On 2 June 2021, the US Food & Drug Administration (FDA) authorized the marketing of a device that may be used to help diagnose autism spectrum disorder (ASD). The authorization allows pediatricians to use a device developed and marketed by Cognoa, a California (US) company seeking to advance timely, early identification of behavioral health issues.
The Cognoa assessment is comprised of three parts: A 4-minute, parent-report questionnaire; observation of key behaviors using a 2-minute, semi-structured home video of children; and a 2-minute clinician-completed questionnaire. The FDA examined how safe and effective the system was in a study of 425 patients aged 18 months through 5 years. That study revealed agreement between the Cognoa system and a panel of clinical experts. The FDA reported that, among the 31% of children that the system called "positive" or "negative," the system and the expert panels agreed about whether children had ASD on 81% of cases; the system was accurate in 98% of children who did and 79% of those who did not have ASD. A study by Abbas et al. (2020) reported that the system performs better than alternative screeners when employed with children 18-72 months of age.
It is important to note that the Cognoa device has only been tested as an aid in diagnosis. It has not been found to be an appropriate system to use on its own for diagnosis of ASD.
Said another way, developers hope that the diagnostic aid will help physcians expedite formal diagnosis of ASD. According to the FDA bulletin,
“Autism spectrum disorder can delay a child’s physical, cognitive and social development, including motor skill development, learning, communication and interacting with others. The earlier ASD can be diagnosed, the more quickly intervention strategies and appropriate therapies can begin,” said Jeff Shuren, M.D., J.D., director of the FDA’s Center for Devices and Radiological Health. “Today’s marketing authorization provides a new tool for helping diagnose children with ASD.”
Abbas, H., Garberson, F., Liu-Mayo, S., Glover, E., & Wall, D. P. (2020). Multi-modular AI approach to streamline autism diagnosis in young children. Scientific Reports, 10, 5014. https://doi.org/10.1038/s41598-020-61213-w