Analysis of EEG Sleep Spindle Parameters from Apnea Patients Using Massive Computing and Decision Tree

Gunther  J. L. Gerhardt; Ney Lemke; Diego  Z. Carvalho; Emerson  L. de Santa-Helena; Suzana  V. Schonwald; Guilherme Dellagustin; Jose  L. Rybarczyk Filho

doi:10.18226/23185279.v2iss1p15

Authors

Gunther J. L. Gerhardt CCET, Universidade de Caxias do Sul, R. Francisco Getúlio Vargas, 1130, Caxias do Sul-RS-Brazil, CEP95070-560
Ney Lemke Department of Physics and Biophysics, Institute of Biosciences, Universidade Estadual Paulista Júlio de Mesquita Filho, Brazil
Diego Z. Carvalho Sleep Laboratory, Neurology Medicine Division, Hospital de Clínicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Brazil
Emerson L. de Santa-Helena Department of Physics, Universidade Federal de Sergipe, Brazil
Suzana V. Schonwald Sleep Laboratory, Neurology Medicine Division, Hospital de Clínicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Brazil
Guilherme Dellagustin Sleep Laboratory, Neurology Medicine Division, Hospital de Clínicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Brazil
Jose L. Rybarczyk Filho Department of Physics and Biophysics, Institute of Biosciences, Universidade Estadual Paulista Júlio de Mesquita Filho, Brazil

DOI:

https://doi.org/10.18226/23185279.v2iss1p15

Keywords:

EEG, Signal Analysis, Matching Pursuit, Obstructive apnea, Machine Learning, Decision tree

Abstract

In this study, Matching Pursuit (MP) procedure is applied to the detection and analysis of EEG sleep spindles in patients evaluated for suspected OSAS. Elements having the frequency of EEG sleep spindles are selected from different dictionary sizes, with and without a frequency modulation function (chirp) for signal description. This procedure was done with high computational cost in order to find best parameters for real EEG data description. At the end we used the atom parameters as input for a decision tree-based classifier, making possible to obtain a classification according to apnea-hypopnea index group and allowing to see how atom parameters such as frequency and amplitude are affected by the presence of sleep apnea.