Chandan K. Karmakar

Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings

Obstructive sleep apnea syndrome (OSAS) is associated with cardiovascular morbidity as well as excessive daytime sleepiness and poor quality of life. In this study, we apply a machine learning technique [support vector machines (SVMs)] for automated recognition of OSAS types from their nocturnal ECG recordings. A total of 125 sets of nocturnal ECG recordings acquired from normal subjects (OSAS- ) and subjects with OSAS (OSAS+), each of approximately 8 h in duration, were analyzed. Features extracted from successive wavelet coefficient levels after wavelet decomposition of signals due to heart rate variability (HRV) from RR intervals and ECG-derived respiration (EDR) from R waves of QRS amplitudes were used as inputs to the SVMs to recognize OSAS +/- subjects. Using leave-one-out technique, the maximum accuracy of classification for 83 training sets was found to be 100% for SVMs using a subset of selected combination of HRV and EDR features. Independent test results on 42 subjects showed that it correctly recognized 24 out of 26 OSAS + subjects and 15 out of 16 OSAS - subjects (accuracy = 92.85%; Cohens kappa value of 0.85). For estimating the relative severity of OSAS, the posterior probabilities of SVM outputs were calculated and compared with respective apnea/hypopnea index. These results suggest superior performance of SVMs in OSAS recognition supported by wavelet-based features of ECG. The results demonstrate considerable potential in applying SVMs in an ECG-based screening device that can aid a sleep specialist in the initial assessment of patients with suspected OSAS.

Automated recognition of patients with obstructive sleep apnoea using wavelet-based features of electrocardiogram recordings

Patients with obstructive sleep apnoea syndrome (OSAS) are at increased risk of developing hypertension and other cardiovascular diseases. This paper explores the use of support vector machines (SVMs) for automated recognition of patients with OSAS types (+/-) using features extracted from nocturnal ECG recordings, and compares its performance with other classifiers. Features extracted from wavelet decomposition of heart rate variability (HRV) and ECG-derived respiration (EDR) signals of whole records (30 learning sets from physionet) are presented as inputs to train the SVM classifier to recognize OSAS+/- subjects. The optimal SVM parameter set is then determined by using a leave-one-out procedure. Independent test results have shown that an SVM using a subset of a selected combination of HRV and EDR features correctly recognized 30/30 of physionet test sets. In comparison, classification performance of K-nearest neighbour, probabilistic neural network, and linear discriminant classifiers on test data was lower. These results, therefore, demonstrate considerable potential in applying SVM in ECG-based screening and can aid sleep specialists in the initial assessment of patients with suspected OSAS.

Sensitivity of temporal heart rate variability in Poincaré plot to changes in parasympathetic nervous system activity

BackgroundA novel descriptor (Complex Correlation Measure (CCM)) for measuring the variability in the temporal structure of Poincaré plot has been developed to characterize or distinguish between Poincaré plots with similar shapes.MethodsThis study was designed to assess the changes in temporal structure of the Poincaré plot using CCM during atropine infusion, 70° head-up tilt and scopolamine administration in healthy human subjects. CCM quantifies the point-to-point variation of the signal rather than gross description of the Poincaré plot. The physiological relevance of CCM was demonstrated by comparing the changes in CCM values with autonomic perturbation during all phases of the experiment. The sensitivities of short term variability (SD 1), long term variability (SD 2) and variability in temporal structure (CCM) were analyzed by changing the temporal structure by shuffling the sequences of points of the Poincaré plot. Surrogate analysis was used to show CCM as a measure of changes in temporal structure rather than random noise and sensitivity of CCM with changes in parasympathetic activity.ResultsCCM was found to be most sensitive to changes in temporal structure of the Poincaré plot as compared to SD 1 and SD 2. The values of all descriptors decreased with decrease in parasympathetic activity during atropine infusion and 70° head-up tilt phase. In contrast, values of all descriptors increased with increase in parasympathetic activity during scopolamine administration.ConclusionsThe concordant reduction and enhancement in CCM values with parasympathetic activity indicates that the temporal variability of Poincaré plot is modulated by the parasympathetic activity which correlates with changes in CCM values. CCM is more sensitive than SD 1 and SD 2 to changes of parasympathetic activity.

Comparison of pulse rate variability with heart rate variability during obstructive sleep apnea

We investigate whether pulse rate variability (PRV) extracted from finger photo-plethysmography (Pleth) waveforms can be the substitute of heart rate variability (HRV) from RR intervals of ECG signals during obstructive sleep apnea (OSA). Simultaneous measurements (ECG and Pleth) were taken from 29 healthy subjects during normal (undisturbed sleep) breathing and 22 patients with OSA during OSA events. Highly significant (p<0.01) correlations (1.0>r>0.95) were found between heart rate (HR) and pulse rate (PR). Bland-Altman plot of HR and PR shows good agreement (<5% difference). Comparison of 2 min recording epochs demonstrated significant differences (p<0.01) in time, frequency domains and complexity analysis, between normal and OSA events using PRV as well as HRV measures. Results suggest that both HRV and PRV indices could be used to distinguish OSA events from normal breathing during sleep. However, several variability measures (SDNN, RMSSD, HF power, LF/HF and sample entropy) of PR and HR were found to be significantly (p<0.01) different during OSA events. Therefore, we conclude that PRV provides accurate inter-pulse variability to measure heart rate variability under normal breathing in sleep but does not precisely reflect HRV in sleep disordered breathing.

Toe clearance and velocity profiles of young and elderly during walking on sloped surfaces

BackgroundMost falls in older adults are reported during locomotion and tripping has been identified as a major cause of falls. Challenging environments (e.g., walking on slopes) are potential interventions for maintaining balance and gait skills. The aims of this study were: 1) to investigate whether or not distributions of two important gait variables [minimum toe clearance (MTC) and foot velocity at MTC (VelMTC)] and locomotor control strategies are altered during walking on sloped surfaces, and 2) if altered, are they maintained at two groups (young and elderly female groups).MethodsMTC and VelMTC data during walking on a treadmill at sloped surfaces (+3°, 0° and -3°) were analysed for 9 young (Y) and 8 elderly (E) female subjects.ResultsMTC distributions were found to be positively skewed whereas VelMTC distributions were negatively skewed for both groups on all slopes. Median MTC values increased (Y = 33%, E = 7%) at negative slope but decreased (Y = 25%, E = 15%) while walking on the positive slope surface compared to their MTC values at the flat surface (0°). Analysis of VelMTC distributions also indicated significantly (p < 0.05) lower minimum and 25th percentile (Q1) values in the elderly at all slopes.ConclusionThe young displayed a strong positive correlation between MTC median changes and IQR (interquartile range) changes due to walking on both slopes; however, such correlation was weak in the older adults suggesting differences in control strategies being employed to minimize the risk of tripping.

Understanding Ageing Effects by Approximate Entropy Analysis of gait variability

Ageing influences gait patterns which in turn affects the control mechanism of human locomotor balance. The aim of this study is to investigate the relationship between approximate entropy (ApEn) and standard deviation (SD) of a gait variable (minimum toe clearance, MTC) for young and elderly gait patterns. MTC data of 30 healthy young (HY), 27 healthy elderly (HE) and 10 falls risk (FR) elderly subjects with balance problems were analyzed. The ApEn values of MTC were significantly correlated with SD of MTC in the three groups; however, such correlations were abolished in the randomly shuffled MTC data of HE and HY group. These findings have implications of understanding ageing effect on gait variability and the likely risks of tripping falls during gait. Results are also potentially useful for the early diagnosis of common gait pathologies.

Classification of 5-S Epileptic EEG Recordings Using Distribution Entropy and Sample Entropy

Epilepsy is an electrophysiological disorder of the brain, the hallmark of which is recurrent and unprovoked seizures. Electroencephalogram (EEG) measures electrical activity of the brain that is commonly applied as a non-invasive technique for seizure detection. Although a vast number of publications have been published on intelligent algorithms to classify interictal and ictal EEG, it remains an open question whether they can be detected using short-length EEG recordings. In this study, we proposed three protocols to select 5 s EEG segment for classifying interictal and ictal EEG from normal. We used the publicly-accessible Bonn database, which consists of normal, interical, and ictal EEG signals with a length of 4097 sampling points (23.6 s) per record. In this study, we selected three segments of 868 points (5 s) length from each recordings and evaluated results for each of them separately. The well-studied irregularity measure—sample entropy (SampEn)—and a more recently proposed complexity measure—distribution entropy (DistEn)—were used as classification features. A total of 20 combinations of input parameters m and τ for the calculation of SampEn and DistEn were selected for compatibility. Results showed that SampEn was undefined for half of the used combinations of input parameters and indicated a large intra-class variance. Moreover, DistEn performed robustly for short-length EEG data indicating relative independence from input parameters and small intra-class fluctuations. In addition, it showed acceptable performance for all three classification problems (interictal EEG from normal, ictal EEG from normal, and ictal EEG from interictal) compared to SampEn, which showed better results only for distinguishing normal EEG from interictal and ictal. Both SampEn and DistEn showed good reproducibility and consistency, as evidenced by the independence of results on analysing protocol.

Detection of Respiratory Arousals Using Photoplethysmography (PPG) Signal in Sleep Apnea Patients

Respiratory events during sleep induce cortical arousals and manifest changes in autonomic markers in sleep disorder breathing (SDB). Finger photoplethysmography (PPG) has been shown to be a reliable method of determining sympathetic activation. We hypothesize that changes in PPG signals are sufficient to predict the occurrence of respiratory-event-related cortical arousal. In this study, we develop a respiratory arousal detection model in SDB subjects by using PPG features. PPG signals from 10 SDB subjects (9 male, 1 female) with age range 43-75 years were used in this study. Time domain features of PPG signals, such as 1) PWA-pulse wave amplitude, 2) PPI-peak-to-peak interval, and 3) Area-area under peak, were used to detect arousal events. In this study, PWA and Area have shown better performance (higher accuracy and lower false rate) compared to PPI features. After investigating possible groupings of these features, combination of PWA and Area (PWA + Area) was shown to provide better accuracy with a lower false detection rate in arousal detection. PPG-based arousal indexes agreed well across a wide range of decision thresholds, resulting in a receiver operating characteristic with an area under the curve of 0.91. For the decision threshold (PCthresh = 25%) chosen for the final analyses, a sensitivity of 68.1% and a specificity of 95.2% were obtained. The results showed an accuracy of 84.68%, 85.15%, 86.93%, and 50.79% with a false rate of 21.80%, 55.41%, 64.78%, and 50.79% at PCthresh = 25% or PPI, PWA, Area , and PWA + Area features, respectively. This indicates that combining PWA and Area features reduced the false positive rate without much affecting the sensitivity of the arousal detection system. In conclusion, the PPG-based respiratory arousal detection model is a simple and promising alternative to the conventional electroencephalogram (EEG)-based respiratory arousal detection system.

Analyzing temporal variability of standard descriptors of Poincaré plots

The Poincaré map is a visual technique to recognize the hidden correlation patterns of a time series signal. The standard descriptors of the Poincaré map are used to quantify the plot that measures the gross variability of the time series data. However, the problem lies in capturing temporal information of the plot quantitatively. In this article, we propose a new formulation for calculating the standard descriptors SD1 and SD2 from localized measures SD1^(w) and SD2^(w). To justify the importance of the temporal measure, SD1^(w), SD2^(w) are calculated for the 2 case studies (normal sinus rhythm [NSR] vs congestive heart failure and NSR vs arrhythmia) and are compared with the performance using the overall measures (SD1, SD2). Using overall SD1, receiver operating characteristic areas of 0.72 and 0.86 were obtained for NSR vs congestive heart failure and NSR vs arrhythmia, and using the proposed method resulted in 0.82 and 0.89. Because we have shown that the overall SD1 and SD2 are functions of the respective localized measures SD1^(w) and SD2^(w), we can conclude that use of localized measure provides equal or higher performance in pathology detection compared with the overall SD1 or SD2.

Investigating the changes in heart rate asymmetry (HRA) with perturbation of parasympathetic nervous system

The heart rate asymmetry (HRA) is a disproportionate distribution of heart rate signal. The current study was designed to assess the changes in HRA in experimental conditions using Poincaré plot during parasympathetic blockade (atropine infusion) and parasympathetic enhancement (scopolamine administration). After atropine infusion, the heart rate variability in 5 out of 8 subjects was found asymmetric. In contrast, all 8 subjects were found to be asymmetric during scopolamine administration. The physiological relevance of HRA was demonstrated by showing correlation with standard frequency domain parameters during all phases of the experiment. The deviation of asymmetry index (GIp) from symmetric range was further analyzed, which was maximum during scopolamine administration and minimum during atropine infusion. These findings suggest that parasympathetic block reduces the prevalence of HRA, and has significant correlation of GIp with frequency domain features of HRV analysis.