Classification techniques on computerized systems to predict and/or to detect Apnea: A systematic review

Article ID	Journal	Published Year	Pages	File Type
4958226	Computer Methods and Programs in Biomedicine	2017	10 Pages	PDF

Abstract

A classification model should provide an auto-adaptive and no external-human action dependency. In addition, the accuracy of the classification models is related with the effective features selection. New high-quality studies based on randomized controlled trials and validation of models using a large and multiple sample of data are recommended.

Keywords

RCT PPV NARX KNN MSA LS-SVM RDI CAS PNN ANFIS SAS aHI EOG ROC HMM MLR PPG BHC BNN RBFNN LVQ ANN VDA ECOC Error correcting output code SRN AUC k-nearest neighbor Randomized controlled trial Sleep apnea obstructive sleep apnea Central sleep apnea positive predictive value negative predictive value oxygen saturation Electroencephalogram EMG electromyography electrocardiogram ECG electrooculography AIRS Osa Linear discriminant analysis LDA Voice activity detection least squares support vector machine Logistic regression multi-linear regression Sleep apnea syndrome Adaptive neuro-fuzzy inference system Artificial Immune Recognition System Apnea index Respiratory disturbance index Probabilistic neural network Bayesian neural network Radial basis function neural network Artificial Neural Network Simple Recurrent Network Classification Photoplethysmogram Support vector machine SVM true positive false positive Area under receiver operating characteristic curve Hidden Markov model Systematic review Learning vector quantization NPV یا negative predictive value false negative true negative EEG PSG Polysomnogram receiver operating characteristic Machine learning