From the panic of professors desperate to catch plagiarizers, to the creation of an “AI assistant,” on almost every single social media platform and website, fears of AI have run rampant.
But what if AI wasn’t here to take our jobs? What if we could utilize AI for the betterment of our society?
Good news- we can, and we are utilizing AI in unpredicted ways. AI has made its way into a somewhat surprising environment: healthcare settings. The possibility of an AI model with the capability of diagnosing autism in children is life-changing.
A machine learning (ML) model known as AutMedAI has now predicted autism spectrum disorder (ASD), using only minimal medical and background information. A study done by Karolinska Institute and published in JAMA Network Open aimed to not only prove the use of AI in diagnosing ASD but to also assess the value of the ML model.
With the support of this model, early detection of autism is possible. Early detection of ASD is crucial in forming the support a child needs. With an almost 80% accuracy, children under the age of two stand to benefit greatly from the ML model. However, the implementation of this model aims to assist in the diagnosis of ASD, not replace standard assessments.
“I want to emphasize that our goal is for the model to become a valuable tool for health care, and it is not intended to replace a clinical assessment of autism,” Kristiina Tammimies, Associate Professor at the Center of Neurodevelopmental Disorders at Karolinska Institute (KIND) and last author of the study, said.
KIND describes its organization as a “competence center for research, development, and education in neurodevelopmental conditions, such as autism and ADHD.”
“With an accuracy of almost 80 percent for children under the age of two, we hope that this will be a valuable tool for healthcare,” Tammimies said.
The possibility of AutMedAI assisting with early diagnosis would largely benefit autistic patients as early intervention strategies have been proven to enhance development and build adaptive skills.
Early identification helps target and address the specific needs of individuals. For example, when autism is diagnosed early, extra teaching and time can be put towards areas needing improvement, such as social communication and behavior.
In addition, early identification helps families access “support services, educational resources, and community programs,” which help with “facilitating better coping mechanisms, reducing parental stress, and increasing adult independence,” according to a study published by the California Institute of Behavioral Neurosciences & Psychology, titled, “Early Diagnosis of Autism Spectrum Disorder: A Review and Analysis of the Risks and Benefits.”
Is it possible that AI could offer a healthier future for us all?
