Study objectivesWe aimed to build a tool which facilitates manual labeling of sleep slow oscillations (SOs) and evaluate the performance of traditional sleep SO detection algorithms on such a manually labeled data set. We sought to develop improved methods for SO detection.MethodSOs in polysomnographic recordings acquired during nap time from ten older adults were manually labeled using a custom built graphical user interface tool. Three automatic SO detection algorithms previously used in the literature were evaluated on this data set. Additional machine learning and deep learning algorithms were trained on the manually labeled data set.ResultsOur custom built tool significantly decreased the time needed for manual labeling, allowing us to manually inspect 96,277 potential SO events. The three automatic SO detection algorithms showed relatively low accuracy (max. 61.08%), but results were qualitatively similar, with SO density and amplitude increasing with sleep depth. The machine learning and deep learning algorithms showed higher accuracy (best: 99.20%) while maintaining a low prediction time.ConclusionsAccurate detection of SO events is important for investigating their role in memory consolidation. In this context, our tool and proposed methods can provide significant help in identifying these events.

中文翻译：

---

改进脑电图数据中睡眠慢振荡的检测

研究目标我们的目标是构建一种工具，方便手动标记睡眠慢振荡 (SO)，并评估传统睡眠 SO 检测算法在此类手动标记数据集上的性能。我们寻求开发改进的 SO 检测方法。方法 使用定制的图形用户界面工具对 10 名老年人在午睡期间获取的多导睡眠图记录中的 SO 进行手动标记。在此数据集上评估了文献中先前使用的三种自动 SO 检测算法。其他机器学习和深度学习算法在手动标记的数据集上进行了训练。结果我们的定制工具显着减少了手动标记所需的时间，使我们能够手动检查 96,277 个潜在的 SO 事件。三种自动 SO 检测算法的准确度相对较低（最高 61.08%），但结果在质量上相似，SO 密度和幅度随着睡眠深度而增加。机器学习和深度学习算法显示出更高的准确度（最佳：99.20%），同时保持较低的预测时间。 结论 准确检测 SO 事件对于研究它们在记忆巩固中的作用非常重要。在这种情况下，我们的工具和提出的方法可以为识别这些事件提供重要帮助。