Can artificial intelligence pass the Fellowship of the Royal College of Radiologists examination? Multi-reader diagnostic accuracy study.
Can artificial intelligence pass the Fellowship of the Royal College of Radiologists examination? Multi-reader diagnostic accuracy study.
复制标题
DOI：
10.1136/bmj-2022-072826
复制
发表时间：
2022-12-21
影响因子：
105.7
通讯作者：
Weir-McCall, Jonathan Richard
中科院分区：
文献类型：
--
作者：
Shelmerdine, Susan Cheng;Martin, Helena;Shirodhar, Kapil;Shamshuddin, Sameer;Weir-McCall, Jonathan Richard
确定人工智能候选人是否可以通过皇家放射科医师学会（FRCR）考试的快速（放射）报告部分。前瞻性多读卡器诊断准确性研究。联合王国。一名人工智能候选人（Smarturgences, Milvue）和26名在过去12个月内通过FRCR考试的放射科医生。人工智能与放射科医师在10次模拟FRCR快速报告检查中的准确率和通过率比较（每次检查包含30张x线片，准确率要求90%通过）。当从分析中排除不可解释的图像时，人工智能候选人的平均总体准确率为79.5%(95%置信区间为74.1%至84.3%)，并通过了10次模拟FRCR考试中的两次。放射科医生的平均准确率为84.8%(76.1-91.9%)，通过了10次模拟考试中的4次。人工智能的敏感性为83.6%(95%置信区间为76.2%至89.4%)，特异性为75.2%(66.7%至82.5%)，而所有放射科医生的综合估计为84.1%（81.0%至87.0%）和87.3%（85.0%至89.3%）。在148/300张x光片中，90%的放射科医生正确解读的x光片中，人工智能候选人在14/148（9%）中是错误的。在20/300张放射科医生解释错误的x光片中，人工智能候选人在10/20（50%）中是正确的。大多数成像缺陷与肌肉骨骼片的解释有关，而不是胸片。当为人工智能候选人提供特殊豁免（即排除不可解释的图像）时，人工智能候选人能够通过10次模拟考试中的两次。人工智能候选人有可能通过专注于肌肉骨骼病例和学习解释目前被认为“不可解释”的轴向骨骼和腹部的x光片来提高其x光片解释技能。
To determine whether an artificial intelligence candidate could pass the rapid (radiographic) reporting component of the Fellowship of the Royal College of Radiologists (FRCR) examination. Prospective multi-reader diagnostic accuracy study. United Kingdom. One artificial intelligence candidate (Smarturgences, Milvue) and 26 radiologists who had passed the FRCR examination in the preceding 12 months. Accuracy and pass rate of the artificial intelligence compared with radiologists across 10 mock FRCR rapid reporting examinations (each examination containing 30 radiographs, requiring 90% accuracy rate to pass). When non-interpretable images were excluded from the analysis, the artificial intelligence candidate achieved an average overall accuracy of 79.5% (95% confidence interval 74.1% to 84.3%) and passed two of 10 mock FRCR examinations. The average radiologist achieved an average accuracy of 84.8% (76.1-91.9%) and passed four of 10 mock examinations. The sensitivity for the artificial intelligence was 83.6% (95% confidence interval 76.2% to 89.4%) and the specificity was 75.2% (66.7% to 82.5%), compared with summary estimates across all radiologists of 84.1% (81.0% to 87.0%) and 87.3% (85.0% to 89.3%). Across 148/300 radiographs that were correctly interpreted by >90% of radiologists, the artificial intelligence candidate was incorrect in 14/148 (9%). In 20/300 radiographs that most (>50%) radiologists interpreted incorrectly, the artificial intelligence candidate was correct in 10/20 (50%). Most imaging pitfalls related to interpretation of musculoskeletal rather than chest radiographs. When special dispensation for the artificial intelligence candidate was provided (that is, exclusion of non-interpretable images), the artificial intelligence candidate was able to pass two of 10 mock examinations. Potential exists for the artificial intelligence candidate to improve its radiographic interpretation skills by focusing on musculoskeletal cases and learning to interpret radiographs of the axial skeleton and abdomen that are currently considered “non-interpretable.”
登录
查看更多内容
影响因子：
5.9
作者：
Savadjiev, Peter;Chong, Jaron;Gallix, Benoit
通讯作者：
Gallix, Benoit
影响因子：
15.2
作者：
Aggarwal R;Sounderajah V;Martin G;Ting DSW;Karthikesalingam A;King D;Ashrafian H;Darzi A
通讯作者：
Darzi A
影响因子：
2.3
作者：
通讯作者：
--
影响因子：
5.8
作者：
Bates, Douglas;Maechler, Martin;Walker, Steven C.
通讯作者：
Walker, Steven C.
影响因子：
30.8
作者：
Seah, Jarrel C. Y.;Tang, Cyril H. M.;Jones, Catherine M.
通讯作者：
Jones, Catherine M.