Department of Medicine, Division of Cardiovascular Diseases, Washington University School of Medicine in St. Louis, MO (S.L.C., K.M.M., S.S.S., P.S.C., R.G., D.H.C., T.M.M., A.M.M.).
Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN (A.H.K., A.J.D., S.J.A., C.V.D., P.A.N.).
Circ Arrhythm Electrophysiol. 2024 Aug;17(8):e012663. doi: 10.1161/CIRCEP.123.012663. Epub 2024 Jul 25.
Differentiating wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide tachycardia via 12-lead ECG interpretation is a crucial but difficult task. Automated algorithms show promise as alternatives to manual ECG interpretation, but direct comparison of their diagnostic performance has not been undertaken.
Two electrophysiologists applied 3 manual WCT differentiation approaches (ie, Brugada, Vereckei aVR, and VT score). Simultaneously, computerized data from paired WCT and baseline ECGs were processed by 5 automated WCT differentiation algorithms (WCT Formula, WCT Formula II, VT Prediction Model, Solo Model, and Paired Model). The diagnostic performance of automated algorithms was compared with manual ECG interpretation approaches.
A total of 212 WCTs (111 VT and 101 supraventricular wide tachycardia) from 104 patients were analyzed. WCT Formula demonstrated superior accuracy (85.8%) and specificity (87.1%) compared with Brugada (75.2% and 57.4%, respectively) and Vereckei aVR (65.3% and 36.4%, respectively). WCT Formula II achieved higher accuracy (89.6%) and specificity (85.1%) against Brugada and Vereckei aVR. Performance metrics of the WCT Formula (accuracy 85.8%, sensitivity 84.7%, and specificity 87.1%) and WCT Formula II (accuracy 89.8%, sensitivity 89.6%, and specificity 85.1%) were similar to the VT score (accuracy 84.4%, sensitivity 93.8%, and specificity 74.2%). Paired Model was superior to Brugada in accuracy (89.6% versus 75.2%), specificity (97.0% versus 57.4%), and F1 score (0.89 versus 0.80). Paired Model surpassed Vereckei aVR in accuracy (89.6% versus 65.3%), specificity (97.0% versus 75.2%), and F1 score (0.89 versus 0.74). Paired Model demonstrated similar accuracy (89.6% versus 84.4%), inferior sensitivity (79.3% versus 93.8%), but superior specificity (97.0% versus 74.2%) to the VT score. Solo Model and VT Prediction Model accuracy (82.5% and 77.4%, respectively) was superior to the Vereckei aVR (65.3%) but similar to Brugada (75.2%) and the VT score (84.4%).
Automated WCT differentiation algorithms demonstrated favorable diagnostic performance compared with traditional manual ECG interpretation approaches.
通过 12 导联心电图解读将宽 QRS 心动过速（WCT）区分成室性心动过速（VT）和室上性宽 QRS 心动过速是一项至关重要但具有挑战性的任务。自动化算法作为心电图解读的替代方法具有很大的应用前景，但尚未对其诊断性能进行直接比较。
两名电生理学家应用了 3 种手动 WCT 区分方法（即 Brugada、Vereckei aVR 和 VT 评分）。同时，对来自 104 名患者的 212 例 WCT（111 例 VT 和 101 例室上性宽 QRS 心动过速）的配对 WCT 和基线心电图进行计算机化数据处理，由 5 种自动化 WCT 区分算法（WCT 公式、WCT 公式 II、VT 预测模型、Solo 模型和配对模型）处理。比较了自动化算法与手动心电图解读方法的诊断性能。
共分析了来自 104 名患者的 212 例 WCT（111 例 VT 和 101 例室上性宽 QRS 心动过速）。与 Brugada（分别为 75.2%和 57.4%）和 Vereckei aVR（分别为 65.3%和 36.4%）相比，WCT 公式在准确性（85.8%）和特异性（87.1%）方面表现更好。WCT 公式 II 在准确性（89.6%）和特异性（85.1%）方面优于 Brugada 和 Vereckei aVR。WCT 公式（准确性 85.8%，敏感性 84.7%，特异性 87.1%）和 WCT 公式 II（准确性 89.8%，敏感性 89.6%，特异性 85.1%）的性能指标与 VT 评分（准确性 84.4%，敏感性 93.8%，特异性 74.2%）相似。配对模型在准确性（89.6% 对 75.2%）、特异性（97.0% 对 57.4%）和 F1 评分（0.89 对 0.80）方面优于 Brugada。配对模型在准确性（89.6% 对 65.3%）、特异性（97.0% 对 75.2%）和 F1 评分（0.89 对 0.74）方面优于 Vereckei aVR。配对模型的准确性（89.6% 对 84.4%）相似，敏感性（79.3% 对 93.8%）较低，但特异性（97.0% 对 74.2%）优于 VT 评分。Solo 模型和 VT 预测模型的准确性（分别为 82.5%和 77.4%）优于 Vereckei aVR（65.3%），但与 Brugada（75.2%）和 VT 评分（84.4%）相似。
与传统的手动心电图解读方法相比，自动化 WCT 区分算法表现出良好的诊断性能。
