Eye-tracking-based measurement may aid in autism diagnoses in young children: JAMA
USA: Eye-tracking-based measurement of social visual engagement was predictive of autism diagnoses by clinical experts in young children aged 16- to 30 months referred to speciality clinics, a recent study has revealed. Social visual engagement is how kids look at and learn from their social environment.
In the multisite, prospective, double-blind study, published in the Journal of the American Medical Association (JAMA), 475 children were assessed for autism in 6 speciality clinics. Measurement of social visual engagement had 80.7% specificity and 71.0% sensitivity relative to expert clinical diagnosis. In the children subgroup whose autism diagnosis was certain (n=335), the test had 85.4% specificity and 78.0% sensitivity.
Children with autism signs often experience more than 1 year of delay before diagnosis and often experience longer delays if they are from ethnically, racially, or economically disadvantaged backgrounds. Most diagnoses are also received without the use of standardized diagnostic instruments. eye-tracking measurement of social visual engagement has shown potential as a performance-based biomarker to aid in the early diagnosis of autism.
Warren Jones, Marcus Autism Center, Children’s Healthcare of Atlanta, Atlanta, Georgia, and colleagues aimed to evaluate the performance of eye-tracking measurement of social visual engagement (index test) relative to expert clinical diagnosis in young children referred to speciality autism clinics.
The study included 16- to 30-month-old children enrolled at 6 US speciality centres from 2018 to 2019. Staff were blinded to clinical diagnoses and used automated devices for measuring eye-tracking–based social visual engagement. Expert clinical diagnoses were done using best practice standardized protocols by specialists blind to index test results. The study was completed in a 1-day protocol for each participant.
Primary outcome measures included test specificity and sensitivity relative to expert clinical diagnosis. Secondary outcome measures were test correlations with expert clinical assessments of verbal ability, social disability, and nonverbal cognitive ability.
The study led to the following findings:
- Eye-tracking measurement of social visual engagement was successful in 475 of the 499 enrolled children (mean age, 24.1 months).
- By expert clinical diagnosis, 46.5% had autism and 53.5% did not.
- In all children, the measurement of social visual engagement had a sensitivity of 71.0% and a specificity of 80.7%.
- In the subgroup of 335 children whose autism diagnosis was certain, sensitivity was 78.0% and specificity was 85.4%.
- Eye-tracking test results correlated with expert clinical assessments of individual levels of social disability (r = −0.75), verbal ability (r = 0.65), and nonverbal cognitive ability (r = 0.65).
"In young children referred to speciality clinics, eye-tracking–based measurement of social visual engagement was predictive of autism diagnoses by clinical experts," the researchers wrote.
"Further evaluation is warranted of the role of eye-tracking–based measurement in early diagnosis and assessment of autism in routine speciality clinic practice," they concluded.
Reference:
Jones W, Klaiman C, Richardson S, et al. Eye-Tracking–Based Measurement of Social Visual Engagement Compared With Expert Clinical Diagnosis of Autism. JAMA. 2023;330(9):854–865. doi:10.1001/jama.2023.13295
