Utility of multilayer perceptron neural network classifiers in the diagnosis of the obstructive sleep apnoea syndrome from nocturnal oximetry

• Published in: Computer methods and programs in biomedicine Vol. 92; no. 1; pp. 79 - 89
• Main Authors: Marcos, J. Víctor, Hornero, Roberto, Álvarez, Daniel, del Campo, Félix, Zamarrón, Carlos, López, Miguel
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier Ireland Ltd 01.10.2008
• Subjects: Algorithms; Diagnosis, Computer-Assisted - methods; Female; Humans; Internal Medicine; Male; Middle Aged; Multilayer perceptron neural network; Neural Networks (Computer); Nocturnal oxygen saturation; Non-linear analysis; Obstructive sleep apnoea syndrome; Other; Oximetry - methods; Pattern classification; Pattern Recognition, Automated - methods; Polysomnography - methods; Reproducibility of Results; Sensitivity and Specificity; Sleep Apnea, Obstructive - diagnosis; Sleep Apnea, Obstructive - physiopathology; Multilayer perceptron neural network; Nocturnal oxygen saturation; Pattern classification; Non-linear analysis; Obstructive sleep apnoea syndrome
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2008.05.006

Abstract The aim of this study is to assess the ability of multilayer perceptron (MLP) neural networks as an assistant tool in the diagnosis of the obstructive sleep apnoea syndrome (OSAS). Non-linear features from nocturnal oxygen saturation (SaO2 ) recordings were used to discriminate between OSAS positive and negative patients. A total of 187 subjects suspected of suffering from OSAS (111 with a positive diagnosis of OSAS and 76 with a negative diagnosis of OSAS) took part in the study. The initial population was divided into training, validation and test sets for deriving and testing our neural network classifier. Three methods were applied to extract non-linear features from SaO2 signals: approximate entropy (ApEn), central tendency measure (CTM) and Lempel–Ziv complexity (LZC). The selected MLP-based classifier provided a diagnostic accuracy of 85.5% (89.8% sensitivity and 79.4% specificity). Our neural network algorithm could represent a useful technique for OSAS detection. It could contribute to reduce the demand for polysomnographic studies in OSAS screening.