Accuracy of a 2-minute eye-tracking assessment to differentiate young children with and without autism.
Kristelle Hudry, Lacey Chetcuti, Diana Weiting Tan and 10 others
PMID 40640958WHAT IT FOUND
A 2-minute eye-tracking test correctly identified 79 of 96 autistic children and 70 of 100 non-autistic controls.
It missed 17 autistic children and falsely flagged 30 controls. The test supports screening but cannot replace clinical diagnosis.
Key findings
01The algorithm achieved 82% sensitivity and 70% specificity, correctly classifying 79 autistic and 70 non-autistic children.
02Misclassified autistic children had higher overall tracking rates and less pronounced behavioural autism features than correctly classified cases.
03The developers of the eye-tracking technology funded the trial and independently performed the algorithm development after data collection.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study groups were not matched for age, sex, or socio-demographics, which may have influenced classification accuracy. The algorithm development was performed by employees of the technology manufacturer, raising potential conflicts of interest. The study did not test the tool's reliability over time or its performance in a general clinical referral population.
Declared interests
Funding was provided by the developer/manufacturer JKC. Algorithm development was conducted by JKC staff independently of the clinical team.
The easy way to misread this
Do not interpret the 76% overall accuracy as evidence the test is ready for clinical diagnosis. The 30 false positives among non-autistic children and 17 missed autistic children mean this tool cannot replace expert clinical judgement and standardised behavioural assessments.