指南与共识乳腺

ChatGPT 提供的急性乳腺症状建议的适宜性

Appropriateness of acute breast symptom recommendations provided by ChatGPT.
指南 / 共识 · Clin Imaging · 2025-06-16

本研究评估 ChatGPT-3.5 对急性乳腺症状常见问题的回答准确性,并探讨使用通俗语言与医学术语是否影响回答准确性。问题依据美国放射学会适宜性标准(ACR AC)及三级转诊乳腺中心临床经验制定,由五位乳腺放射学专科培训医师评估。结果显示,常见急性乳腺症状问题在通俗与医学术语表述下均为 7/7(100%)适宜,而妊娠相关乳腺症状问题仅 3/9(33%)适宜,可触及乳腺异常处理及影像推荐问题 3/4(75%)适宜。

要点

  • ChatGPT-3.5 对常见急性乳腺症状问题的回答在通俗与医学术语表述下均 7/7(100%)适宜。
  • 妊娠相关乳腺症状问题仅 3/9(33%)回答适宜。
  • 可触及乳腺异常处理及影像推荐问题 3/4(75%)回答适宜。

核心结论

  • ChatGPT-3.5 可在医学术语或通俗表述下自动生成急性乳腺症状适当处理的相关医疗信息,但鉴于妊娠相关乳腺症状及可触及异常处理存在不适当建议,医师监督仍至关重要。

诊断标准与关键数值

  • 评估标准包括临床判断及对 ACR 指南的依从性,回答评分为:1)适宜;2)不适宜(任何回答包含不适当信息);3)不可靠(回答不一致);以多数票决定每个问题的适宜性。

临床应用与阅片要点

  • 作者指出,鉴于妊娠相关乳腺症状及可触及异常处理存在不适当建议,医师监督仍至关重要。

局限性

  • 原文未报告局限性。

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: We evaluated the accuracy of ChatGPT-3.5's responses to common questions regarding acute breast symptoms and explored whether using lay language, as opposed to medical language, affected the accuracy of the responses.

METHODS: Questions were formulated addressing acute breast conditions, informed by the American College of Radiology (ACR) Appropriateness Criteria (AC) and our clinical experience at a tertiary referral breast center. Of these, seven addressed the most common acute breast symptoms, nine addressed pregnancy-associated breast symptoms, and four addressed specific management and imaging recommendations for a palpable breast abnormality. Questions were submitted three times to ChatGPT-3.5 and all responses were assessed by five fellowship-trained breast radiologists. Evaluation criteria included clinical judgment and adherence to the ACR guidelines, with responses scored as: 1) "appropriate," 2) "inappropriate" if any response contained inappropriate information, or 3) "unreliable" if responses were inconsistent. A majority vote determined the appropriateness for each question.

RESULTS: ChatGPT-3.5 generated responses were appropriate for 7/7 (100 %) questions regarding common acute breast symptoms when phrased both colloquially and using standard medical terminology. In contrast, ChatGPT-3.5 generated responses were appropriate for 3/9 (33 %) questions about pregnancy-associated breast symptoms and 3/4 (75 %) questions about management and imaging recommendations for a palpable breast abnormality.

CONCLUSION: ChatGPT-3.5 can automate healthcare information related to appropriate management of acute breast symptoms when prompted with both standard medical terminology or lay phrasing of the questions. However, physician oversight remains critical given the presence of inappropriate recommendations for pregnancy associated breast symptoms and management of palpable abnormalities.

来源:Clin Imaging,查看原文。版权归原作者所有。

引用

  1. Byrd C, Kingsbury C, Niell B, et al. Appropriateness of acute breast symptom recommendations provided by ChatGPT. Clin Imaging. 2025. PMID: 40540768. doi:10.1016/j.clinimag.2025.110549

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。