解释方式重要吗?不同类型的人工智能解释对胸部X线诊断表现及医生对人工智能信任的影响存在差异
该多中心前瞻性随机研究于2022年4月至9月纳入220名医生(放射科医生及内科/急诊科医生),测试局部(基于特征)与全局(基于原型)两种AI解释类型及AI建议正确性和置信度对胸部X线诊断表现、AI建议有用性感知及信任的影响。结果显示局部解释在AI建议正确时诊断准确率更高(β=0.86,Padj<.001),并整体提高诊断效率(β=-0.19,Padj=.01);医生对局部解释的简单信任更高(β=1.32,Padj=.048),但解释类型或置信度未显著影响主观测量。
要点
- 局部AI解释在建议正确时诊断准确率优于全局解释(β=0.86,Padj<.001)。
- 局部解释整体缩短考虑AI建议的时间,提高诊断效率(β=-0.19,Padj=.01)。
- 无论AI建议正确与否,医生对局部解释的简单信任均高于全局解释(β=1.32,Padj=.048)。
核心结论
- AI解释类型影响医生的诊断表现和对AI的信任,即使医生自身未意识到这种影响。
研究设计与样本
- 多中心前瞻性随机研究,2022年4月至2022年9月进行,纳入220名医生(中位年龄30岁,IQR 28-32.75岁;146名男性),AI解释类型为组间因素,AI正确性和置信度为组内因素,使用广义线性混合效应模型分析,Holm-Sidak校正多重比较。
关键影像表现/征象
- AI建议正确时,局部解释组诊断准确率优于全局解释组(β=0.86,Padj<.001)。
- 局部解释整体减少考虑AI建议的时间,提高诊断效率(β=-0.19,Padj=.01)。
- 解释类型、AI置信度与医生任务专长对诊断准确率存在交互效应(β=-1.05,Padj=.04)。
诊断标准与关键数值
- 局部解释在AI建议正确时诊断准确率优于全局解释(β=0.86,Padj<.001)。
- 局部解释整体提高诊断效率(β=-0.19,Padj=.01)。
- 诊断准确率存在解释类型×AI置信度×任务专长的交互效应(β=-1.05,Padj=.04)。
- 对局部解释的简单信任高于全局解释(β=1.32,Padj=.048)。
临床应用与阅片要点
- 放射科医生(任务专家)与内科/急诊科医生(任务非专家)在AI辅助下阅读胸部X线时,局部解释可能提高诊断准确率(原文显示β=0.86,Padj<.001,限于AI建议正确时)。
- 局部解释可能缩短考虑AI建议的时间(β=-0.19,Padj=.01),有助于提高诊断效率。
- 无论AI建议正确与否,医生对局部解释的简单信任均高于全局解释(β=1.32,Padj=.048)。
- AI解释类型和置信度未显著影响医生诊断信心及对AI有用性的感知(原文报告无显著影响证据)。
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
Background It is unclear whether artificial intelligence (AI) explanations help or hurt radiologists and other physicians in AI-assisted radiologic diagnostic decision-making. Purpose To test whether the type of AI explanation and the correctness and confidence level of AI advice impact physician diagnostic performance, perception of AI advice usefulness, and trust in AI advice for chest radiograph diagnosis. Materials and Methods A multicenter, prospective randomized study was conducted from April 2022 to September 2022. Two types of AI explanations prevalent in medical imaging-local (feature-based) explanations and global (prototype-based) explanations-were a between-participant factor, while AI correctness and confidence were within-participant factors. Radiologists (task experts) and internal or emergency medicine physicians (task nonexperts) received a chest radiograph to read; then, simulated AI advice was presented. Generalized linear mixed-effects models were used to analyze the effects of the experimental variables on diagnostic accuracy, efficiency, physician perception of AI usefulness, and "simple trust" (ie, speed of alignment with or divergence from AI advice); the control variables included knowledge of AI, demographic characteristics, and task expertise. Holm-Sidak corrections were used to adjust for multiple comparisons. Results Data from 220 physicians (median age, 30 years [IQR, 28-32.75 years]; 146 male participants) were analyzed. Compared with global AI explanations, local AI explanations yielded better physician diagnostic accuracy when the AI advice was correct (β = 0.86; P value adjusted for multiple comparisons [Padj] < .001) and increased diagnostic efficiency overall by reducing the time spent considering AI advice (β = -0.19; Padj = .01). While there were interaction effects of explanation type, AI confidence level, and physician task expertise on diagnostic accuracy (β = -1.05; Padj = .04), there was no evidence that AI explanation type or AI confidence level significantly affected subjective measures (physician diagnostic confidence and perception of AI usefulness). Finally, radiologists and nonradiologists placed greater simple trust in local AI explanations than in global explanations, regardless of the correctness of the AI advice (β = 1.32; Padj = .048). Conclusion The type of AI explanation impacted physician diagnostic performance and trust in AI, even when physicians themselves were not aware of such effects. © RSNA, 2024 Supplemental material is available for this article.
引用
- Prinster D, Mahmood A, Saria S, et al. Care to Explain? AI Explanation Types Differentially Impact Chest Radiograph Diagnostic Performance and Physician Trust in AI. Radiology. 2024. PMID: 39560483. doi:10.1148/radiol.233261
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。