Huang Jui-Tzu, Tseng Chih-Hsueh, Huang Wei-Ming, Yu Wen-Chung, Cheng Hao-Min, Chao Hsi-Lu, Chiang Chern-En, Chen Chen-Huan, Yang Albert C, Sung Shih-Hsien
Department of Medicine, Taipei Veterans General Hospital, No. 201, Sec. 2, Shipai Rd., Beitou District, Taipei 112, Taiwan.
Department of Internal Medicine, National Yang Ming Chiao Tung University, No. 155, Sec. 2, Linong Street, Beitou District, Taipei 112, Taiwan.
Eur Heart J Digit Health. 2025 Feb 11;6(2):252-260. doi: 10.1093/ehjdh/ztaf003. eCollection 2025 Mar.
Left ventricular hypertrophy (LVH) is clinically important; current electrocardiography (ECG) diagnostic criteria are inadequate for early detection. This study aimed to develop an artificial intelligence (AI)-based algorithm to improve the accuracy and prognostic value of ECG criteria for LVH detection.
A total of 42 016 patients (64.3 ± 16.5 years, 55.3% male) were enrolled. LV mass index was calculated from echocardiographic measurements. Left ventricular hypertrophy screening utilized ECG criteria, including Sokolow-Lyon, Cornell product, Cornell/strain index, Framingham criterion, and Peguero-Lo Presti. An AI algorithm using CatBoost was developed and validated (training dataset 80% and testing dataset 20%). F1 scores, reflecting the harmonic mean of precision and recall, were calculated. Mortality data were obtained through linkage with the National Death Registry. The CatBoost-based AI algorithm outperformed conventional ECG criteria in detecting LVH, achieving superior sensitivity, specificity, positive predictive value, F1 score, and area under curve. Significant features to predict LVH involved QRS and P-wave morphology. During a median follow-up duration of 10.1 years, 1655 deaths occurred in the testing dataset. Cox regression analyses showed that LVH identified by AI algorithm (hazard ratio and 95% confidence interval: 1.587, 1.309-1.924), Sokolow-Lyon (1.19, 1.038-1.365), Cornell product (1.301, 1.124-1.505), Cornell/strain index (1.306, 1.185-1.439), Framingham criterion (1.174, 1.062-1.298), and echocardiography-confirmed LVH (1.124, 1.019-1.239) were all significantly associated with mortality. Notably, AI-diagnosed LVH was more predictive of mortality than echocardiography-confirmed LVH.
Artificial intelligence-based LVH diagnosis outperformed conventional ECG criteria and was a superior predictor of mortality compared to echocardiography-confirmed LVH.
左心室肥厚（LVH）具有重要临床意义；目前的心电图（ECG）诊断标准不足以进行早期检测。本研究旨在开发一种基于人工智能（AI）的算法，以提高ECG标准检测LVH的准确性和预后价值。
共纳入42016例患者（64.3±16.5岁，55.3%为男性）。根据超声心动图测量计算左心室质量指数。左心室肥厚筛查采用ECG标准，包括索科洛-里昂标准、康奈尔乘积、康奈尔/应变指数、弗雷明汉标准和佩格罗-洛普雷斯蒂标准。开发并验证了一种使用CatBoost的AI算法（训练数据集80%，测试数据集20%）。计算反映精度和召回率调和均值的F1分数。通过与国家死亡登记处的链接获取死亡率数据。基于CatBoost的AI算法在检测LVH方面优于传统ECG标准，具有更高的敏感性、特异性、阳性预测值、F1分数和曲线下面积。预测LVH的显著特征涉及QRS波和P波形态。在中位随访期10.1年期间，测试数据集中有1655例死亡。Cox回归分析表明，AI算法识别的LVH（风险比和95%置信区间：1.587，1.309 - 1.924）、索科洛-里昂标准（1.19，1.038 - 1.365）、康奈尔乘积（1.301，1.124 - 1.505）、康奈尔/应变指数（1.306，1.185 - 1.439）、弗雷明汉标准（1.174，1.062 - 1.298）以及超声心动图证实的LVH（1.124，1.019 - 1.239）均与死亡率显著相关。值得注意的是，AI诊断的LVH比超声心动图证实的LVH对死亡率的预测性更强。
基于人工智能的LVH诊断优于传统ECG标准，并且与超声心动图证实的LVH相比，是死亡率的更优预测指标。
