Phenotypic differences between female and male individuals with suspicion of autism spectrum disorder.

Researchers studied whether autism looks different in girls compared to boys by analyzing diagnostic test results from over 2,000 people. They found that fewer signs from the standard autism test were needed to identify autism in girls, but the current diagnostic tools work well for both girls and boys. However, girls were still underrepresented in the study, making up less than 20% of participants with autism.

This study used machine learning to analyze diagnostic data from 1,057 individuals with ASD and 1,230 without ASD to identify sex differences in autism presentation. The research found that fewer diagnostic features from the ADOS assessment were needed to accurately identify autism in females compared to males, while maintaining similar classification accuracy. Despite identifying some phenotypic differences between sexes, the study concluded that existing diagnostic tools adequately capture core autistic features in both females and males. The female sample comprised only 18.1% of the ASD group, reflecting continued underrepresentation in autism research that may limit detection of smaller effect sizes.

Current ADOS diagnostic tools appear adequate for identifying autism in both sexes, suggesting no immediate need for sex-specific diagnostic modifications. However, clinicians should remain aware of potential phenotypic differences between males and females when conducting assessments, while recognizing that core autistic features are captured effectively by existing protocols.

Female participants comprised only 18.1% of the ASD sample, potentially limiting statistical power to detect small to moderate effects. The study acknowledges that females with ASD may still be underrepresented, affecting generalizability of findings to the broader female autism population.

Although autism spectrum disorder (ASD) is a common developmental disorder, our knowledge about a behavioral and neurobiological female phenotype is still scarce. As the conceptualization and understanding of ASD are mainly based on the investigation of male individuals, females with ASD may not be adequately identified by routine clinical diagnostics. The present machine learning approach aimed to identify diagnostic information from the Autism Diagnostic Observation Schedule (ADOS) that discriminates best between ASD and non-ASD in females and males. Random forests (RF) were used to discover patterns of symptoms in diagnostic data from the ADOS (modules 3 and 4) in 1057 participants with ASD (18.1% female) and 1230 participants with non-ASD (17.9% % female).

Predictive performances of reduced feature models were explored and compared between females and males without intellectual disabilities. Reduced feature models relied on considerably fewer features from the ADOS in females compared to males, while still yielding similar classification performance (e.g., sensitivity, specificity). As in previous studies, the current sample of females with ASD is smaller than the male sample and thus, females may still be underrepresented, limiting the statistical power to detect small to moderate effects. Our results do not suggest the need for new or altered diagnostic algorithms for females with ASD.

Although we identified some phenotypic differences between females and males, the existing diagnostic tools seem to sufficiently capture the core autistic features in both groups.