Scientists have developed and tested deep learning models that can support clinicians by providing accurate results and clear and explainable insights, including model estimated probability scores for autism.
The model is outlined in a study published in eclinicalmedicine (Journal of Lancet) was used to analyze resting fMRI data. This is a non-invasive method that indirectly reflects brain activity through altered blood oxygenation.
In doing so, the model achieved cross-validation accuracy of up to 98% of autism spectrum disorder (ASD) and neural type classification, generating clear and explainable maps of brain regions that most affect their decisions.
Diagnosis of ASD has increased significantly over the past 20 years, partially reflecting increased awareness, increased screening, and changes in diagnostic criteria and clinical practice. Early identification and access to evidence-based support improves developmental and adaptive outcomes, and although effective, it may improve quality of life.
However, current diagnosis relies primarily on face-to-face and behavioral assessments, and there is an urgent need to improve assessment pathways as waits for confirmed diagnosis can range from months to years.
Researchers hope that with further verification, their models will benefit people with autism and clinicians who evaluate and support them by providing accurate and explainable insights to inform decisions.
The study was the result of a final year undergraduate project by BSC (Hons) computer science student Suryansh Vidya, overseen by Dr. Amir Aly, and researchers in engineering, computing and mathematics at the University of Plymouth. They were supported by researchers who are part of the Peninsula Medical College by the University of Psychology School and the Cornwall Intellectual Disability Equitable Research (CIDER) group.
Dr Amir Alley, a lecturer in artificial intelligence and robotics at the university and academic lead and corresponding author of the research, said, “There are over 700,000 people with autism in the UK, many others waiting to be evaluated. Accurate results and clear and explainable insights, including model estimated probability scores, further validated support for prioritizing and adjusting ratings.”
Using autism Brain Imaging Data Exchange (ABIDE) cohort containing 884 participants ages 7-64 at 17 sites, the team analyzed pre-processed RS-FMRI data and compared side-by-side for explanatory methods. Gradient-based techniques are the most effective, and the resulting maps are broadly consistent across pre-processing approaches, indicating which brain regions most affected the prediction of the model.
This work has already been carried out by PhD researcher Kush Gupta, who co-authored the current study. It incorporates a variety of multimodal data and machine learning models with the aim of developing robust, generalizable, AI-driven models that can support clinicians in autism assessment worldwide. This complements Dr. Aly's broader research programme, including the use of robots to support people with autism, and the development of AI methods to analyze data in the health sector.
Professor Rohit Shankar MBE, professor of neuropsychiatry at the university and director of the Cider Group, is a senior author of the current study. He added: “I have shown that artificial intelligence can serve as a catalyst for advancement in early autism detection and diagnosis accuracy, but some of the words of Robert Frost come to mind.
reference: Vidya S, Gupta K, Aly A, Wills A, Ifeachor E, Shankar R. Identification of key brain regions for autism diagnosis from FMRI data using explanatory AI: an observational analysis of Abide Dataset. eclinicalmedicine. doi:10.1016/j.eclinm.2025.103452
This article has been republished from: Note: Materials may have been edited for length and content. For more information, please contact the source quoted. You can access the press release publishing policy here.
