AI Innovations Enhance Speed and Accuracy in Diagnosing Autism and ADHD

In a groundbreaking study published on July 8, 2025, in *Nature’s Scientific Reports*, a team of researchers led by Professor Jorge José at Indiana University (IU) has unveiled a novel diagnostic method leveraging artificial intelligence (AI) to significantly expedite and enhance the accuracy of diagnosing autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD). This innovative approach aims to address a critical issue in the current diagnostic landscape, where children often face wait times of up to 18 months to receive an appointment with a psychiatrist for suspected neurodivergent disorders.

Professor Jorge José, the James H. Rudy Distinguished Professor of Physics at IU Bloomington and a member of the Stark Neuroscience Research Institute at IU School of Medicine, emphasized the challenges psychiatrists face in diagnosing neurodivergent disorders, stating, "The symptoms of neurodivergent disorders are very heterogeneous; psychiatrists call them ‘spectrum disorders’ because there’s no one observable thing that tells them if a person is neurotypical or not."

The team, which includes distinguished faculty such as John I. Nurnberger, Distinguished Professor Emeritus at IU School of Medicine, and Martin Plawecki, Associate Professor of Psychiatry, has focused on developing tools that utilize quantitative biomarkers and biometrics to provide a more objective assessment of neurodivergent conditions. Their recent research outlines a methodology that could potentially reduce the diagnostic timeline to as little as 15 minutes, offering a much-needed solution in educational settings where early intervention is critical.

Khoshrav Doctor, a Ph.D. student at the University of Massachusetts Amherst and a former visiting research scholar at IU, noted that while this AI-driven approach serves as a powerful supplementary tool, it is not intended to replace the critical role of psychiatrists in diagnosing and treating these disorders. "It could help as an additional tool in the clinician’s toolbelt," Doctor stated. "It also gives us the ability to see who might need the quickest intervention and direct them to providers earlier."

The foundation of this research lies in identifying movement biomarkers—subtle physical movements that can distinguish neurotypical individuals from those with autism. In 2018, José published a study in collaboration with Rutgers that revealed these movement biomarkers, which can be detected through advanced sensor technology. Participants in the study were asked to reach for targets on a computer screen, while sensors recorded hundreds of images of their movements, resulting in measurable differences between neurotypical individuals and those diagnosed with autism.

Advancements in sensor technology have allowed the team to capture more comprehensive data regarding movement patterns, including velocity, acceleration, and rotation. Chaundy McKeever, a graduate student in physics at IU, explained, "We’re taking a physicist’s approach to looking at the brain and analyzing movement specifically. We’ve found that, typically, the more sporadic their movement, the more severe a disorder is."

Using supervised deep-learning techniques, the researchers analyzed the movement data of participants with various diagnoses, yielding insights into the severity of their conditions. José remarked, "By studying the statistics of the motion fluctuations, invisible to the naked eye, we can assess the severity of a disorder in terms of a new set of biometrics. No psychiatrist can currently tell you how serious a condition is."

This enhanced understanding of the severity of neurodivergent disorders holds significant implications for treatment. José noted that a more accurate assessment allows healthcare providers to tailor treatments more effectively, ensuring that patients receive the appropriate level of care based on the severity of their conditions. "Some patients will need a significant number of services and specialized treatments," he explained. "If, however, the severity of a patient’s disorder is in the middle of the spectrum, their treatments can be adjusted to be less demanding and often can be carried out at home, making their care more affordable and easier to manage."

As this promising research progresses, it signifies a pivotal step toward more efficient and accurate diagnostic practices in the realm of neurodivergent disorders. The introduction of AI not only has the potential to revolutionize the diagnostic process but also to enhance the quality of life for countless individuals and their families by facilitating timely and appropriate interventions.