Assessment of four statistical pattern recognition techniques to assist in obstructive sleep apnoea diagnosis from nocturnal oximetry

• Published in: Medical engineering & physics Vol. 31; no. 8; pp. 971 - 978
• Main Authors: Marcos, J. Víctor, Hornero, Roberto, Álvarez, Daniel, del Campo, Félix, Zamarrón, Carlos
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.10.2009
• Subjects: Algorithms; Data Interpretation, Statistical; Discriminant Analysis; Humans; K-Nearest neighbours; Linear Models; Logistic Models; Logistic regression; Male; Middle Aged; Obstructive sleep apnoea; Oximetry - statistics & numerical data; Oxygen - metabolism; Oxygen saturation; Pattern Recognition, Automated; Radiology; Sleep Apnea, Obstructive - diagnosis; Sleep Apnea, Obstructive - metabolism; Statistical pattern recognition; Time Factors; Logistic regression; Discriminant analysis; Obstructive sleep apnoea; Statistical pattern recognition; Oxygen saturation; K-Nearest neighbours
• ISSN: 1350-4533; 1873-4030; 1873-4030
• DOI: 10.1016/j.medengphy.2009.05.010

The aim of this study is to assess the utility of traditional statistical pattern recognition techniques to help in obstructive sleep apnoea (OSA) diagnosis. Classifiers based on quadratic (QDA) and linear (LDA) discriminant analysis, K-nearest neighbours (KNN) and logistic regression (LR) were evaluated. Spectral and nonlinear input features from oxygen saturation (SaO 2) signals were applied. A total of 187 recordings from patients suspected of suffering from OSA were available. This initial dataset was divided into training set (74 subjects) and test set (113 subjects). Twelve classification algorithms were developed by applying QDA, LDA, KNN and LR with spectral features, nonlinear features and combination of both groups. The performance of each algorithm was measured on the test set by means of classification accuracy and receiver operating characteristic (ROC) analysis. QDA, LDA and LR showed better classification capability than KNN. The classifier based on LDA with spectral features provided the best diagnostic ability with an accuracy of 87.61% (91.05% sensitivity and 82.61% specificity) and an area under the ROC curve (AROC) of 0.925. The proposed statistical pattern recognition techniques could be applied as an OSA screening tool.