Language models deconstruct the clinical intuition behind diagnosing autism
3 institutional releases
Published in Cell · View the paper (DOI)
Researchers used a large language model to analyze clinical reports of autism patients and found that repetitive behaviors and special interests are most indicative of an autism diagnosis. The study aims to improve diagnostic guidelines by reducing the focus on social factors.
Coverage from 3 institutions
- Repetitive behaviors and special interests are more indicative of an autism diagnosis than a lack of social skills Cell Press · Mar 26, 2025 · first to report
- Using LLMS to understand how autism gets diagnosed University of Montreal · Mar 26, 2025
- AI analysis of healthcare records reveals key factors in autism diagnosis McGill University · Mar 26, 2025