Assessment of Feature Selection and Classification Approaches to Enhance Information From Overnight Oximetry in the Context of Apnea Diagnosis

Abstract

This study is aimed at assessing the usefulness of different feature selection and classification methodologies in the context of sleep apnea hypopnea syndrome (SAHS) detection. Feature extraction, selection and classification stages were applied to analyze blood oxygen saturation (SaO2) recordings in order to simplify polysomnography (PSG), the gold standard diagnostic methodology for SAHS. Statistical, spectral and nonlinear measures were computed to compose the initial feature set. Principal component analysis (PCA), forward stepwise feature selection (FSFS) and genetic algorithms (GAs) were applied to select feature subsets. Fisher's linear discriminant (FLD), logistic regression (LR) and support vector machines (SVMs) were applied in the classification stage. Optimum classification algorithms from each combination of these feature selection and classification approaches were prospectively validated on datasets from two independent sleep units. FSFS + LR achieved the highest diagnostic performance using a small feature subset (4 features), reaching 83.2% accuracy in the validation set and 88.7% accuracy in the test set. Similarly, GAs + SVM also achieved high generalization capability using a small number of input features (7 features), with 84.2% accuracy on the validation set and 84.5% accuracy in the test set. Our results suggest that reduced subsets of complementary features (25% to 50% of total features) and classifiers with high generalization ability could provide high-performance screening tools in the context of SAHS.

Automated Screening of Children With Obstructive Sleep Apnea Using Nocturnal Oximetry: An Alternative to Respiratory Polygraphy in Unattended Settings

“…21,41 Notwithstanding, previous studies demonstrated that our approach could be easily optimized for any technical setting in order to achieve a high diagnostic performance. 24,42 In addition, current high-performance oximeters already match technical characteristics of in-hospital equipment overcoming previous limitations of portable devices due to restrictions in memory storage capability and battery life. Finally, the proposed methodology presented herein aims to confirm or discard the presence of OSA (ie, to perform binary classification).…”

“…23,24 Therefore, an individual or chromosome from the population is just a combination of features (ie, a feature subset from the initial oximetric feature space composed of 18 features). A two-symbol binary codification was used to encode each feature subset or individual in the population, where the k-th bit denotes the absence (0) or the presence (1) of the k-th feature.…”

“…35 In the current study, probability of crossover (P c ) values ranging from .5 to .9 and probability of mutation (P m ) values ranging from .01 to .09 were used to introduce variations into the offspring along 100 generations. 23,24,33,34 The elite or percentage of the best individuals in the old population preserved after each generation were also varied between zero and 25%. 23,24 For each cutoff point for childhood OSA (1, 3, and 5 events/h), the optimum feature subset from the last generation was selected in terms of diagnostic performance.…”

“…22 Previous studies have assessed the usefulness and applicability of GAs in the context of OSA diagnosis in adults. 23,24 The aims of this study were twofold. The first was to exhaustively characterize at-home SpO 2 recordings and to compose models aimed at classifying children showing high-risk for OSA.…”

Assessment of Time and Frequency Domain Entropies to Detect Sleep Apnoea in Heart Rate Variability Recordings from Men and Women

“…Thus, MsE has shown its usefulness to study heart rate dynamics [22], to find differences in the HRV from healthy subjects and subjects suffering from congestive heart failure and atrial fibrillation [23], to show different behaviours in the heart rate of young and elder [23], to quantify the complexity of human gait [24], to improve the knowledge of the EEG behaviour in AD patients [25], as well as to evaluate the effects of drugs in the EEG of schizophrenia patients [26]. Moreover, spectral entropy (SE) has been helpful to quantify the depth of anaesthesia in EEG recordings from women undergoing gynaecological surgery [27], to detect endpoints in speech signals recorded in noisy environments [28], to show the changes that AD causes in the spectrum of magnetoencephalographic and EEG recordings [17,29], as well as to enhance the automatic detection of SAHS from single-channel SpO2 recordings obtained during nocturnal oximetry [30].…”