Optimized symbolic dynamics approach for the analysis of the respiratory pattern
Optimized symbolic dynamics approach for the analysis of the respiratory pattern
复制标题
DOI：
10.1109/tbme.2005.856293
复制
发表时间：
2005-11-01
影响因子：
4.6
通讯作者：
Voss, A
中科院分区：
文献类型：
--
作者：
Caminal, P;Vallverdú, M;Voss, A
传统的时域数据分析技术通常不足以表征呼吸的复杂动态。在本文中，使用符号动力学分析呼吸模式变异性。一组 20 名接受机械通气脱机试验的患者在两种不同的压力支持通气水平下进行研究，以获得具有不同变异性的呼吸容量信号。分析吸气时间、呼气时间、呼吸持续时间、吸气时间分数、潮气量和平均吸气流量的时间序列。两个不同的符号字母表（具有三个和四个符号）被认为是描述呼吸器的特征）、图案可变性。该方法的评估是使用 40 个呼吸量信号进行的，根据临床标准分为两类：低变异性 (LV) 或高变异性 (HV)。使用符号动力学的单一指标进行判别分析，能够以 100% 的样本外准确率对呼吸量信号进行分类。
Traditional time domain techniques of data analysis are often not sufficient to characterize the complex dynamics of respiration. In this paper, the respiratory pattern variability is analyzed using symbolic dynamics. A group of 20 patients on weaning trials from mechanical ventilation are studied at two different pressure support ventilation levels, in order to obtain respiratory volume signals with different variability. Time series of inspiratory time, expiratory time, breathing duration, fractional inspiratory time, tidal volume and mean inspiratory flow are analyzed. Two different symbol alphabets, with three and four symbols, are considered to characterize the respirator), pattern variability. Assessment of the method is made using the 40 respiratory volume signals classified using clinical criteria into two classes: low variability (LV) or high variability (HV). A discriminant analysis using single indexes from symbolic dynamics has been able to classify the respiratory volume signals with an out-of-sample accuracy of 100%.