文献速递肿瘤 PET/CT核素与放射性配体治疗

ChatGPT-4o能否依据PROMISE V2标准可靠地标准化PSMA PET/CT与PET/MRI报告?一项探索性研究

Can chatGPT-4o reliably standardize PSMA PET/CT and PET/MRI reports using PROMISE V2 criteria? - An exploratory study.
PubMed 文献 · EJNMMI Res · 2026-06-26

本研究评估ChatGPT-4o从非结构化PSMA-PET/CT与PET/MRI报告中提取PROMISE V2分类的性能。PSMA-PET/CT的miTNM总准确率为79.8%,PET/MRI为91.0%(OR=2.80,95%CI:1.32-6.51,p=0.003)。T分期PET/MRI优于PET/CT(83.8% vs. 57.7%,OR=3.83,95%CI:1.34-12.69,p=0.006),N分期数值上更高(100% vs. 85.9%,p=0.014),M分期与PRIMARY评分两模态相当。

要点

  • ChatGPT-4o提取PROMISE V2的N、M分期可靠,T分期准确率有限
  • PET/MRI的miTNM总准确率91.0%显著高于PET/CT的79.8%
  • 分类理由可信度高,miTNM最低Likert评分≥4.8,PRIMARY≥4.1

核心结论

  • ChatGPT-4o能从自由文本PSMA-PET报告中可靠提取PROMISE V2的N和M分期分类,但T分期准确率有限。

研究设计与样本

  • 探索性研究,评估ChatGPT-4o从非结构化PSMA-PET/CT与PET/MRI报告中提取PROMISE V2分类的性能。

主要发现

  • PSMA-PET/CT的miTNM总准确率为79.8%,PSMA-PET/MRI为91.0%(OR=2.80,95%CI:1.32-6.51,p=0.003)。
  • T分期PET/MRI准确率83.8%优于PET/CT的57.7%(OR=3.83,95%CI:1.34-12.69,p=0.006)。
  • N分期PET/MRI准确率100%数值上高于PET/CT的85.9%(p=0.014)。
  • M分期两模态相当(89.1% vs. 95.7%;OR=0.84,95%CI:0.20-4.19,p=0.748)。
  • PRIMARY评分两模态相当(70.4% vs. 88.1%;OR=0.43,95%CI:0.05-2.14,p=0.315)。

关键数值与推荐

  • miTNM分类理由可信度最低Likert评分≥4.8,PRIMARY评分最低≥4.1。

临床怎么用

  • 可探索用ChatGPT-4o辅助从自由文本PSMA-PET报告中提取N、M分期结构化分类,T分期需谨慎。

局限性

  • 原文未报告局限性内容。

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: Structured reporting standardizes and facilitates reporting, improves accurate communication, and ultimately clinical decision-making. Although standardized frameworks such as PROMISE criteria are available for prostate-specific membrane antigen positron emission tomography (PSMA PET) for prostate cancer patients, free-text reporting remains predominant in both clinical routine and trials. Large language models (LLMs) may enable low-effort, time-efficient extraction of structured classifications from narrative reports. This study evaluated the performance of ChatGPT-4o for extracting PROMISE V2-based classifications from unstructured PSMA-PET/CT and PET/MRI reports. RESULTS: For PSMA-PET/CT, overall miTNM accuracy was 79.8%, whereas PSMA-PET/MRI achieved a significantly higher accuracy of 91.0% (OR = 2.80, 95% CI: 1.32-6.51, p = 0.003). Component-wise, PET/MRI outperformed PET/CT in T-stage classification (83.8% vs. 57.7%; OR = 3.83, 95% CI: 1.34-12.69, p = 0.006) and demonstrated numerically higher N-stage classification accuracy (100% vs. 85.9%, p = 0.014), while M-stage classification was comparable between modalities (89.1% vs. 95.7%; OR = 0.84, 95% CI: 0.20-4.19, p = 0.748). PRIMARY score accuracy was also comparable for PET/CT and PET/MRI (70.4% vs. 88.1%; OR = 0.43, 95% CI: 0.05-2.14, p = 0.315). ChatGPT-4o's rationale for classifications was rated highly plausible across modalities, with a minimum Likert score of ≥ 4.8 for miTNM and 4.1 for PRIMARY. CONCLUSION: ChatGPT-4o enables reliable extraction of PROMISE V2-based N- and M-stage classifications from free-text PSMA-PET reports, with limited accuracy for T-stage. This work provides a first step toward leveraging LLMs to support structured and efficient reporting in PSMA PET imaging and points out present limitations.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Hinterberger A, Mangold MH, Weigel C, et al. Can chatGPT-4o reliably standardize PSMA PET/CT and PET/MRI reports using PROMISE V2 criteria? - An exploratory study. EJNMMI Res. 2026. PMID: 42360587. doi:10.1186/s13550-026-01475-z

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。