Overview
- Analysis of over 1,600 stool samples reveals 31 unique microbial signatures in children with autism.
- The study broadens focus beyond bacteria to include fungi, viruses, and archaea in the gut.
- Machine learning models based on these markers show high accuracy in predicting autism.
- Experts believe this approach could reduce diagnostic delays and improve early intervention.
- Further research is needed to confirm the microbiome's role and validate findings across diverse populations.