T-wave alternans (TWA) analysis was shown in >14,000 individuals studied worldwide over the past two decades to be a useful tool to assess risk for cardiovascular mortality and sudden arrhythmic death. TWA analysis by the modified moving average (MMA) method is FDA-cleared and CMS-reimbursed (CAG-00293R2). Because the MMA technique is inherently suitable for dynamic tracking of alternans levels, it was selected for development of artificial intelligence (AI)-enabled algorithms using convolutional neural networks (CNN) to achieve rapid, efficient, and accurate assessment of P-wave alternans (PWA), R-wave alternans (RWA), and TWA. The novel application of CNN algorithms to enhance MMA analysis generated efficient and powerful pattern-recognition algorithms for highly accurate alternans quantification. Algorithm reliability and accuracy were verified using simulated ECGs achieving R ≥ 0.99 ( < 0.01) in response to noise inputs and artifacts that emulate real-life conditions. Accuracy of the new AI-MMA algorithms in TWA analysis ( = 5) was significantly improved over unsupervised, automated MMA output ( = 0.036) and did not differ from conventional MMA analysis with expert overreading ( = 0.21). Accuracy of AI-MMA in PWA analysis ( = 45) was significantly improved over unsupervised, automated MMA output ( < 0.005) and did not differ from conventional MMA analysis with expert overreading ( = 0.89). TWA and PWA by AI-MMA were correlated with conventional MMA output over-read by an expert reader (R = 0.7765, R = 0.9504, respectively). This novel technique for AI-MMA analysis could be suitable for use in diverse in-hospital and out-of-hospital monitoring systems, including cardiac implantable electronic devices and smartwatches, for tracking atrial and ventricular arrhythmia risk.

中文翻译：

---

卷积神经网络在人工智能支持的 P 波、R 波和 T 波交替移动平均分析中的新应用，用于检测房性和室性心律失常的风险

过去二十年来，对全球超过 14,000 名个体进行的研究显示，T 波交替 (TWA) 分析是评估心血管死亡和心律失常性猝死风险的有用工具。采用修正移动平均 (MMA) 方法进行的 TWA 分析已获得 FDA 批准并由 CMS 报销 (CAG-00293R2)。由于 MMA 技术本质上适合动态跟踪交替水平，因此选择它来开发使用卷积神经网络 (CNN) 的人工智能 (AI) 算法，以实现 P 波交替水平的快速、高效和准确的评估。 PWA)、R 波交替 (RWA) 和 TWA。CNN 算法在增强 MMA 分析方面的新颖应用产生了高效且强大的模式识别算法，可实现高精度的交替定量。使用模拟心电图验证算法的可靠性和准确性，实现 R ≥ 0.99 (< 0.01)，以响应模拟现实生活条件的噪声输入和伪影。TWA 分析中新的 AI-MMA 算法的准确性 (= 5) 比无监督的自动化 MMA 输出 (= 0.036) 显着提高，并且与采用专家复读的传统 MMA 分析 (= 0.21) 没有区别。PWA 分析中 AI-MMA 的准确性 (= 45) 比无监督的自动化 MMA 输出 (< 0.005) 显着提高，并且与专家复读的传统 MMA 分析 (= 0.89) 没有差异。AI-MMA 的 TWA 和 PWA 与专家阅读器过度阅读的传统 MMA 输出相关（分别为 R = 0.7765、R = 0.9504）。这种用于 AI-MMA 分析的新技术可适用于各种院内和院外监测系统，包括心脏植入式电子设备和智能手表，用于跟踪房性和室性心律失常风险。