From the Department of Radiology, University of Alabama at Birmingham, 619 S 19th St, Birmingham, AL 35233.
Radiology. 2023 Oct;309(1):e230702. doi: 10.1148/radiol.230702.
Background Artificial intelligence (AI) algorithms have shown high accuracy for detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) studies in academic studies. Purpose To determine whether use of an AI triage system to detect PE on CTPA studies improves radiologist performance or examination and report turnaround times in a clinical setting. Materials and Methods This prospective single-center study included adult participants who underwent CTPA for suspected PE in a clinical practice setting. Consecutive CTPA studies were evaluated in two phases, first by radiologists alone ( = 31) (May 2021 to June 2021) and then by radiologists aided by a commercially available AI triage system ( = 37) (September 2021 to December 2021). Sixty-two percent of radiologists (26 of 42 radiologists) interpreted studies in both phases. The reference standard was determined by an independent re-review of studies by thoracic radiologists and was used to calculate performance metrics. Diagnostic accuracy and turnaround times were compared using Pearson χ and Wilcoxon rank sum tests. Results Phases 1 and 2 included 503 studies (participant mean age, 54.0 years ± 17.8 [SD]; 275 female, 228 male) and 1023 studies (participant mean age, 55.1 years ± 17.5; 583 female, 440 male), respectively. In phases 1 and 2, 14.5% (73 of 503) and 15.9% (163 of 1023) of CTPA studies were positive for PE ( = .47). Mean wait time for positive PE studies decreased from 21.5 minutes without AI to 11.3 minutes with AI ( < .001). The accuracy and miss rate, respectively, for radiologist detection of any PE on CTPA studies was 97.6% and 12.3% without AI and 98.6% and 6.1% with AI, which was not significantly different ( = .15 and = .11, respectively). Conclusion The use of an AI triage system to detect any PE on CTPA studies improved wait times but did not improve radiologist accuracy, miss rate, or examination and report turnaround times. © RSNA, 2023 See also the editorial by Murphy and Tee in this issue.
背景 人工智能 (AI) 算法在学术研究中对 CT 肺动脉造影 (CTPA) 研究中肺栓塞 (PE) 的检测表现出了很高的准确性。目的 确定在临床环境中使用 AI 分诊系统检测 CTPA 研究中的 PE 是否可以提高放射科医生的表现或检查和报告周转时间。材料与方法 本前瞻性单中心研究纳入了在临床实践环境中因疑似 PE 而行 CTPA 的成年参与者。连续的 CTPA 研究分两个阶段进行评估,首先由放射科医生单独评估 ( = 31) (2021 年 5 月至 6 月),然后由放射科医生使用商业上可用的 AI 分诊系统辅助评估 ( = 37) (2021 年 9 月至 12 月)。62%的放射科医生 (42 名放射科医生中的 26 名)在两个阶段都对研究进行了评估。参考标准是由胸部放射科医生独立重新审查研究来确定的,并用于计算性能指标。使用 Pearson χ 和 Wilcoxon 秩和检验比较诊断准确性和周转时间。结果 第 1 阶段和第 2 阶段分别包括 503 项研究 (参与者平均年龄,54.0 岁 ± 17.8 [SD];275 名女性,228 名男性) 和 1023 项研究 (参与者平均年龄,55.1 岁 ± 17.5;583 名女性,440 名男性)。在第 1 阶段和第 2 阶段,503 项 CTPA 研究中有 14.5% (73/503) 和 1023 项 CTPA 研究中有 15.9% (163/1023) 为 PE 阳性 (=.47)。阳性 PE 研究的平均等待时间从无 AI 时的 21.5 分钟降至有 AI 时的 11.3 分钟 ( <.001)。放射科医生在 CTPA 研究中检测到任何 PE 的准确率和漏诊率分别为 97.6%和 12.3%,无 AI 时为 98.6%和 6.1%,有 AI 时为 98.6%和 6.1%,差异无统计学意义 (=.15 和 =.11,分别)。结论 使用 AI 分诊系统检测 CTPA 研究中的任何 PE 均可缩短等待时间,但并未提高放射科医生的准确性、漏诊率或检查和报告周转时间。 © 2023 RSNA