Cona Filippo, Pizza Fabio, Provini Federica, Magosso Elisa
Department of Electrical, Electronic and Information Engineering "Guglielmo Marconi", University of Bologna, Via Venezia 52, 47521 Cesena, Italy.
Department of Biomedical and Neuromotor Sciences, University of Bologna, Via Ugo Foscolo 7, 40123 Bologna, Italy; IRCCS Istituto delle Scienze Neurologiche, AUSL di Bologna, Bellaria Hospital, Via Altura 3, 40139 Bologna, Italy.
Med Eng Phys. 2014 Jul;36(7):954-61. doi: 10.1016/j.medengphy.2014.03.019. Epub 2014 Apr 25.
Slow eye movements (SEMs) are typical of drowsy wakefulness and light sleep. SEMs still lack of systematic physical characterization. We present a new algorithm, which substantially improves our previous one, for the automatic detection of SEMs from the electro-oculogram (EOG) and extraction of SEMs physical parameters. The algorithm utilizes discrete wavelet decomposition of the EOG to implement a Bayes classifier that identifies intervals of slow ocular activity; each slow activity interval is segmented into single SEMs via a template matching method. Parameters of amplitude, duration, velocity are automatically extracted from each detected SEM. The algorithm was trained and validated on sleep onsets and offsets of 20 EOG recordings visually inspected by an expert. Performances were assessed in terms of correctly identified slow activity epochs (sensitivity: 85.12%; specificity: 82.81%), correctly segmented single SEMs (89.08%), and time misalignment (0.49 s) between the automatically and visually identified SEMs. The algorithm proved reliable even in whole sleep (sensitivity: 83.40%; specificity: 72.08% in identifying slow activity epochs; correctly segmented SEMs: 93.24%; time misalignment: 0.49 s). The algorithm, being able to objectively characterize single SEMs, may be a valuable tool to improve knowledge of normal and pathological sleep.
慢眼动（SEMs）是困倦觉醒和浅睡眠的典型特征。慢眼动仍缺乏系统的物理特征描述。我们提出了一种新算法，该算法大幅改进了我们之前的算法，用于从眼电图（EOG）中自动检测慢眼动并提取慢眼动的物理参数。该算法利用眼电图的离散小波分解来实现一个贝叶斯分类器，以识别慢眼动活动的时间段；每个慢活动时间段通过模板匹配方法被分割为单个慢眼动。从每个检测到的慢眼动中自动提取幅度、持续时间、速度等参数。该算法在由专家进行视觉检查的20份眼电图记录的睡眠开始和结束阶段进行了训练和验证。通过正确识别的慢活动时段（灵敏度：85.12%；特异性：82.81%）、正确分割的单个慢眼动（89.08%）以及自动识别和视觉识别的慢眼动之间的时间错位（0.49秒）来评估性能。该算法在整个睡眠过程中也被证明是可靠的（在识别慢活动时段时，灵敏度：83.40%；特异性：72.08%；正确分割的慢眼动：93.24%；时间错位：0.49秒）。该算法能够客观地描述单个慢眼动，可能是增进对正常和病理睡眠认识的一个有价值的工具。
