文献速递泌尿生殖技术与安全PETCT

评估ChatGPT对68Ga PSMA PET/CT报告为患者所做的总结

Assessing ChatGPT's summarization of 68Ga PSMA PET/CT reports for patients.
PubMed 文献 · Abdom Radiol (NY) · 2024-09-30

本研究将164例新诊断前列腺癌患者的68Ga PSMA PET/CT报告输入ChatGPT-4,要求其回答5个关于肿瘤是否侵犯邻近器官、邻近淋巴结、远处淋巴结、骨及其他器官的问题。ChatGPT-4回答的清晰度和准确性采用Likert量表评分,清晰度均分4.93~4.99,准确性均分4.79~4.96;有远处淋巴结转移的患者准确性评分低于无远处淋巴结转移者(4.28±1.45 vs 4.94±0.39,p<0.001);13例(8%)的回答存在潜在有害信息。结论认为ChatGPT-4能成功解读结构化68Ga PSMA PET/CT报告,但今天不太可能取代医师的评估,尤其因为它可能产生编造的信息。

要点

  • ChatGPT-4对结构化68Ga PSMA PET/CT报告5个问题的清晰度均分为4.93~4.99,准确性均分为4.79~4.96。
  • 有远处淋巴结转移患者的准确性评分低于无远处淋巴结转移者(4.28±1.45 vs 4.94±0.39,p<0.001)。
  • 13例(8%)患者的ChatGPT-4回答存在潜在有害信息。

核心结论

  • ChatGPT-4能成功解读新诊断前列腺癌患者的结构化68Ga PSMA PET/CT报告,但今天不太可能取代医师的评估,尤其因为它可能产生编造的信息。

研究设计与样本

  • 本研究将164例新诊断前列腺癌患者的68Ga PSMA PET/CT报告输入ChatGPT-4,要求其回答5个关于肿瘤是否侵犯邻近器官、邻近淋巴结、远处淋巴结、骨及其他器官的问题,并对回答的清晰度和准确性进行Likert量表评分。

诊断标准与关键数值

  • ChatGPT-4回答5个问题的清晰度均分分别为4.93±0.32、4.95±0.25、4.96±0.19、4.99±0.11、4.96±0.30;准确性均分分别为4.87∓0.61、4.87∓0.62、4.79±0.83、4.96±0.25、4.93±0.45。有远处淋巴结转移患者准确性均分4.28±1.45,无远处淋巴结转移患者4.94±0.39,p<0.001。

临床应用与阅片要点

  • ChatGPT-4可用于解读结构化68Ga PSMA PET/CT报告,但今天不太可能取代医师的评估,尤其因为它可能产生编造的信息;13例(8%)患者的回答存在潜在有害信息。

局限性

  • 今天不太可能取代医师的评估,尤其因为它可能产生编造的信息。
  • 13例(8%)患者的回答存在潜在有害信息。

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)。

英文原文(摘要)· 点击展开

PURPOSE: ChatGPT has recently been the subject of many studies, and its responses to medical questions have been successful. We examined ChatGPT-4's evaluation of structured 68Ga prostate-specific membrane antigen (PSMA) PET/CT reports of newly diagnosed prostate cancer patients.

METHODS: 68Ga PSMA PET/CT reports of 164 patients were entered to ChatGPT-4. ChatGPT-4 was asked to respond the following questions according to the PET/CT reports: 1-Has the cancer in the prostate extended to organs adjacent to the prostate? 2-Has the cancer in the prostate spread to neighboring lymph nodes? 3-Has the cancer in the prostate spread to lymph nodes in distant areas? 4-Has the cancer in the prostate spread to the bones? 5-Has the cancer in the prostate spread to other organs? ChatGPT-4's responses were scored on a Likert-type scale for clarity and accuracy.

RESULTS: The mean scores for clarity were 4.93 ± 0.32, 4.95 ± 0.25, 4.96 ± 0.19, 4.99 ± 0.11, and 4.96 ± 0.30, respectively. The mean scores for accuracy were 4.87 ∓ 0.61, 4.87 ∓ 0.62, 4.79 ± 0.83, 4.96 ± 0.25, and 4.93 ± 0.45, respectively. Patients with distant lymphatic metastases had a lower mean accuracy score than those without (4.28 ± 1.45 vs. 4.94 ± 0.39; p < 0.001). ChatGPT-4's responses in 13 patients (8%) had the potential for harmful information.

CONCLUSION: ChatGPT-4 successfully interprets structured 68Ga PSMA PET/CT reports of reports of newly diagnosed prostate cancer patients. However, it is unlikely that ChatGPT-4 evaluations will replace physicians' evaluations today, especially since it can produce fabricated information.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Bülbül O, Bülbül HM, Kaba E, et al. Assessing ChatGPT's summarization of 68Ga PSMA PET/CT reports for patients. Abdom Radiol (NY). 2024. PMID: 39347975. doi:10.1007/s00261-024-04619-8

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。