Pulmonary/Critical Care, University of Arizona College of Medicine Phoenix, Phoenix, AZ, USA.
Internal Medicine, University of Arizona College of Medicine Phoenix, Phoenix, AZ, USA.
J Investig Med. 2024 Oct;72(7):652-660. doi: 10.1177/10815589241258968. Epub 2024 Jul 31.
Multidisciplinary pulmonary embolism response teams (PERTs) have shown that timely triage expedites treatment. The use of artificial intelligence (AI) may help improve pulmonary embolism (PE) management with early CT pulmonary angiogram (CTPA) screening and accelerate PERT coordination. This study aimed to test the clinical validity of an FDA-approved PE AI algorithm. CTPA scan data of 200 patients referred due to automated AI detection of suspected PE were retrospectively reviewed. In our institution, all patients suspected of PE received a CTPA. The AI app was then used to analyze CTPA for the presence of PE and calculate the right-ventricle/left-ventricle (RV/LV) ratio. We compared the AI's output with the radiologists' report. Inclusion criteria included segmental PE with and without RV dysfunction and high-risk PE. The primary endpoint was false positive rate. Secondary end points included clinical outcomes according to the therapy selected, including catheter-directed interventions, systemic thrombolytics, and anticoagulation. Fifty-seven of 200 exams (28.5%) were correctly identified as positive for PE by the algorithm. A total of 143 exams (71.5%) were incorrectly reported as positive. In 8% of cases, PERT was consulted. Four patients (7%) received systemic thrombolytics without any complications. There were six patients (10.5%) who developed high-risk PE and underwent thrombectomy, one of whom died. Among 46 patients with acute PE without right heart strain, 44 (95%) survived. The false positive rate of our AI algorithm was 71.5%, higher than what was reported in the AI's prior clinical validity study (91% sensitivity, 100% specificity). A high rate of discordant AI auto-detection of suspected PE raises concerns about its diagnostic accuracy. This can lead to increased workloads for PERT consultants, alarm/notification fatigue, and automation bias. The AI direct notification process to the PERT team did not improve PERT triage efficacy.
多学科肺栓塞反应团队 (PERT) 已表明，及时分诊可加快治疗速度。人工智能 (AI) 的使用可能有助于通过早期 CT 肺动脉造影 (CTPA) 筛查来改善肺栓塞 (PE) 的管理，并加速 PERT 的协调。本研究旨在测试一种获得 FDA 批准的 PE AI 算法的临床有效性。回顾性分析了因自动化 AI 检测疑似 PE 而转诊的 200 例患者的 CTPA 扫描数据。在我们的机构中，所有疑似 PE 的患者均接受 CTPA 检查。然后，AI 应用程序用于分析 CTPA 以确定是否存在 PE，并计算右心室/左心室 (RV/LV) 比值。我们将 AI 的输出与放射科医生的报告进行了比较。纳入标准包括有和无 RV 功能障碍的节段性 PE 和高危 PE。主要终点是假阳性率。次要终点包括根据所选治疗方法的临床结果，包括导管定向介入、全身溶栓和抗凝治疗。该算法正确识别 200 次检查中的 57 次（28.5%）为 PE 阳性。共有 143 次检查（71.5%）被错误报告为阳性。在 8%的情况下，PERT 被咨询。有 4 名患者（7%）接受了全身溶栓治疗，没有任何并发症。有 6 名患者（10.5%）发展为高危 PE 并接受了血栓切除术，其中 1 名患者死亡。在 46 例无右心压应变的急性 PE 患者中，有 44 例（95%）存活。我们的 AI 算法的假阳性率为 71.5%，高于其之前的临床有效性研究报告的假阳性率（91%的敏感性，100%的特异性）。高度不一致的 AI 自动检测疑似 PE 引起了人们对其诊断准确性的担忧。这可能导致 PERT 顾问的工作量增加、报警/通知疲劳和自动化偏见。AI 直接向 PERT 团队发出通知的过程并没有提高 PERT 的分诊效果。
Zotero 插件