LLM-derived narrative metrics in chronic pain: convergent validity and novel cognitive constructs

Abstract

The use of subjective reports and questionnaires to evaluate chronic pain, while the gold standard, conveys a limited scope of the patients’ experience and is burdensome. Here we demonstrate that large language models (LLMs) can evaluate patient-provided texts and automatically generate specific, clinically meaningful, and reliable scores for the sensory, affective, and social dimensions of chronic pain. LLMs can also generate assessor-dependent constructs such as agency and personal narrative.