Shimizu Masato, Suzuki Makoto, Fujii Hiroyuki, Kimura Shigeki, Nishizaki Mitsuhiro, Sasano Tetsuo
Department of Cardiology, Yokohama Minami Kyosai Hospital, Yokohama, Japan.
Odawara Cardiovascular Hospital, Odawara, Japan.
Cardiovasc Digit Health J. 2022 Jul 16;3(4):179-188. doi: 10.1016/j.cvdhj.2022.07.001. eCollection 2022 Aug.
Qualitative differences in 12-lead electrocardiograms (ECG) at onset have been reported in patients with takotsubo syndrome (TTS) and acute anterior myocardial infarction (Ant-AMI). We aimed to distinguish these diseases by machine learning (ML) approach of microvolt-level quantitative measurements.
We enrolled 56 consecutive patients with sinus rhythm TTS (median age, 77 years; 16 men), and 1-to-1 random matching was performed based on age and sex of the patients. The ECG in the emergency room was evaluated using an automated system (ECAPs12c; Nihon-Koden). Statistical and ML predictive models for TTS were constructed using clinical features and ECG parameters.
Statistically significant differences were observed in 25 parameters; the V ST level at the J point (V STJ) showed the lowest value ( < .001). V STJ ≤+18 μV showed the highest accuracy for TTS (0.773). The highest area under the receiver operating characteristic curve (AUROC) was shown in the aVR ST level at 1/16th of the preceding R-R interval after the J point (aVR STmid: 0.727). Conversely, the light gradient boosting machine (model_LGBM) and extra tree classifier (model_ET) indicated higher accuracy (model_LGBM: 0.842, model_ET: 0.831) and AUROC (model_LGBM: 0.868, model_ET 0.896) than other statistical models. V STJ had high feature importance and Shapley additive explanation values in the 2 ML models.
ML applied to automated microvolt-level ECG measurements showed the possibility of distinguishing between TTS and Ant-AMI, which may be a clinically useful ECG-based discriminator.
据报道，在应激性心肌病（TTS）和急性前壁心肌梗死（Ant-AMI）患者发病时，12导联心电图（ECG）存在质的差异。我们旨在通过微伏级定量测量的机器学习（ML）方法区分这些疾病。
我们纳入了56例连续的窦性心律TTS患者（中位年龄77岁；16名男性），并根据患者的年龄和性别进行1:1随机匹配。使用自动系统（ECAPs12c；日本光电）评估急诊室的心电图。利用临床特征和心电图参数构建TTS的统计和ML预测模型。
观察到25个参数存在统计学显著差异；J点处的V ST水平（V STJ）显示出最低值（<0.001）。V STJ≤+18 μV对TTS的诊断准确性最高（0.773）。在J点后前一个R-R间期的1/16处的aVR ST水平显示出最高的受试者工作特征曲线下面积（AUROC）（aVR STmid：0.727）。相反，轻梯度提升机（model_LGBM）和极端随机树分类器（model_ET）显示出比其他统计模型更高的准确性（model_LGBM：0.842，model_ET：0.831）和AUROC（model_LGBM：0.868，model_ET 0.896）。V STJ在这2个ML模型中具有较高的特征重要性和Shapley值。
将ML应用于自动微伏级心电图测量显示出区分TTS和Ant-AMI的可能性，这可能是一种基于心电图的临床有用鉴别方法。
