基于成人与儿童心电图深度生存分析的多中心基准研究
Deep Survival Analysis from Adult and Pediatric Electrocardiograms: A Multi-center Benchmark Study
AI总结：
本研究在三大成人与儿童队列中系统评估了AI-ECG死亡率预测模型，发现深度生存方法优于基于时间窗的分类器，且跨队列训练显著提升了模型性能。
摘要：
应用于心电图的人工智能（AI-ECG）在死亡率预测方面展现出潜力，但方法的异质性和私有数据集限制了其可推广的见解。为解决这一问题，我们在三个大型队列中系统评估了模型设计选择：Beth Israel Deaconess（MIMIC-IV：n = 795,546 ECGs，美国）、Telehealth Network of Minas Gerais（Code-15：n = 345,779，巴西）和 Boston Children's Hospital（BCH：n = 255,379，美国）。我们评估了预测全因死亡率的模型，比较了基于时间窗的分类与深度生存方法，所用神经网络架构包括卷积网络和 transformers，并以仅含人口统计学信息的模型和梯度提升模型作为基准。表现最优的模型性能良好（中位一致性：Code-15，0.83；MIMIC-IV，0.78；BCH，0.81）。纳入年龄和性别在所有数据集上均提升了性能。Classifier-Cox 模型对时间窗选择表现出依赖站点的敏感性（中位 Pearson's R：Code-15，0.35；MIMIC-IV，-0.71；BCH，0.37）。外部验证降低了一致性，在某些情况下，仅含人口统计学信息的模型在 Code-15 上的表现优于外部训练的 AI-ECG 模型。然而，在多站点数据上训练的模型比特定站点模型高出 5-22%。研究结果突出了稳健部署 AI-ECG 的关键因素：深度生存方法优于基于时间窗的分类器，人口统计学协变量提升了预测性能，基于分类器的模型需要针对特定站点进行校准，而跨队列训练（即使在成人与儿童队列之间）显著提升了性能。这些结果强调了模型类型、人口统计学特征和训练多样性在开发能可靠适用于不同人群的 AI-ECG 模型中的重要性。
英文摘要：
Artificial intelligence applied to electrocardiography (AI-ECG) shows potential for mortality prediction, but heterogeneous approaches and private datasets have limited generalizable insights. To address this, we systematically evaluated model design choices across three large cohorts: Beth Israel Deaconess (MIMIC-IV: n = 795,546 ECGs, United States), Telehealth Network of Minas Gerais (Code-15: n = 345,779, Brazil), and Boston Children's Hospital (BCH: n = 255,379, United States). We evaluated models predicting all-cause mortality, comparing horizon-based classification and deep survival methods with neural architectures including convolutional networks and transformers, benchmarking against demographic-only and gradient boosting baselines. Top models performed well (median concordance: Code-15, 0.83; MIMIC-IV, 0.78; BCH, 0.81). Incorporating age and sex improved performance across all datasets. Classifier-Cox models showed site-dependent sensitivity to horizon choice (median Pearson's R: Code-15, 0.35; MIMIC-IV, -0.71; BCH, 0.37). External validation reduced concordance, and in some cases demographic-only models outperformed externally trained AI-ECG models on Code-15. However, models trained on multi-site data outperformed site-specific models by 5-22%. Findings highlight factors for robust AI-ECG deployment: deep survival methods outperformed horizon-based classifiers, demographic covariates improved predictive performance, classifier-based models required site-specific calibration, and cross-cohort training, even between adult and pediatric cohorts, substantially improved performance. These results emphasize the importance of model type, demographics, and training diversity in developing AI-ECG models reliably applicable across populations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
