作者: J.I. Trapero , C.J Arizmendi , H. Gonzalez , C. Forero , B.F. Giraldo
DOI: 10.1109/EMBC.2017.8037609
关键词:
摘要: In this work, the cardiorespiratory pattern of patients undergoing extubation process is studied. First, respiratory and cardiac signals were resampled, next Symbolic Dynamics (SD) technique was implemented, followed a dimensionality reduction applying Forward Selection (FS) Moving Window with Variance Analysis (MWVA) methods. Finally, Linear Discriminant (LDA) Support Vector Machines (SVM) classifiers used. The study analyzed 153 weaning process, classified into 3 groups: Successful Group (SG: 94 patients), Failed (FG: 39 who had been successful during to be reintubated before 48 hours, Reintubated (RG: 21 patients). According results, best classification present an accuracy higher than 88.98 ± 0.013% in all proposed combinations.