Large language models show potential for psychosis risk assessment from clinical interview transcripts
AI language models show promise for assessing early psychosis risk from interviews
An evaluation study of 373 participants with clinical high risk for psychosis transcripts found that large language models (LLMs) achieved 8…
Large AI models correctly identified early psychosis risk 80% of the time from interview transcripts, matching human expert scores while mos…
Corticolimbic Glutamate-Functional Connectivity Associations Found in Antipsychotic-Naive CHR-P Individuals
Could early brain changes in psychosis risk be linked to specific chemical connections?
An observational study of antipsychotic-naive clinical high-risk for psychosis (CHR-P) participants (n=22), healthy controls (n=23), and fir…
People at high risk for psychosis show weaker brain chemical connections before symptoms appear, unlike those who have already developed the…