GPT-4o辅助急诊头颈CTA报告重构:自动化与人工处理策略对比
单中心回顾性研究评估102份急诊头颈CTA报告,比较自动处理(AP)、人工修改(MM)及两种GPT-4o辅助报告(GPT-4o-A基于所见、GPT-4o-B基于所见和印象)的主观质量、临床可解释性、评分者间一致性和处理时间;GPT-4o-B总体质量最高但耗时较长,支持GPT-4o作为人在回路工具辅助急诊报告而非替代医师监督。
要点
- GPT-4o-B(基于所见和印象生成)在放射科医师感知准确性、完整性和文本质量上评分最高。
- AP报告处理时间最短(中位21.0秒),GPT-4o-A和GPT-4o-B耗时显著更长。
- GPT-4o需作为人在回路工具使用,不能替代医师监督。
核心结论
- GPT-4o-B提供最佳总体质量和高可解释性,但处理时间较长。
- GPT-4o-A更高效但不全面。
- 研究结果支持GPT-4o作为人在回路工具改善急诊报告,而非替代医师监督。
研究设计与样本
- 单中心回顾性研究,评估102份急诊头颈CTA报告,未评估诊断准确性或临床结局。
- 由3名放射科医师和3名急诊医师对每例四种报告类型进行5点Likert量表评分。
- 放射科医师评估感知准确性、感知完整性和感知文本质量;急诊医师评估可理解性和感知潜在危害。
- 评分者间一致性采用组内相关系数(ICC 2,1);报告类型差异采用Friedman检验和Wilcoxon事后检验(Holm校正)。
诊断标准与关键数值
- 放射科医师间一致性:感知准确性ICC=0.909,感知完整性ICC=0.927,感知文本质量ICC=0.875。
- 急诊医师间一致性:可理解性ICC=0.662(中等),感知潜在危害ICC=0.967(优秀)。
- 放射科医师评分:GPT-4o-B最高,感知准确性、完整性和文本质量均为5.0(IQR 5.0-5.0)。
- 放射科医师评分:AP最低,感知准确性2.0(1.0-2.0)、完整性2.0(1.0-2.0)、文本质量3.0(2.0-3.0)。
- 急诊医师评分:可理解性AP和GPT-4o-B最高,均为5.0(4.0-5.0);感知潜在危害MM最低1.0(1.0-1.0),AP最高3.0(2.0-3.0)。
临床应用与阅片要点
- GPT-4o-B适合需要高完整性和准确性的报告场景,但需注意处理时间较长。
- GPT-4o-A可用于时间敏感但全面性要求较低的场合。
- AP报告虽然快速但质量评分低,需谨慎使用。
局限性
- 单中心回顾性研究,样本量102份。
- 仅评估主观感知质量,未评估诊断准确性或临床结局。
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: To compare perceived quality, perceived clinical interpretability, interrater agreement, and processing time of four reporting strategies for emergency head-and-neck CT angiography (CTA): automated processing (AP) reports, manually modified (MM) reports, GPT-4o-A reports (generated from findings section of MM reports), and GPT-4o-B reports (generated from findings and impression sections).
METHODS: In this single-center retrospective study, we evaluated 102 emergency head-and-neck CTA reports using subjective Likert-scale ratings of perceived report quality - no assessment of diagnostic accuracy or clinical outcomes was performed. Four report types per case were evaluated by three radiologists and three emergency physicians. Radiologists rated perceived accuracy, perceived completeness, and perceived text quality; emergency physicians rated understandability and perceived potential harm on 5-point Likert scales. Interrater agreement was evaluated using the intraclass correlation coefficient (ICC 2,1). Differences among report types were analyzed with Friedman test and Wilcoxon post-hoc tests with Holm correction.
RESULTS: Radiologist agreement was high for perceived accuracy (ICC = 0.909), perceived completeness (0.927), and perceived text quality (0.875); whereas emergency physician agreement was moderate for understandability (0.662) and excellent for perceived potential harm (0.967). Report type significantly affected all outcomes (all P < 0.001). GPT-4o-B received the highest radiologist ratings for perceived accuracy, completeness, and text quality, all 5.0 (IQR, 5.0-5.0), whereas AP received the lowest ratings of 2.0 (1.0-2.0), 2.0 (1.0-2.0), and 3.0 (2.0-3.0), respectively. Among emergency physicians, understandability was highest for AP and GPT-4o-B, both 5.0 (4.0-5.0), while perceived potential harm was lowest for MM, 1.0 (1.0-1.0), and highest for AP, 3.0 (2.0-3.0). Processing time differed significantly (P < 0.001): AP 21.0 s (18.0-25.0), GPT-4o-A 271.5 s (198.0-336.0), MM 311.5 s (245.0-387.0), and GPT-4o-B 338.5 s (268.0-414.0).
CONCLUSION: GPT-4o-B provided the best overall quality and high interpretability, with longer processing time. GPT-4o-A was more efficient but less comprehensive. Findings support GPT-4o as a human-in-the-loop tool to improve emergency reporting, not replace physician oversight.
引用
- Qin F, Xu R, Zeng R, et al. GPT-4o-assisted restructuring of emergency head-and-neck computed tomography angiography reports: evaluation of automated vs. manual processing strategies. Neuroradiology. 2026. PMID: 42944916. doi:10.1007/s00234-026-04214-2
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。