Large language models can supplement the assessment of clinical high risk for psychosis.

The following project acts as proof of concept on the usefulness of AI-based tools to capture latent psychosis risk information.

We used assessor notes for 2,077 Structured Interview for Psychosis-risk Syndromes interviews as input for different AI-based natural language processing models to produce metrics for psychosis risk, namely, a trained encoder-only model (ModernBERT), and zero-shot and few-shot instantiation of two decoder-only models (Large Language Model Meta AI Version 4 [LLaMA-4] and GPT-4.1 mini).