Arcentales Andrés, Giraldo Beatriz F, Caminal Pere, Diaz Iván, Benito Salvador
Dept. ESAII, Universitat Politècnica de Catalunya (UPC), Spain.
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:2485-8. doi: 10.1109/IEMBS.2010.5626533.
A considerable number of patients in weaning process have problems to keep spontaneous breathing during the trial and after it. This study proposes to extract characteristic parameters of the RR series and respiratory flow signal according to the patients' condition in weaning test. Three groups of patients have been considered: 93 patients with successful trials (group S), 40 patients that failed to maintain spontaneous breathing (group F), and 21 patients who had successful weaning trials, but that had to be reintubated before 48 hours (group R). The characterization was performed using spectral analysis of the signals, through the power spectral density, cross power spectral density and Coherence method. The parameters were extracted on the three frequency bands (VLF, LF and HF), and the principal statistical differences between groups were obtained in bands of VLF and HF. The results show an accuracy of 76.9% in the classification of the groups S and F.
相当多处于撤机过程中的患者在试验期间及之后保持自主呼吸存在问题。本研究建议根据患者撤机测试时的状况提取RR序列和呼吸流量信号的特征参数。研究考虑了三组患者:93例试验成功的患者(S组)、40例未能维持自主呼吸的患者(F组)以及21例撤机试验成功但在48小时内必须重新插管的患者(R组)。通过功率谱密度、互功率谱密度和相干方法对信号进行频谱分析来进行特征描述。在三个频段(VLF、LF和HF)上提取参数,并在VLF和HF频段获得了组间的主要统计学差异。结果显示,S组和F组分类的准确率为76.9%。