I read press releases of studies daily, and I know how a communication office of a university can boost a study to enormous proportions, but this press release doesn’t hold back at all:

A new one-minute video game is able to accurately and efficiently identify children with autism from those who have ADHD or are neurotypical.

This could indeed be the case, and I’m ready to believe this, but I noted immediately that it’s not an accepted paper in a journal but a published preprint. At the same time, the study does look promising.

Abstract of the study:

Background: Reliable and specific biomarkers that can distinguish Autism Spectrum Disorders (ASD) from commonly co-occurring Attention Deficit/Hyperactivity Disorder (ADHD) are lacking, causing misses and delays in diagnosis, and reducing access to interventions and quality of life.

Aims: To examine whether an innovative, brief (one-minute), videogame method called Computerised Assessment of Motor Imitation (CAMI) can identify ASD-specific imitation differences compared to neurotypical and ADHD children.

Method: This cross-sectional study used CAMI alongside standardised parent-report (SRS-2) and observational measures of autism (ADOS-2), ADHD (Conners), and motor ability (PANESS). Sample included a total of 183 children aged 7-13 years who had ADHD (without ASD), had ASD (with ADHD: ASD+ADHD, and without ADHD: ASD-only), and were neurotypical.

Results: Regardless of co-occurring ADHD, ASD children showed poorer CAMI performance than neurotypical children (p<.0001, Adjusted R2=.28), whereas ADHD and neurotypical children showed similar CAMI performance. Receiver Operating Curve and Support Vector Machine analyses showed that CAMI distinguishes ASD from both NT (80% true positive rate) and ADHD children (70% true positive rate) with a high success rate significantly above chance. Among autistic children, poor CAMI performance was associated with increased autism traits, particularly ADOS measures of social affect and restricted and repetitive behaviours (Adjusted R2=.23), but not with ADHD traits or motor ability.

Conclusions: Four levels of analyses – diagnostic group comparisons, dimensional associations, and classification metrics based on Receiver Operating Curve and Support Vector Machine – confirm that poor imitation measured by the low-cost and scalable CAMI method specifically distinguishes ASD not only from neurotypical development but also from commonly co-occurring ADHD.