Scoring Physician Risk Communication in Prostate Cancer Using Large Language Models

Abstract

Effective risk communication is essential to shared decision-making in prostate cancer care. However, the quality of physician communication of key concepts varies widely in real-world consultations. Manual evaluation of communication is labor-intensive and not scalable. We present a structured, rubric-based framework that uses large language models (LLMs) to automatically score the quality of risk communication in prostate cancer consultations. Using transcripts from 20 clinical visits, we curated and annotated 487 physician-spoken sentences that referenced five key concepts for shared decision-making: cancer prognosis, life expectancy, and three treatment side effects (erectile dysfunction, incontinence, and irritative urinary symptoms). Each sentence was assigned a score from 0 to 5 based on the precision and patient-specificity of communicated risk, using a validated scoring rubric. We modeled this task as five multiclass classification problems and evaluated both finetuned transformer baselines and GPT-4o with rubric-based and chain-of-thought (CoT) prompting. Our best performing approach, which combined rubric-based CoT prompting with few-shot learning, achieved micro averaged F1 scores between 85.0 and 92.0 across domains, outperforming supervised baselines and matching inter-annotator agreement. These findings establish a scalable foundation for AI-driven evaluation of physician-patient communication in oncology and beyond.

Ähnliche Arbeiten