A brand new study published in JAMA Network Open used AI to discover toddlers who could have autism spectrum disorder (ASD).
Researchers at Karolinska Institutet in Sweden have developed a machine learning model that may predict autism with roughly 80% accuracy in children under the age of two, using only basic medical and background information.
The study, led by Dr. Kristiina Tammimies and her team, used data from the Simons Foundation Powering Autism Research for Knowledge (SPARK) database, which incorporates extensive information on individuals with autism and their families.
The researchers analyzed data from 30,660 participants, evenly split between those with and without an autism diagnosis.
“Using [the] AI model, it could possibly be possible to make use of available information and earlier discover individuals with elevated likelihood for autism in order that they’ll get earlier diagnosis and help,” said Dr. Tammimies, emphasizing the potential impact of their work.
The team focused on 28 easily obtainable measures that may very well be collected before a toddler reaches 24 months of age.
These included parent-reported information from medical and background questionnaires, resembling age at first smile, eating behaviors, and language development milestones.
The researchers then created and tested 4 different machine learning models, ultimately choosing the best-performing one, which they named “AutMedAI.”
Promising results
To make sure the AutMedAI model worked well on different groups of individuals, the team tested it on two separate datasets:
- Nearly 12,000 recent participants from an updated version of their original database
- About 3,000 individuals with autism from a special study
The results were encouraging. When tested on the larger dataset of recent participants, the AI appropriately identified 78.9% of kids as either having autism or not. This means it was accurate in about 4 out of 5 cases.
Dr. Tammimies noted, “I need to emphasize that the algorithm cannot diagnose autism as this could [still] be done with gold standard clinical methods.”
The researchers also found features that were particularly predictive of autism.
These included problems with eating foods, the age at which children first constructed longer sentences, the age at which they achieved potty training, and the age at which they first smiled.
Interestingly, the model’s performance was robust across different age groups, sexes, and racial backgrounds.
This is especially noteworthy, as some existing screening tools have shown biases in identifying autism across diverse groups.
Early diagnosis can improve patient outcomes
Early detection of autism is important. It unlocks the door to timely interventions that may hugely improve a toddler’s development and long-term outcomes.
As Dr. Shyam Rajagopalan, the study’s first writer, explained, “This can drastically change the conditions for early diagnosis and interventions, and ultimately improve the standard of life for a lot of individuals and their families.”
However, the researchers caution that further validation in clinical settings is vital before the model is rolled out.
They’re also working on incorporating genetic information into the model, which could further boost its accuracy.
Of course, AI diagnostic tools only complement other clinical observations – and never replace them.
This research joins a growing body of labor exploring AI applications in mental health.
For instance, recent studies have shown AI’s potential in predicting anxiety levels based on individuals’ reactions to photographs, and in assisting with the diagnosis of schizophrenia.
Other AI-powered early diagnosis systems have been developed for neurological conditions, resembling Parkinson’s, showing how the technology can support early intervention and treatment.