Baker Peter O, Karim Shifa R, Smith Stephen W, Meyers H Pendell, Robinson Aaron E, Ibtida Ishmam, Karim Rehan M, Keller Gabriel A, Royce Kristie A, Puskarich Michael A
Department of Emergency Medicine, University of Minnesota Medical School, Minneapolis, Minnesota.
Baylor University, Waco, Texas.
Prehosp Emerg Care. 2025;29(3):218-226. doi: 10.1080/10903127.2024.2399218. Epub 2024 Sep 12.
Data suggest patients suffering acute coronary occlusion myocardial infarction (OMI) benefit from prompt primary percutaneous intervention (PPCI). Many emergency medical services (EMS) activate catheterization labs to reduce time to PPCI, but suffer a high burden of inappropriate activations. Artificial intelligence (AI) algorithms show promise to improve electrocardiogram (ECG) interpretation. The primary objective was to evaluate the potential of AI to reduce false positive activations without missing OMI.
Electrocardiograms were categorized by (1) STEMI criteria, (2) ECG integrated device software and (3) a proprietary AI algorithm (Queen of Hearts (QOH), Powerful Medical). If multiple ECGs were obtained and any one tracing was positive for a given method, that diagnostic method was considered positive. The primary outcome was OMI defined as an angiographic culprit lesion with either TIMI 0-2 flow; or TIMI 3 flow with either peak high sensitivity troponin- > 5000 ng/L or new wall motion abnormality. The primary analysis was per-patient proportion of false positives.
A total of 140 patients were screened and 117 met criteria. Of these, 48 met the primary outcome criteria of OMI. There were 80 positives by STEMI criteria, 88 by device algorithm, and 77 by AI software. All approaches reduced false positives, 27% for STEMI, 22% for device software, and 34% for AI ( < 0.01 for all). The reduction in false positives did not significantly differ between STEMI criteria and AI software ( = 0.19) but STEMI criteria missed 6 (5%) OMIs, while AI missed none ( = 0.01).
In this single-center retrospective study, an AI-driven algorithm reduced false positive diagnoses of OMI compared to EMS clinician gestalt. Compared to AI (which missed no OMI), STEMI criteria also reduced false positives but missed 6 true OMI. External validation of these findings in prospective cohorts is indicated.
数据表明，急性冠状动脉闭塞性心肌梗死（OMI）患者可从及时的直接经皮冠状动脉介入治疗（PPCI）中获益。许多紧急医疗服务（EMS）机构启动导管室以缩短PPCI时间，但存在较高的不适当启动负担。人工智能（AI）算法有望改善心电图（ECG）解读。主要目的是评估AI在减少假阳性启动且不遗漏OMI方面的潜力。
心电图按以下方式分类：（1）ST段抬高型心肌梗死（STEMI）标准、（2）ECG集成设备软件和（3）一种专有AI算法（红心女王（QOH），强大医疗公司）。如果获取了多份心电图且给定方法的任何一份描记图呈阳性，则该诊断方法被视为阳性。主要结局为OMI，定义为具有TIMI 0 - 2级血流的血管造影罪犯病变；或TIMI 3级血流且高峰高敏肌钙蛋白>5000 ng/L或新出现的室壁运动异常。主要分析为每位患者的假阳性比例。
共筛选了140例患者，117例符合标准。其中，48例符合OMI的主要结局标准。根据STEMI标准有80例阳性，根据设备算法有88例阳性，根据AI软件有77例阳性。所有方法均减少了假阳性，STEMI标准减少了27%，设备软件减少了22%，AI减少了34%（所有P均<0.01）。STEMI标准与AI软件之间假阳性减少率无显著差异（P = 0.19），但STEMI标准漏诊了6例（5%）OMI，而AI未漏诊（P = 0.01）。
在这项单中心回顾性研究中，与EMS临床医生的整体判断相比，一种AI驱动的算法减少了OMI的假阳性诊断。与AI（未漏诊任何OMI）相比，STEMI标准也减少了假阳性，但漏诊了6例假性OMI。这些结果需要在前瞻性队列中进行外部验证。
Zotero 插件