Researchers at the UCL Institute for Neurology have harnessed AI language models to identify subtle speech patterns in schizophrenia patients. Their study, featured in PNAS, explores the potential of AI-driven language analysis for psychiatric diagnosis and evaluation.
Traditionally, psychiatric diagnoses rely heavily on verbal interactions, with limited use of objective tests like blood work or brain scans. This hampers our understanding of mental health causes and treatment progress.
In the study, 26 participants with schizophrenia and 26 without were tasked with verbal fluency exercises. By employing an AI language model trained on extensive internet text, the team assessed the predictability of words recalled by participants. Control group responses were more predictable than those from schizophrenia patients, especially in severe cases.
The researchers suggest that this discrepancy may be linked to how the brainforms associations between memories and ideas, a concept supported by brain scanning data in the same study.
Dr. Matthew Nour, the lead author, emphasized the transformative potential of AI language models in psychiatry, a field intrinsically linked to language and meaning.
Schizophrenia, a widespread psychiatric disorder, affects millions worldwide. Common symptoms include hallucinations, delusions, cognitive disarray, and behavioral changes.
The UCL and Oxford team plans to expand their study with a broader patient sample and varied speech settings to explore clinical applications of this technology. Dr. Nour anticipates the integration of AI language models into medical practice in the coming decade, offering a promising future for neuroscience and mental health research.