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

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.

We thank all the participants who enrolled in this study. This work was supported by the National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health under award number R01AR080627 (P.G.). Department of Statistics and Operations Research, University of North Carolina, Chapel-Hill, NC, USA Department of Anesthesiology and Perioperative Medicine, School of Medicine and Dentistry, University of Rochester, Rochester, NY, USA Department of Psychiatry, School of Medicine, and Dentistry, University of Rochester, Rochester, NY, USA Menninger Department of Psychiatry and Behavioral Sciences, Baylor College of Medicine, Houston, TX, USA Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA R.N. and G.C. are/were employees of IBM Research and accessed the LLM platform evaluated in this study (IBM Watson) through institutional research access provided by their employer.

IBM had no role in study design, data collection, analysis, interpretation of results, or the decision to publish. The authors declare no other competing interests. Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material.

If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. Norel, R., Zhang, Z., Gewandter, J. et al.

LLM-derived narrative metrics in chronic pain: convergent validity and novel cognitive constructs. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03359-x DOI: https://doi.org/10.1038/s41746-026-03359-x