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

• Published in: Computer methods and programs in biomedicine Vol. 140; pp. 265 - 274
• Main Authors: Pombo, Nuno, Garcia, Nuno, Bousson, Kouamana
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.03.2017
• Subjects: Algorithms; Classification; Diagnosis, Computer-Assisted; Humans; Internal Medicine; Machine learning; Other; Polysomnography; Sleep apnea; Sleep Apnea Syndromes - classification; Sleep Apnea Syndromes - diagnosis; Systematic review; Threshold-based classification; HI; AHI; BNN; LR; LVQ; Systematic review; Sleep apnea; AUC; PNN; MLR; Classification; Sp02; ANFIS; NARX; EMG; ML; PSG; EEG; ROC; AI; CAS; BHC; ANN; RCT; SAS; PPG; FN; LDA; FP; KNN; SVM; SRN; ECOC; VDA; LS-SVM; NPV; RDI; PPV; MSA; Threshold-based classification; EOG; OSA; ECG; HMM; RBFNN; Machine learning; AIRS; TN; TP; Sleep Apnea Syndrome; Error Correcting Output Code; Support Vector Machine; False Negative; Voice Activity Detection; Hidden Markov Model; electrooculography; Probabilistic Neural Network; Logistic Regression; Respiratory Disturbance Index; Apnea Index; Randomized Controlled Trial; Artificial Neural Network; Learning Vector Quantization; Electrocardiogram; Apnea and Hypopnea Index; Artificial Immune Recognition System; Positive Predictive Value; Hypopnea Index; Oxygen Saturation; Multi-Linear Regression; Area Under receiver operating characteristic Curve; Electroencephalogram; Radial Basis Function Neural Network; Bayesian Neural Network; Mixed Sleep Apnea; Linear Discriminant Analysis; True Positive; Electromyography; receiver operating characteristic; Binary Hierarchical Classification; Least Squares Support Vector Machine; Nonlinear AutoRegressive network with eXogenous; Negative Predictive Value; K-Nearest Neighbor; Central Sleep Apnea; Polysomnogram; True Negative; Obstructive Sleep Apnea; Photoplethysmogram; Simple Recurrent Network; False Positive; Adaptive Neuro-Fuzzy Inference System
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2017.01.001

•We provide a comprehensive review of the existing state of the art of classification models for apnea.•We identify several limitations and open problems in the computerized decision for apnea.•A classification model should provide an auto-adaptive and no external-human action dependency.•The accuracy of the classification models is related with the effective features selection.•RCTs and validation of models using a large and multiple sample of data are recommended. Sleep apnea syndrome (SAS), which can significantly decrease the quality of life is associated with a major risk factor of health implications such as increased cardiovascular disease, sudden death, depression, irritability, hypertension, and learning difficulties. Thus, it is relevant and timely to present a systematic review describing significant applications in the framework of computational intelligence-based SAS, including its performance, beneficial and challenging effects, and modeling for the decision-making on multiple scenarios. This study aims to systematically review the literature on systems for the detection and/or prediction of apnea events using a classification model. Forty-five included studies revealed a combination of classification techniques for the diagnosis of apnea, such as threshold-based (14.75%) and machine learning (ML) models (85.25%). In addition, the ML models, were clustered in a mind map, include neural networks (44.26%), regression (4.91%), instance-based (11.47%), Bayesian algorithms (1.63%), reinforcement learning (4.91%), dimensionality reduction (8.19%), ensemble learning (6.55%), and decision trees (3.27%). 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.