Section of Pacing and Electrophysiology, Division of Cardiology, First Affiliated Hospital of Nanjing Medical University, Guangzhou Road 300, Nanjing, 210006, Jiangsu, China.
Department of Cardiology, Nanjing BenQ Medical Center, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing, 210021, Jiangsu, China.
J Interv Card Electrophysiol. 2024 Sep;67(6):1391-1398. doi: 10.1007/s10840-024-01743-9. Epub 2024 Jan 22.
Differential diagnosis of wide QRS tachycardia (WQCT) has been a challenging issue. Published algorithms to distinguish ventricular tachycardia (VT) and supraventricular tachycardia (SVT) have limited diagnostic capabilities.
A total of 278 patients with WQCT from January 2010 to March 2022 were enrolled. The electrophysiological study confirmed SVT in 154 patients and VT in 65 ones. Two hundred nineteen WQCT 12-lead ECGs were randomly divided into development cohort (n = 165) and testing cohort (n = 54) data sets. The development cohort was split into a training group (n = 115) and an internal validation group (n = 50). Forty ECG features extracted from the 219 WQCT ECGs are fed into 9 iteratively trained ML algorithms. This novel ML algorithm was also compared with four published algorithms.
In the development cohort, the Gradient Boosting Machine (GBM) model displayed the maximum area under curve (AUC) (0.91, 95% confidence interval (CI) 0.81-1.00). In the testing cohort, the GBM model had a higher AUC of 0.97 compared to 4 validated ECG algorithms, namely, Brugada (0.68), avR (0.62), RWPTII (0.72), and LLA algorithms (0.70). Accuracy, sensitivity, specificity, negative predictive value, and positive predictive value of the GBM model were 0.94, 0.97, 0.90, 0.94, and 0.95, respectively.
A GBM ML model contributes to distinguishing SVT from VT based on surface ECG features. In addition, we were able to identify important indicators for distinguishing WQCT.
宽 QRS 心动过速（WQCT）的鉴别诊断一直是一个具有挑战性的问题。已发表的区分室性心动过速（VT）和室上性心动过速（SVT）的算法具有有限的诊断能力。
共纳入 2010 年 1 月至 2022 年 3 月期间 278 例 WQCT 患者。电生理研究证实 154 例患者为 SVT，65 例患者为 VT。将 219 例 WQCT 12 导联心电图随机分为发展队列（n=165）和测试队列（n=54）数据集。发展队列分为训练组（n=115）和内部验证组（n=50）。从 219 例 WQCT 心电图中提取 40 个心电图特征，并输入 9 个迭代训练的 ML 算法。该新型 ML 算法还与四个已发表的算法进行了比较。
在发展队列中，梯度提升机（GBM）模型显示出最大的曲线下面积（AUC）（0.91，95%置信区间（CI）0.81-1.00）。在测试队列中，GBM 模型的 AUC 为 0.97，高于 4 个经过验证的心电图算法，即 Brugada（0.68）、avR（0.62）、RWPTII（0.72）和 LLA 算法（0.70）。GBM 模型的准确率、灵敏度、特异性、阴性预测值和阳性预测值分别为 0.94、0.97、0.90、0.94 和 0.95。
GBM ML 模型有助于根据体表心电图特征区分 SVT 和 VT。此外，我们能够识别区分 WQCT 的重要指标。
