomics in autism research, focusing on early identification and intervention outcomes. By combining early clinical markers followed with the integration of genomic data, our aim is to find a suitable model for early screening and identification of autism. Furthermore, we have shown that genetic information can be used to identify subgroups with differential intervention outcomes. Through showcasing the power of machine learning and genomics, I highlight the potential for early identification and tailored interventions in autism, ultimately improving outcomes.