Applying Machine Learning for Early Detection of Autism Spectrum Disorder from Maternal Microbiome Data

Recent research has shown that those who have an inherited predisposition to autism spectrum disorder (ASD) demonstrate a strong association between gut microbiome dysbiosis and brain development through the gut-brain axis. Previous studies demonstrate that this predisposition is predominantly vertically transmitted from mother to child during labour and through breast milk. During this transmission step, several bacterial strains acting as biomarkers in the maternal gut microbiome have been shown to be conserved in the child. Current ASD diagnostic methods rely on behavioral assessments and genetic screening, often delaying intervention and placing additional stress on mothers during early parenthood. Utilizing maternal gut microbiome biomarkers in adjunct with genetic screening could provide a non-invasive screening tool that could enable timely risk detection, facilitating early interventions that improve developmental outcomes and reduce parental anxiety. To achieve this, we leverage random forests, a supervised machine learning algorithm that has been shown to accurately classify microbiome samples as originating from children with ASD or neurotypical children. Additionally, the bacterial species Bacteroides, Lachnospira, Anaerobutyricum, and Ruminococcus torques have been identified as strong biomarkers for ASD. The aim of the study is to evaluate the predictive accuracy of maternal gut microbiome data for pre screening for children with ASD, and validate whether previously identified biomarkers for ASD are conserved in maternal gut microbiome samples. Using samples from a mother’s gut microbiome to determine risk could revolutionize early ASD identification and diagnosis. Considering the connection between genetics and microbiome composition, this approach strengthens traditional genetic screening, offering a more comprehensive risk assessment. Further, by preparing parents earlier in their pregnancies, they can sooner explore supportive therapies, adjust prenatal and postnatal care, and access support systems. This proactive strategy could ultimately improve developmental outcomes, reduce diagnostic delays, and contribute to a deeper understanding of ASD’s environmental and biological influences.