The newly developed machine learning model has demonstrated the ability to predict autism in young children from limited information, according to a study by Karolinska Institutet published in JAMA Network Open. This model has the potential to facilitate the early detection of autism, which is critical for providing timely support. "With an accuracy of almost 80% for children under the age of two, we hope that this will be a valuable tool for health care," said Kristiina Tammimies, Associate Professor at KIND, the Department of Women's and Children's Health at Karolinska Institutet, and the study's senior author.
The research team utilized data from the SPARK database, which includes information on approximately 30,000 individuals with and without autism spectrum disorders in the United States. By analyzing a combination of 28 different parameters, the researchers developed four distinct machine-learning models to identify patterns in the data. These parameters were selected based on information about children that can be obtained without extensive assessments and medical tests before 24 months of age.
The model that performed the best was named "AutMedAI." Among approximately 12,000 individuals, the AutMedAI model accurately identified about 80% of children with autism. Notably, age of first smile, first short sentence, and the presence of eating difficulties were strong predictors of autism when combined with other parameters.
"The results of the study are significant becau.