大语言模型在转移性前列腺癌临床决策支持中的效用:多中心专家验证
该多中心回顾性研究评估了五种大语言模型在238例转移性前列腺癌患者一线系统治疗决策中的表现。模型通过零样本提示生成摘要、治疗推荐及理由,经MDT安全裁定和三位肿瘤内科专家评分。安全通过率为79.0%-84.9%,安全通过输出效用评分处于5分制低至中4分范围,但约15%-21%输出突破安全阈值,不支持无监督使用。
要点
- 当前大语言模型可作为转移性前列腺癌初始治疗规划的辅助草稿工具,但无法替代临床决策。
- 在严格安全门槛下,约15%-21%的模型输出被判定为不安全,禁止无监督使用。
- 模型失败多集中于文档不完整的疑难病例,以缺失信息提取错误和指南逻辑偏差为主。
核心结论
- 当前大语言模型可支持转移性前列腺癌诊疗作为草稿辅助工具,但在严格门槛下约15%-21%的输出突破安全阈值,排除了在初始治疗规划场景中的无监督使用。
研究设计与样本
- 多中心回顾性评估,纳入三个三级中心2018-2025年238例连续转移性前列腺癌病例。
- 测试五种当代大语言模型,通过公开网页界面在锁定零样本提示方案下生成临床摘要、一线系统治疗推荐及理由。
- 输出经两阶段评估:先由多学科团队进行二分类安全裁定,未通过者所有领域Likert评分赋值为1;再由三位资深肿瘤内科医生对安全通过输出进行5分Likert评分。
- 配对有序结局采用Friedman检验及Holm校正事后比较,二分类安全结局采用Cochran Q及McNemar检验。
主要发现
- 安全通过率范围为79.0%至84.9%。
- 在安全通过的输出中,平均效用评分(5分Likert)处于低至中4分范围。
- 模型间差异在摘要总结方面最为明显,治疗推荐和理由在多重重比较校正后差异有限。
- 失败集中于文档不完整的疑难病例,以缺失信息相关提取错误、疾病状态/通路错误、指南逻辑偏差及安全检查遗漏为主。
临床怎么用
- 当前大语言模型可作为转移性前列腺癌初始治疗规划的草稿辅助工具,但不得在无监督条件下用于治疗决策。
- 临床使用时应重点核查文档不完整病例中缺失信息提取、疾病状态判断及指南逻辑的准确性。
局限性
- 研究为回顾性设计,样本来自三个三级中心,结论外推需谨慎。
- 模型通过公开网页界面以锁定零样本提示测试,未评估其他提示策略或临床集成环境下的表现。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Initial systemic treatment planning for metastatic prostate cancer (mPCa) requires rapid synthesis of heterogeneous clinical and biomarker information. Large language models (LLMs) could assist clinicians, but their safety and acceptability in this high-stakes setting remain uncertain. METHODS: We conducted a multicenter retrospective evaluation of 238 consecutive mPCa cases from three tertiary centers (2018-2025). Five contemporary LLMs were tested via publicly available web interfaces under a locked, zero-shot prompting protocol to generate a clinical summary, a first-line systemic treatment recommendation, and a rationale. Outputs underwent two-stage assessment: (1) multidisciplinary team (MDT) binary safety adjudication using a one-strike gate with a prespecified taxonomy of critical errors; unsafe outputs were assigned a Likert score of 1 for all domains; (2) three senior medical oncologists independently rated safety-passed outputs on 5-point Likert scales for summary accuracy, guideline-concordant and patient-tailored recommendations, and rationale quality. Paired ordinal outcomes were analyzed with Friedman tests and Holm-adjusted post hoc comparisons, and binary safety outcomes with Cochran's Q and McNemar tests. RESULTS: Safety rates ranged from 79.0% to 84.9%. Among safety-passed outputs, mean utility scores (5-point Likert) were in the low-to-mid 4 range. Between-model differences were most apparent for summarization, whereas treatment recommendations and rationales showed modest separation after multiplicity adjustment. Failures clustered in hard cases with incomplete documentation and were dominated by missingness-related extraction errors, disease-state/pathway errors, guideline logic deviations, and safety-check omissions. CONCLUSIONS: Current LLMs can support mPCa care as drafting assistants, but ∼15%-21% of outputs breached safety thresholds under a strict gate, precluding unsupervised use at initial treatment-planning encounters.
引用
- Chen Y, He K, Qu W, et al. Clinical utility of large language models in metastatic prostate cancer: A multicenter expert validation for decision support. Eur J Cancer. 2026. PMID: 41831267. doi:10.1016/j.ejca.2026.116667
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。