Exploiting Large Language Models for Diagnosing Autism Associated Language Disorders and Identifying Distinct Features

Abstract Diagnosing language disorders associated with autism is a complex challenge, often hampered by the subjective nature and variability of traditional assessment methods. In this study, we explored Large Language Models (LLMs) to overcome the speed and precision obstacles by enhancing sensitivity and profiling linguistic features for autism diagnosis. This research utilizes natural language understanding capabilities of LLMs to simplify and improve the diagnostic process, focusing on identifying autism-related language patterns. We showed that the proposed method demonstrated improvements over the baseline models, with over a 10% increase in both sensitivity and positive predictive value in a zero-shot learning configuration. Combining accuracy and applicability, the framework could serve as a valuable supplementary tool within the diagnostic process for ASD-related language patterns. We identified ten key features of autism-associated language disorders across scenarios. Features such as echolalia, pronoun reversal, and atypical language usage play a critical role in diagnosing ASD and informing tailored treatment plans.