Institute of Measurement Science, Slovak Academy of Sciences, Bratislava, Slovak Republic.
Artif Intell Med. 2011 Sep;53(1):25-33. doi: 10.1016/j.artmed.2011.06.004. Epub 2011 Jul 13.
The objective of this study is to find the best set of characteristics of polysomnographic signals for the automatic classification of sleep stages.
A selection was made from 74 measures, including linear spectral measures, interdependency measures, and nonlinear measures of complexity that were computed for the all-night polysomnographic recordings of 20 healthy subjects. The adopted multidimensional analysis involved quadratic discriminant analysis, forward selection procedure, and selection by the best subset procedure. Two situations were considered: the use of four polysomnographic signals (EEG, EMG, EOG, and ECG) and the use of the EEG alone.
For the given database, the best automatic sleep classifier achieved approximately an 81% agreement with the hypnograms of experts. The classifier was based on the next 14 features of polysomnographic signals: the ratio of powers in the beta and delta frequency range (EEG, channel C3), the fractal exponent (EMG), the variance (EOG), the absolute power in the sigma 1 band (EEG, C3), the relative power in the delta 2 band (EEG, O2), theta/gamma (EEG, C3), theta/alpha (EEG, O1), sigma/gamma (EEG, C4), the coherence in the delta 1 band (EEG, O1-O2), the entropy (EMG), the absolute theta 2 (EEG, Fp1), theta/alpha (EEG, Fp1), the sigma 2 coherence (EEG, O1-C3), and the zero-crossing rate (ECG); however, even with only four features, we could perform sleep scoring with a 74% accuracy, which is comparable to the inter-rater agreement between two independent specialists.
We have shown that 4-14 carefully selected polysomnographic features were sufficient for successful sleep scoring. The efficiency of the corresponding automatic classifiers was verified and conclusively demonstrated on all-night recordings from healthy adults.
本研究旨在寻找最佳的多导睡眠图信号特征集，用于自动睡眠分期。
从 74 项线性谱测度、互相关测度和复杂度非线性测度中进行选择，这些测度是对 20 名健康受试者整夜多导睡眠记录进行计算得到的。采用的多维分析包括二次判别分析、前向选择过程和最佳子集选择过程。考虑了两种情况：使用 4 个多导睡眠图信号（EEG、EMG、EOG 和 ECG）和仅使用 EEG。
对于给定的数据库，最佳的自动睡眠分类器与专家的睡眠图达成了约 81%的一致性。分类器基于以下 14 个多导睡眠图信号特征：β和δ频带（EEG，通道 C3）的功率比、分形指数（EMG）、方差（EOG）、σ1 带的绝对功率（EEG，C3）、δ2 带的相对功率（EEG，O2）、θ/γ（EEG，C3）、θ/α（EEG，O1）、σ/γ（EEG，C4）、δ1 带的相干性（EEG，O1-O2）、熵（EMG）、绝对θ2（EEG，Fp1）、θ/α（EEG，Fp1）、σ2 相干性（EEG，O1-C3）和零交叉率（ECG）。然而，即使仅使用 4 个特征，我们也可以以 74%的准确率进行睡眠评分，这与两名独立专家之间的评分一致性相当。
我们已经证明，4-14 个精心选择的多导睡眠图特征足以进行成功的睡眠评分。相应的自动分类器的效率在健康成年人的整夜记录中得到了验证和明确证明。
