London: AI technology can help predict which young children are more likely to develop autism, a new study has revealed.
The researchers said that an AI program called AutMedA could find in medical data children who could be diagnosed prematurely with autism at age 2 or younger without a case medical test.
The “AutMedAI” program was able to identify about 80 percent of children at risk for autism using data from a cohort of 12,000 children, researchers reported in the journal JAMA Open Network.
Specifically, the age of a child’s first smile, their first short sentences and the presence of eating difficulties showed a strong likelihood of autism, the researchers said.
“With almost 80 percent accuracy in predicting autism in children under 2 years old, we hope this will be a valuable tool for healthcare,” said senior researcher Cristina Tamimez.
