Long waits for autism diagnosis are a big problem in many parts of the United States. In Missouri many families wait nearly a year and must travel far to reach specialty centres. Researchers at the University of Missouri School of Medicine worked with the company Cognoa to test an FDA-approved device called CanvasDx. The device uses AI and patient information to predict a positive or negative autism diagnosis. If the information is not clear, it returns an "indeterminate" result.
The study used the ECHO Autism community to work with primary care clinicians. Keeping care local helped families get a diagnosis several months sooner. In the sample of 80 children the device gave determinate results for about half and did not produce false positives or false negatives, and it never contradicted a clinician's diagnosis.
Difficult words
- diagnosis — a doctor’s identification of an illness or condition
- specialty — a specific area of medical care or work
- indeterminate — not clear or not decided yet
- primary care — basic medical care from a local doctor
- false positive — a test result that wrongly shows a disease is presentfalse positives
- predict — say what will likely happen before it does
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- How could a faster diagnosis help a family with a child?
- What do you think about using AI to help medical diagnosis? Why?
- Would you prefer care close to home or travel to a specialist? Why?
Related articles
Gagandeep Kang on Vaccines, Surveillance and Child Health in India
Gagandeep Kang, a leading expert on enteric diseases, urges India to prepare tools to prevent viral outbreaks. She helped develop indigenous rotavirus vaccines, built surveillance networks and now works at the Gates Foundation.
Many pesticides used in Latin America are banned in the EU
A study found that many active pesticide ingredients allowed on major crops in eight Latin American countries are banned or not authorised in the EU. The researchers examined public approval records up to December 2020 and warn of health risks.
AI and fake media in Bangladesh’s election
Before the February 12 election that followed a July 2024 student uprising, AI-generated images, videos and edited photocards spread false stories. Fact-checkers and a study found many cases of manipulation that targeted leaders and parties.