Generating Clinical Vignettes that Preserve Cognitive Formulations

2026-08-30

AI Summary

研究提出FORMA框架，通过构建认知模型生成符合临床结构的病例短文，解决大语言模型生成内容虽流畅但缺乏特定临床结构的问题。

Abstract

Large language models can generate fluent clinical case vignettes, but fluency alone does not ensure fidelity to a specifiable clinical structure. We introduce FORMA, a theory-grounded framework that compiles a cognitive model of a disorder into a directed weighted graph, samples a person-specific configuration of that graph, and validates whether the generated vignette preserves the specified components and causal links. We instantiate FORMA on Posttraumatic Stress Disorder using the Ehlers and Clark cognitive model, generating 16,500 vignettes across 500 personas, 11 generation models, and three ablation conditions. Evaluation combines an external edge-recovery probe, two clinical experts, a scaled LLM judge, and a clinician user study with 100 licensed practitioners. The cognitive graph is recoverable from full-condition vignettes (MCC = +0.41, AUC = 0.70) but not from zero-shot generation (MCC = +0.01, AUC = 0.50). Experts rate full vignettes substantially higher than zero-shot alternatives, and clinicians perceive them to be human-written 85% of the time, compared with 22% for zero-shot. FORMA also reduces demographic disparity in perceived quality by 1.5-7x. These results show that cognitive formulation can serve as an auditable specification for scalable synthetic clinical text generation. A repository with the data and code is available online: https://github.com/Amit-Oren/FORMA.

Problem

• Clinical Vignettes
• Cognitive Formulations
• Large Language Models
• Fidelity

Innovation

• FORMA
• Cognitive Formulation
• Clinical Vignettes
• Directed Weighted Graph
• Posttraumatic Stress Disorder