使用ChatGPT将自由文本放射学报告转换为结构化报告:一项甲状腺超声研究
回顾性研究纳入136例患者的136份甲状腺超声报告共184个结节,评估ChatGPT-3.5与ChatGPT-4.0按ACR-TIRADS生成结构化报告的准确性。ChatGPT-3.5满意结构化报告202份(74.3%)优于ChatGPT-4.0的69份(25.4%),而ChatGPT-4.0结节分类准确率69.3%优于ChatGPT-3.5的34.5%,管理建议更全面正确且结节分类一致性更高。
要点
- ChatGPT-4.0结节分类准确率69.3%,高于ChatGPT-3.5的34.5%。
- ChatGPT-3.5满意结构化报告74.3%,高于ChatGPT-4.0的25.4%。
- ChatGPT-4.0结节分类ICC=0.732,高于ChatGPT-3.5的ICC=0.429。
核心结论
- ChatGPT可将自由文本甲状腺超声报告转换为结构化格式,ChatGPT-3.5擅长生成结构化报告,ChatGPT-4.0在结节分类和管理建议准确性上更优。
研究设计与样本
- 回顾性研究,纳入136例患者的136份甲状腺超声报告共184个结节,使用ChatGPT-3.5和ChatGPT-4.0基于ACR-TIRADS指南生成结构化报告,由两名放射科医师评估。
诊断标准与关键数值
- 以ACR-TIRADS指南为结构化依据,ChatGPT-3.5满意结构化报告74.3% vs ChatGPT-4.0 25.4%(OR=8.490,95%CI:5.775-12.481,p<0.001)。
临床应用与阅片要点
- ChatGPT-4.0结节分类准确率69.3% vs ChatGPT-3.5 34.5%(OR=4.282,95%CI:3.145-5.831,p<0.001),管理建议更全面或正确(OR=1.791,95%CI:1.297-2.473,p<0.001)。
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: The importance of structured radiology reports has been fully recognized, as they facilitate efficient data extraction and promote collaboration among healthcare professionals. Our purpose is to assess the accuracy and reproducibility of ChatGPT, a large language model, in generating structured thyroid ultrasound reports.
METHODS: This is a retrospective study that includes 184 nodules in 136 thyroid ultrasound reports from 136 patients. ChatGPT-3.5 and ChatGPT-4.0 were used to structure the reports based on ACR-TIRADS guidelines. Two radiologists evaluated the responses for quality, nodule categorization accuracy, and management recommendations. Each text was submitted twice to assess the consistency of the nodule classification and management recommendations.
RESULTS: On 136 ultrasound reports from 136 patients (mean age, 52 years ± 12 [SD]; 61 male), ChatGPT-3.5 generated 202 satisfactory structured reports, while ChatGPT-4.0 only produced 69 satisfactory structured reports (74.3 % vs. 25.4 %, odds ratio (OR) = 8.490, 95 %CI: 5.775-12.481, p < 0.001). ChatGPT-4.0 outperformed ChatGPT-3.5 in categorizing thyroid nodules, with an accuracy of 69.3 % compared to 34.5 % (OR = 4.282, 95 %CI: 3.145-5.831, p < 0.001). ChatGPT-4.0 also provided more comprehensive or correct management recommendations than ChatGPT-3.5 (OR = 1.791, 95 %CI: 1.297-2.473, p < 0.001). Finally, ChatGPT-4.0 exhibits higher consistency in categorizing nodules compared to ChatGPT-3.5 (ICC = 0.732 vs. ICC = 0.429), and both exhibited moderate consistency in management recommendations (ICC = 0.549 vs ICC = 0.575).
CONCLUSIONS: Our study demonstrates the potential of ChatGPT in transforming free-text thyroid ultrasound reports into structured formats. ChatGPT-3.5 excels in generating structured reports, while ChatGPT-4.0 shows superior accuracy in nodule categorization and management recommendations.
引用
- Jiang H, Xia S, Yang Y, et al. Transforming free-text radiology reports into structured reports using ChatGPT: A study on thyroid ultrasonography. Eur J Radiol. 2024. PMID: 38613868. doi:10.1016/j.ejrad.2024.111458
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。