A new study has revealed the possibility of predicting autism in children with an accuracy of up to 80 percent, using a model called “AutMedAI”.
The research team in the study, conducted by the Karolinska Institute in Sweden, relied on large US data (SPARK), containing information on about 30,000 individuals with and without autism spectrum disorders.
The team analyzed this data without the need for extensive medical assessments and medical tests before the children reached 24 months of age, using the “AutMedAI” model.
According to the study, the Artificial Intelligence (AI) model showed good results in identifying children who suffer from more comprehensive difficulties in social communication and cognitive ability, and who suffer from delayed development.
Shyam Rajagopalan, the first author of this study, stressed the importance of the results reached in the early detection of those with autism spectrum disorders and effective therapeutic intervention through relatively limited and easily available info
rmation.
The research team plans to validate the model in clinical settings, and work is underway to include genetic information in the model, which could lead to more specific and accurate predictions.
Source: Qatar News Agency