Skip to main content
QUICK REVIEW

[论文解读] A Machine Learning Approach to Automatic Classification of Eight Sleep Disorders

Dylan Zhuang, Ivey Rao|arXiv (Cornell University)|Apr 14, 2022
EEG and Brain-Computer Interfaces被引用 6
一句话总结

本研究提出一种多通道深度学习模型,利用原始多导睡眠图信号(EEG、EMG、ECG、EOG)对八种睡眠障碍进行分类,所有障碍的敏感度和特异性均超过95%。该模型通过使用原始信号输入,优于基于特征的方法,且通过热力图可视化证实了其学习到的临床相关频率模式。

ABSTRACT

In this research, we attempt to answer the following basic research questions: Is a machine learning model able to classify all types of sleep disorders with high accuracy? Among the different modalities of sleep disorder signals, are some more important than others? Do raw signals improve the performance of a deep learning model when they are used as inputs? Prior research showed that most sleep disorders belong to eight categories. To study the performance of machine learning models in classifying polysomnography recordings into the eight categories of sleep pathologies, we selected the Cyclic Alternating Pattern Sleep Database. We developed a multi-channel Deep Learning model where a set of Convolutional Neural Networks were applied to six channels of raw signals of different modalities, including three channels of EEG signals and one channel each of EMG, ECG , and EOG signals. To compare the performance of the DL model with other models, we designed a model that took spectral features, instead of raw signals, as its inputs. We first studied the "importance" issue of signal modalities using the RF algorithm. We found that ECG contributed most to the important features and EMG second, among the four signal modalities. We then studied the accuracy performance of the proposed machine learning models. We verified that the multi-channel DL-R model, which took raw signals as its inputs, outperformed all other models, with its sensitivity and specificity scores both being above 95 %. This accuracy performance is on a par with those published results which dealt with fewer types of sleep disorders. We adopted two popular heatmap-generating techniques, with which we confirmed that the DL model's superior performance was owing to the CNN network's ability to extract potent features from raw signals.

研究动机与目标

  • 开发一种基于机器学习的框架,用于自动分类八种常见睡眠障碍,使用多导睡眠图(PSG)数据。
  • 评估使用原始生理信号是否能提升深度学习模型的性能,相较于手工提取的频谱特征。
  • 确定不同信号模态(EEG、EMG、ECG、EOG)在分类睡眠病理中的相对重要性。
  • 通过热力图可视化技术评估深度学习模型的可解释性。
  • 比较深度学习模型与传统分类器(SVM、随机森林)在PSG数据上的性能。

提出的方法

  • 一个多通道一维卷积神经网络(CNN)处理六路原始信号:三路EEG、一路EMG、一路ECG和一路EOG。
  • 训练两种深度学习模型:DL-R(以原始信号作为输入)和DL-F(以频谱特征作为输入)。
  • 使用随机森林对不同信号模态的特征重要性进行排序,识别出ECG和EMG为最具判别性的信号。
  • 应用Grad-CAM和Grad-CAM++生成热力图,以实现模型的可解释性,可视化频率范围和峰值频率。
  • 通过敏感度和特异性在八种睡眠障碍类别中进行性能评估:磨牙症(Bru)、失眠(Ins)、发作性睡病(Nar)、周期性肢体运动(Plm)、快速眼动睡眠行为障碍(Rbd)、睡眠呼吸障碍(Sbd)、夜间额叶癫痫(Nfl)和正常(Nrm)。
  • 模型在周期性交替模式(CAP)睡眠数据库上进行评估,该数据库包含108例多导睡眠图记录。

实验结果

研究问题

  • RQ1深度学习模型能否利用原始多导睡眠图信号,在分类全部八种主要睡眠障碍时实现高准确率?
  • RQ2哪种信号模态(EEG、EMG、ECG、EOG)对分类性能贡献最大?
  • RQ3与使用手工提取的频谱特征相比,使用原始信号作为输入是否能提升深度学习模型的性能?
  • RQ4热力图可视化技术能否解释模型预测结果,并与临床观察一致?
  • RQ5基于原始信号的深度学习模型性能与传统分类器及基于特征的深度学习模型相比如何?

主要发现

  • 使用原始信号作为输入的DL-R模型,在所有八种睡眠障碍中均实现了超过95%的敏感度和特异性,优于所有其他模型。
  • 使用频谱特征作为输入的DL-F模型在周期性肢体运动(Plm)患者中表现出特别低的敏感度(62.9%)和特异性(87.1%),表明存在较高的假阳性和假阴性率。
  • 随机森林分析显示,ECG信号对关键特征的贡献最大,其次是EMG,表明其在各模态中具有最高的判别能力。
  • 热力图分析证实,DL-R模型学习到的频率模式与临床发现一致:磨牙症和夜间额叶癫痫表现出明显的低频活动,而失眠则在中高频段活跃。
  • 该模型表现出卓越的鲁棒性,DL-R模型对磨牙症的敏感度和特异性分别达到99.6%和99.6%,对正常睡眠的敏感度和特异性分别为98.2%和95.9%。
  • 本研究证实,基于原始信号训练的深度学习模型能够实现高准确率和临床可解释性,优于传统分类器和基于特征的深度学习模型。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。