Related Experiment Video
Updated: Aug 10, 2025
Author Spotlight: Exploring Autism Spectrum Disorder Symptoms in Fruit Flies — Genetic Models and Behavioral Tests
Published on: September 6, 2024
Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder
Irena Voinsky1, Oleg Y Fridland2, Adi Aran3,4
1Department of Human Molecular Genetics and Biochemistry, Faculty of Medicine, Tel Aviv University, Tel Aviv 69978, Israel.
Insights
Early autism diagnosis is vital, but biomarkers are lacking. This study used RNA sequencing and machine learning to develop tentative diagnostic models for autism spectrum disorder (ASD), achieving 82% accuracy in a proof-of-concept phase.
Area of Science:
- Genetics
- Computational Biology
- Neuroscience
Background:
- Early diagnosis of autism spectrum disorder (ASD) is critical for timely intervention and support.
- Current diagnostic methods are lengthy and lack reliable biological markers.
- Identifying genetic and molecular indicators can significantly improve diagnostic efficiency.
Purpose of the Study:
- To develop and evaluate machine learning (ML) models for the early diagnosis of ASD.
- To identify potential RNA expression biomarkers associated with ASD.
- To explore the utility of RNA sequencing data in conjunction with ML for ASD detection.
Main Methods:
- RNA sequencing was performed on peripheral blood samples from children with ASD and neurotypical (NT) children.
- A dataset of 10 genes with dysregulated blood expression in ASD was identified.
- Random forest classifier and other ML models were trained using RNA expression data.
Main Results:
- Two ML models demonstrated an 82% accuracy in distinguishing between children with ASD and NT children.
- The study identified specific genes with altered blood expression levels in ASD.
- The findings represent a proof-of-concept for ML-based ASD diagnostic tools.
Conclusions:
- ML models utilizing RNA expression data show promise as supportive tools for early ASD diagnosis.
- Further validation with larger cohorts is necessary to refine these diagnostic models.
- This approach may lead to more objective and efficient methods for identifying ASD.
Abstract:
Early diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 American and Israeli children with ASD and 26 neurotypically developing (NT) children to identify 10 genes with dysregulated blood expression levels in children with ASD. Machine learning (ML) analyzes data by computerized analytical model building and may be applied to building diagnostic tools based on the optimization of large datasets. Here, we present several ML-generated models, based on RNA expression datasets collected during our recently published RNA-seq study, as tentative tools for ASD diagnosis. Using the random forest classifier, two of our proposed models yield an accuracy of 82% in distinguishing children with ASD and NT children. Our proof-of-concept study requires refinement and independent validation by studies with far larger cohorts of children with ASD and NT children and should thus be perceived as starting point for building more accurate ML-based tools. Eventually, such tools may potentially provide an unbiased means to support the early diagnosis of ASD.
