IRIDIA, Université Libre de Bruxelles, 1050 Bruxelles, Belgium; Department of Cardiology, UMONS (Université de Mons), 7000 Mons, Belgium.
IRIDIA, Université Libre de Bruxelles, 1050 Bruxelles, Belgium.
Arch Cardiovasc Dis. 2022 Jun-Jul;115(6-7):377-387. doi: 10.1016/j.acvd.2022.04.006. Epub 2022 May 20.
Machine learning and deep learning techniques are now used extensively for atrial fibrillation (AF) screening, but their use for AF crisis forecasting has yet to be assessed in a clinical context.
To assess the value of two machine learning algorithms for the short-term prediction of paroxysmal AF episodes.
We conducted a retrospective study from an outpatient clinic. We developed a deep neural network model that was trained for a supervised binary classification, differentiating between RR interval variations that precede AF onset and RR interval variations far from any AF. We also developed a random forest model to obtain forecast results using heart rate variability variables, with and without premature atrial complexes.
In total, 10,484 Holter electrocardiogram recordings were screened, and 250 analysable AF onsets were labelled. The deep neural network model was able to distinguish if a given RR interval window would lead to AF onset in the next 30 beats with a sensitivity of 80.1% (95% confidence interval 78.7-81.6) at the price of a low specificity of 52.8% (95% confidence interval 51.0-54.6). The random forest model indicated that the main factor that precedes the start of a paroxysmal AF episode is autonomic nervous system activity, and that premature complexes add limited additional information. In addition, the onset of AF episodes is preceded by cyclical fluctuations in the low frequency/high frequency ratio of heart rate variability. Each peak is itself followed by an increase in atrial extrasystoles.
The use of two machine learning algorithms for the short-term prediction of AF episodes allowed us to confirm that the main cause of AF crises lies in an imbalance in the autonomic nervous system, and not premature atrial contractions, which are, however, required as a final firing trigger.
机器学习和深度学习技术现在广泛应用于心房颤动（AF）筛查，但它们在临床环境中用于预测 AF 危机的应用尚未得到评估。
评估两种机器学习算法在预测阵发性 AF 发作的短期预测中的价值。
我们进行了一项回顾性研究，来自一个门诊诊所。我们开发了一种深度神经网络模型，该模型经过监督的二进制分类训练，区分在 AF 发作之前的 RR 间隔变化和远离任何 AF 的 RR 间隔变化。我们还开发了一个随机森林模型，使用心率变异性变量（包括和不包括房性早搏）来获得预测结果。
共筛选了 10484 份动态心电图记录，标记了 250 个可分析的 AF 发作。深度神经网络模型能够区分给定的 RR 间隔窗口是否会导致下 30 个心拍的 AF 发作，其敏感性为 80.1%（95%置信区间为 78.7-81.6），特异性低至 52.8%（95%置信区间为 51.0-54.6）。随机森林模型表明，阵发性 AF 发作开始前的主要因素是自主神经系统活动，而早搏增加的信息量有限。此外，AF 发作的发作之前是心率变异性的低频/高频比的周期性波动。每个峰值本身之后都会增加房性期前收缩。
使用两种机器学习算法对 AF 发作的短期预测允许我们确认 AF 危机的主要原因在于自主神经系统失衡，而不是房性早搏，后者是最后触发的。
