Massiani Pierre-François, Haverbeck Lukas, Thesing Claas, Solowjow Friedrich, Verket Marlo, Zink Matthias Daniel, Schütt Katharina, Müller-Wieland Dirk, Marx Nikolaus, Trimpe Sebastian
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany.
Department of Internal Medicine I, University Hospital RWTH Aachen, Aachen, Germany.
Sci Rep. 2025 Jul 22;15(1):26582. doi: 10.1038/s41598-025-10090-2.
Atrial fibrillation (AF) correlates with an increased risk of all-cause mortality or stroke, mainly due to undiagnosed patients and undertreatment. Its screening is thus a key challenge, for which machine learning methods hold the promise of cheaper and faster campaigns. The robustness of such methods to varying artifacts, noise, and conditions is then crucial. We introduce the first distributional support vector machine (SVM) for robust detection of AF from short, noisy electrocardiograms. It achieves state-of-the-art performance and unprecedented robustness on the screening problem while only leveraging one interpretable feature and little training data. We illustrate these advantages by evaluating on other data sources (cross-data-set) and through sensitivity studies. These strengths result from two main components: (i) preliminary peak detection enabling robust computation of medically relevant features; and (ii) a mathematically principled way of aggregating those features to compare their full distributions. This establishes our algorithm as a relevant candidate for screening campaigns.
心房颤动（AF）与全因死亡率或中风风险增加相关，主要原因是存在未确诊患者以及治疗不足。因此，对其进行筛查是一项关键挑战，机器学习方法有望实现更廉价、更快速的筛查。这些方法对于不同伪影、噪声和条件的鲁棒性至关重要。我们引入了首个分布式支持向量机（SVM），用于从短程、有噪声的心电图中稳健地检测AF。它在筛查问题上实现了最先进的性能和前所未有的鲁棒性，同时仅利用一个可解释特征且只需很少的训练数据。我们通过在其他数据源上进行评估（跨数据集）以及敏感性研究来说明这些优势。这些优势源于两个主要组成部分：（i）初步的峰值检测，能够稳健地计算医学相关特征；（ii）一种数学上有原则的方法来聚合这些特征，以比较它们的完整分布。这使我们的算法成为筛查活动的一个相关候选方法。
