Objective 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. Design Prospective multi-reader diagnostic accuracy study. Setting United Kingdom. Participants One artificial intelligence candidate (Smarturgences, Milvue) and 26 radiologists who had passed the FRCR examination in the preceding 12 months. Main outcome measures 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). Results 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. Conclusions 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.” The data are not publicly available. Requests for the anonymised imaging dataset will be considered and should be sent to the corresponding author at susan.shelmerdine@gosh.nhs.uk.

中文翻译：

---

人工智能能否通过皇家放射科学院院士考试？多阅读器诊断准确性研究

目的 确定人工智能候选人是否可以通过皇家放射科学院院士 (FRCR) 考试的快速（射线照相）报告部分。设计前瞻性多读者诊断准确性研究。设置英国。参与者 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。主要结果衡量人工智能与放射科医生在 10 次模拟 FRCR 快速报告检查（每次检查包含 30 张射线照片，需要 90% 的准确率通过）中的准确性和通过率。结果 当不可解释的图像被排除在分析之外时，人工智能候选人的平均总体准确率为 79.5%（95% 置信区间 74. 1% 到 84.3%）并通过了 10 次模拟 FRCR 考试中的两次。普通放射科医生的平均准确率为 84.8% (76.1-91.9%)，并通过了 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%），而所有放射科医师的汇总估计为 84.1%（81.0% 至 87.0%） ) 和 87.3%（85.0% 至 89.3%）。在超过 90% 的放射科医生正确解读的 148/300 张射线照片中，人工智能候选者有 14/148 (9%) 个是不正确的。在大多数 (>50%) 放射科医生错误解读的 20/300 张射线照片中，人工智能候选者在 10/20 (50%) 中是正确的。大多数成像缺陷与肌肉骨骼而非胸片的解释有关。结论 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。人工智能候选者有可能通过关注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射线照片来提高其射线照相解释技能。数据不公开。对匿名成像数据集的请求将被考虑，并应发送给相应的作者 susan.shelmerdine@gosh.nhs.uk。人工智能候选人能够通过 10 次模拟考试中的两次。人工智能候选者有可能通过关注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射线照片来提高其射线照相解释技能。数据不公开。对匿名成像数据集的请求将被考虑，并应发送给相应的作者 susan.shelmerdine@gosh.nhs.uk。人工智能候选人能够通过 10 次模拟考试中的两次。人工智能候选者有可能通过关注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射线照片来提高其射线照相解释技能。数据不公开。对匿名成像数据集的请求将被考虑，并应发送给相应的作者 susan.shelmerdine@gosh.nhs.uk。