Department of Emergency Medicine, Ajou University School of Medicine, 206, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do 16499, Republic of Korea.
Department of Emergency Medicine, Ajou University School of Medicine, 206, World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do 16499, Republic of Korea.
Int J Cardiol. 2022 Sep 15;363:6-10. doi: 10.1016/j.ijcard.2022.06.012. Epub 2022 Jun 9.
Smartphone-based ECG analyzer using camera input can be useful as everyone have it. The purpose of this study was to evaluate whether such a system can outperform clinicians in detecting ST-elevation myocardial infarction (STEMI) regardless of image acquisition conditions.
We retrospectively enrolled suspected STEMI patients in an emergency department from January to October 2021. A multifaceted cardiovascular assessment system (Quantitative ECG, QCG™) using ECG images to produce a quantitative score (QCG score, ranging from 0 to 100) was compared to human experts of 7 emergency physicians and 3 cardiologists. Voting scores (number of participants answering "yes" for STEMI) were calculated for comparison. The system's robustness was evaluated using an equivalence test where we prove its performance metric (area under the curve of the receiver operating characteristic curve, AUC-ROC) changes within a predetermined equivalence range (-0.01 to 0.01) in 6 different environments (A combination of three different smartphones and two image sources including computer screen and paper).
187 patients (96 STEMI, 51.3%) were analyzed. AUC-ROC of QCG score was 0.919 (0.880-0.957). AUC-ROCs of voting scores, 0.856 (0.799-0.913) for all clinicians, 0.843 (0.786-0.900) for emergency physicians, 0.817 (0.756-0.877) for cardiologists, and 0.848 (0.790-0.905) for high-performance group were significantly lower compared to that of QCG score. The change in AUC-ROC by image acquisition condition was negligible with a narrow confidence interval within -0.01 to 0.01 confirming the equivalence.
Image-based AI system can outperform clinicians in STEMI diagnosis and its performance was robust to change in image acquisition conditions.
基于智能手机的心电图分析器可以利用摄像头输入，这对每个人来说都很有用。本研究旨在评估该系统是否能够在不考虑图像采集条件的情况下，在检测 ST 段抬高型心肌梗死（STEMI）方面优于临床医生。
我们回顾性纳入了 2021 年 1 月至 10 月期间在急诊科就诊的疑似 STEMI 患者。使用心电图图像生成定量评分（QCG 评分，范围为 0 至 100）的多方面心血管评估系统（定量心电图，QCG ™）与 7 名急诊医生和 3 名心脏病专家的人类专家进行了比较。计算了投票评分（回答“是”的参与者人数）进行比较。通过等效性检验评估系统的稳健性，即在 6 种不同环境下（三种不同智能手机的组合和包括计算机屏幕和纸张在内的两种图像源），证明其性能指标（曲线下的面积，ROC 曲线，AUC-ROC）在预定的等效范围内（0.01 到 0.01）变化。
共分析了 187 例患者（96 例 STEMI，51.3%）。QCG 评分的 AUC-ROC 为 0.919（0.880-0.957）。所有临床医生的投票评分 AUC-ROC 为 0.856（0.799-0.913），急诊医生为 0.843（0.786-0.900），心脏病专家为 0.817（0.756-0.877），高绩效组为 0.848（0.790-0.905），均显著低于 QCG 评分。AUC-ROC 随图像采集条件的变化可忽略不计，置信区间狭窄，在 -0.01 到 0.01 之间，证实等效性。
基于图像的人工智能系统在 STEMI 诊断方面可以优于临床医生，其性能对图像采集条件的变化具有稳健性。
