A mathematical model of SARS-CoV-2 immunity predicts paxlovid rebound.

Nirmatrelvir/ritonavir (Paxlovid), an oral antiviral medication targeting SARS-CoV-2, remains an important treatment for COVID-19. Initial studies of nirmatrelvir/ritonavir were performed in SARS-CoV-2 unvaccinated patients without prior confirmed SARS-CoV-2 infection; however, most individuals have now either been vaccinated and/or have experienced SARS-CoV-2 infection. After nirmatrelvir/ritonavir became widely available, reports surfaced of "Paxlovid rebound," a phenomenon in which symptoms (and SARS-CoV-2 test positivity) would initially resolve, but after finishing treatment, symptoms and test positivity would return. We used a previously described parsimonious mathematical model of immunity to SARS-CoV-2 infection to model the effect of nirmatrelvir/ritonavir treatment in unvaccinated and vaccinated patients. Model simulations show that viral rebound after treatment occurs only in vaccinated patients, while unvaccinated (SARS-COV-2 naïve) patients treated with nirmatrelvir/ritonavir do not experience any rebound in viral load. This work suggests that an approach combining parsimonious models of the immune system could be used to gain important insights in the context of emerging pathogens.

Identification of Endotypes of Hospitalized COVID-19 Patients.

Background: Characterization of coronavirus disease 2019 (COVID-19) endotypes may help explain variable clinical presentations and response to treatments. While risk factors for COVID-19 have been described, COVID-19 endotypes have not been elucidated. Objectives: We sought to identify and describe COVID-19 endotypes of hospitalized patients. Methods: Consensus clustering (using the ensemble method) of patient age and laboratory values during admission identified endotypes. We analyzed data from 528 patients with COVID-19 who were admitted to telemetry capable beds at Columbia University Irving Medical Center and discharged between March 12 to July 15, 2020. Results: Four unique endotypes were identified and described by laboratory values, demographics, outcomes, and treatments. Endotypes 1 and 2 were comprised of low numbers of intubated patients (1 and 6%) and exhibited low mortality (1 and 6%), whereas endotypes 3 and 4 included high numbers of intubated patients (72 and 85%) with elevated mortality (21 and 43%). Endotypes 2 and 4 had the most comorbidities. Endotype 1 patients had low levels of inflammatory markers (ferritin, IL-6, CRP, LDH), low infectious markers (WBC, procalcitonin), and low degree of coagulopathy (PTT, PT), while endotype 4 had higher levels of those markers. Conclusions: Four unique endotypes of hospitalized patients with COVID-19 were identified, which segregated patients based on inflammatory markers, infectious markers, evidence of end-organ dysfunction, comorbidities, and outcomes. High comorbidities did not associate with poor outcome endotypes. Further work is needed to validate these endotypes in other cohorts and to study endotype differences to treatment responses.

An observational study of engineering online education during the COVID-19 pandemic.

The COVID-19 pandemic compelled the global and abrupt conversion of conventional face-to-face instruction to the online format in many educational institutions. Urgent and careful planning is needed to mitigate negative effects of pandemic on engineering education that has been traditionally content-centered, hands-on and design-oriented. To enhance engineering online education during the pandemic, we conducted an observational study at California State University, Long Beach (one of the largest and most diverse four-year university in the U.S.). A total of 110 faculty members and 627 students from six engineering departments participated in surveys and answered quantitative and qualitative questions to highlight the challenges they experienced during the online instruction in Spring 2020. Our results identified various issues that negatively influenced the online engineering education including logistical/technical problems, learning/teaching challenges, privacy and security concerns and lack of sufficient hands-on training. For example, more than half of the students indicated lack of engagement in class, difficulty in maintaining their focus and Zoom fatigue after attending multiple online sessions. A correlation analysis showed that while semi-online asynchronous exams were associated with an increase in the perceived cheating by the instructors, a fully online or open-book/open-note exams had an association with a decrease in instructor's perception of cheating. To address various identified challenges, we recommended strategies for educational stakeholders (students, faculty and administration) to fill the tools and technology gap and improve online engineering education. These recommendations are practical approaches for many similar institutions around the world and would help improve the learning outcomes of online educations in various engineering subfields. As the pandemic continues, sharing the results of this study with other educators can help with more effective planning and choice of best practices to enhance the efficacy of online engineering education during COVID-19 and post-pandemic.

Analysis of the Association Between Lung Function and Brain Tissue Oxygen Tension in Severe Traumatic Brain Injury.

INTRODUCTION: Low brain tissue oxygen tension (PbtO2) has been shown to be an independent factor associated with unfavourable outcomes in traumatic brain injury (TBI). Although PbtO2 provides clinicians with an understanding of ischaemic and non-ischaemic derangements of brain physiology, the value alone can be the result of several factors, including partial arterial oxygenation pressure (PaO2), haemoglobin levels (Hb) and cerebral perfusion pressure (CPP). METHODS: This chapter presents a single-centre, retrospective cohort study of 70 adult patients with severe TBI who were admitted to the Neurocritical Care Unit (NCCU) at Addenbrooke's Hospital (Cambridge, UK) between October 2014 and December 2017. A total of 303 simultaneous measurements of different variables that included (but were not limited to) intracranial pressure (ICP), PaO2, PbtO2, CPP and the fraction of inspired oxygen (FiO2) were considered in this work. We conducted a correlation analysis between all of the variables. We also implemented a longitudinal data analysis of the PbtO2 and PaO2/FiO2 ratio (PF ratio). RESULTS: There were strong and independent correlations between PbtO2 and the PF ratio, and between PbtO2 and PaO2, with adjusted p values of <0.001 for both correlations. After adjustment for ICP, age, sex and the Glasgow Coma Scale (GCS) score, a PF ≤ 330 was shown to be an independent risk factor for a compromised PbtO2 value of <20, with an adjusted odds ratio of 1.94 (95% confidence interval 1.12-3.34) and a p value of 0.02. CONCLUSION: Brain and lung interactions in patients with TBI patients have complex interrelationships. Our results confirm the importance of employing lung-protective strategies to prevent brain hypoxia in patients with TBI.

Global Cerebral Autoregulation, Resistance to Cerebrospinal Fluid Outflow and Cerebrovascular Burden in Normal Pressure Hydrocephalus.

INTRODUCTION: We previously examined the relationship between global autoregulation pressure reactivity index (PRx), mean arterial blood pressure (ABP), Resistance to cerebral spinal fluid (CSF) outflow (Rout) and their possible effects on outcome after surgery on 83 shunted patients. In this study, we aimed to quantify the relationship between all parameters that influence Rout, their interaction with the cerebral vasculature, and their role in shunt prognostication. METHODS: From 423 patients having undergone infusion tests for possible NPH, we selected those with monitored ABP and calculated its mean and PRx. After shunting, 6 months patients' outcome was marked using a simple scale (improvement, temporary improvement, and no improvement). We explored the relationship between age, different CSF dynamics variables, and vascular parameters using multivariable models. RESULTS: Rout had a weaker predictive value than ABP (Fisher Discrimination Ratio of 0.02 versus 0.42). ABP > 98 was an independent predictor of shunt outcome with odd ratio 6.4, 95% CI: 1.8-23.4 and p-value = 0.004. There was a strong and significant relationship between the interaction of age, PRx, ABP, and Rout (R = 0.53 with p = 7.28 × 10-0.5). Using our linear model, we achieved an AUC 86.4% (95% CI: 80.5-92.3%) in detecting shunt respondents. The overall sensitivity was 94%, specificity 75%, positive predictive value (PPV) of 54%, and negative predictive value of 97%. CONCLUSION: In patients with low Rout and high cerebrovascular burden, as described by high ABP and disturbed global autoregulation, response to shunting is less likely. The low PPV of high resistance, preserved autoregulation and absence of hypertension could merit further exploration.

The Role of Cerebrospinal Fluid Dynamics in Normal Pressure Hydrocephalus Diagnosis and Shunt Prognostication.

BACKGROUND: Over the years, there have been several reports and trials of the resistance to cerebrospinal fluid (CSF) outflow (Rout) in normal pressure hydrocephalus (NPH). This work aimed to revisit the utility of testing CSF circulation in a large population of patients clinically presenting with NPH. MATERIALS AND METHODS: We retrospectively analyzed the data of 369 NPH patients-either shunted or with endoscopic third ventriculostomy (ETV)-in Cambridge between 1992 and 2018. We determined the patients' outcomes (improvement versus no improvement at 6 months) by applying a threshold on R out values and compared our results with those of existing literature. We also conducted a correlation analysis between all variables and calculated Chi-Statistics (as a measure of separability between improvement and no improvement outcomes) to determine a subset of variables which achieved the highest accuracy in prediction of outcome. RESULTS: In our dataset, R out of 18 mmHg*min/mL achieved the highest Chi-statistics of 9.7 with p-value <0.01 when adjusted for age. In addition to R out, intracranial pressure (ICP) values at the baseline and plateau, CSF production rate and ICP amplitude to slope ratio showed significant Chi-Statistics values (more than 5). Using these variables, an overall accuracy of 0.70 ± 0.09 was achieved for prediction of the shunt outcome. CONCLUSION: Rout can be used for selecting patients for shunt surgery but not for excluding patients from treatment. Critical, multivariable approaches are required to comprehend CSF dynamics and pressure-volume compensation in NPH. Outcome definition and assessment could also be brought to question.

Lung Injury Is a Predictor of Cerebral Hypoxia and Mortality in Traumatic Brain Injury.

Background: A major contributor to unfavorable outcome after traumatic brain injury (TBI) is secondary brain injury. Low brain tissue oxygen tension (PbtO2) has shown to be an independent predictor of unfavorable outcome. Although PbtO2 provides clinicians with an understanding of the ischemic and non-ischemic derangements of brain physiology, its value does not take into consideration systemic oxygenation that can influence patients' outcomes. This study analyses brain and systemic oxygenation and a number of related indices in TBI patients: PbtO2, partial arterial oxygenation pressure (PaO2), PbtO2/PaO2, ratio of PbtO2 to fraction of inspired oxygen (FiO2), and PaO2/FiO2. The primary aim of this study was to identify independent risk factors for cerebral hypoxia. Secondary goal was to determine whether any of these indices are predictors of mortality outcome in TBI patients. Materials and Methods: A single-centre retrospective cohort study of 70 TBI patients admitted to the Neurocritical Care Unit (NCCU) at Cambridge University Hospital in 2014-2018 and undergoing advanced neuromonitoring including invasive PbtO2 was conducted. Three hundred and three simultaneous measurements of PbtO2, PaO2, PbtO2/PaO2, PbtO2/FiO2, PaO2/FiO2 were collected and mortality at discharge from NCCU was considered as outcome. Generalized estimating equations were used to analyse the longitudinal data. Results: Our results showed PbtO2 of 28 mmHg as threshold to define cerebral hypoxia. PaO2/FiO2 found to be a strong and independent risk factor for cerebral hypoxia when adjusting for confounding factor of intracranial pressure (ICP) with adjusted odds ratio of 1.78, 95% confidence interval of (1.10-2.87) and p-value = 0.019. With respect to TBI outcome, compromised values of PbtO2, PbtO2/PaO2, PbtO2/FiO2, and PaO2/FiO2 were all independent predictors of mortality while considered individually and adjusting for confounding factors of ICP, age, gender, and cerebral perfusion pressure (CPP). However, when considering all the compromised values together, only PaO2/FiO2 became an independent predictor of mortality with adjusted odds ratio of 3.47 (1.20-10.04) and p-value = 0.022. Conclusions: Brain and Lung interaction in TBI patients is a complex interrelationship. PaO2/FiO2 seems to be a major determinant of cerebral hypoxia and mortality. These results confirm the importance of employing ventilator strategies to prevent cerebral hypoxia and improve the outcome in TBI patients.

Algorithm for Reliable Detection of Pulse Onsets in Cerebral Blood Flow Velocity Signals.

Transcranial Doppler (TCD) ultrasound has been demonstrated to be a valuable tool for assessing cerebral hemodynamics via measurement of cerebral blood flow velocity (CBFV), with a number of established clinical indications. However, CBFV waveform analysis depends on reliable pulse onset detection, an inherently difficult task for CBFV signals acquired via TCD. We study the application of a new algorithm for CBFV pulse segmentation, which locates pulse onsets in a sequential manner using a moving difference filter and adaptive thresholding. The test data set used in this study consists of 92,012 annotated CBFV pulses, whose quality is representative of real world data. On this test set, the algorithm achieves a true positive rate of 99.998% (2 false negatives), positive predictive value of 99.998% (2 false positives), and mean temporal offset error of 6.10 ± 4.75 ms. We do note that in this context, the way in which true positives, false positives, and false negatives are defined caries some nuance, so care should be taken when drawing comparisons to other algorithms. Additionally, we find that 97.8% and 99.5% of onsets are detected within 10 and 30 ms, respectively, of the true onsets. The algorithm's performance in spite of the large degree of variation in signal quality and waveform morphology present in the test data suggests that it may serve as a valuable tool for the accurate and reliable identification of CBFV pulse onsets in neurocritical care settings.

Accuracy and Reliability of Onset Detection Algorithms in Gait Initiation for Healthy Controls and Participants With Parkinson's Disease.

Accurate and reliable detection of the onset of gait initiation is essential for the correct assessment of gait. Thus, this study was aimed at evaluation of the reliability and accuracy of 3 different center of pressure-based gait onset detection algorithms: A displacement baseline-based algorithm (method 1), a velocity baseline-based algorithm (method 2), and a velocity extrema-based algorithm (method 3). The center of pressure signal was obtained during 10 gait initiation trials from 16 healthy participants and 3 participants with Parkinson's disease. Intrasession and absolute reliability of each algorithm was assessed using the intraclass correlation coefficient and the coefficient of variation of center of pressure displacement during the postural phase of gait initiation. The accuracy was evaluated using the time error of the detected onset by each algorithm relative to that of visual inspection. The authors' results revealed that although all 3 algorithms had high to very high intrasession reliabilities in both healthy subjects and subjects with Parkinson's disease, methods 2 and 3 showed significantly better absolute reliability than method 1 in healthy controls (P = .001). Furthermore, method 2 outperformed the other 2 algorithms in both healthy subjects and subjects with Parkinson's disease with an overall accuracy of 0.80. Based on these results, the authors recommend using method 2 for accurate and reliable gait onset detection.

Feasibility of Hidden Markov Models for the Description of Time-Varying Physiologic State After Severe Traumatic Brain Injury.

OBJECTIVES: Continuous assessment of physiology after traumatic brain injury is essential to prevent secondary brain insults. The present work aims at the development of a method for detecting physiologic states associated with the outcome from time-series physiologic measurements using a hidden Markov model. DESIGN: Unsupervised clustering of hourly values of intracranial pressure/cerebral perfusion pressure, the compensatory reserve index, and autoregulation status was attempted using a hidden Markov model. A ternary state variable was learned to classify the patient's physiologic state at any point in time into three categories ("good," "intermediate," or "poor") and determined the physiologic parameters associated with each state. SETTING: The proposed hidden Markov model was trained and applied on a large dataset (28,939 hr of data) using a stratified 20-fold cross-validation. PATIENTS: The data were collected from 379 traumatic brain injury patients admitted to Addenbrooke's Hospital, Cambridge between 2002 and 2016. INTERVENTIONS: Retrospective observational analysis. MEASUREMENTS AND MAIN RESULTS: Unsupervised training of the hidden Markov model yielded states characterized by intracranial pressure, cerebral perfusion pressure, compensatory reserve index, and autoregulation status that were physiologically plausible. The resulting classifier retained a dose-dependent prognostic ability. Dynamic analysis suggested that the hidden Markov model was stable over short periods of time consistent with typical timescales for traumatic brain injury pathogenesis. CONCLUSIONS: To our knowledge, this is the first application of unsupervised learning to multidimensional time-series traumatic brain injury physiology. We demonstrated that clustering using a hidden Markov model can reduce a complex set of physiologic variables to a simple sequence of clinically plausible time-sensitive physiologic states while retaining prognostic information in a dose-dependent manner. Such states may provide a more natural and parsimonious basis for triggering intervention decisions.

Identification of Pulse Onset on Cerebral Blood Flow Velocity Waveforms: A Comparative Study.

The low cost, simple, noninvasive, and continuous measurement of cerebral blood flow velocity (CBFV) by transcranial Doppler is becoming a common clinical tool for the assessment of cerebral hemodynamics. CBFV monitoring can also help with noninvasive estimation of intracranial pressure and evaluation of mild traumatic brain injury. Reliable CBFV waveform analysis depends heavily on its accurate beat-to-beat delineation. However, CBFV is inherently contaminated with various types of noise/artifacts and has a wide range of possible pathological waveform morphologies. Thus, pulse onset detection is in general a challenging task for CBFV signal. In this paper, we conducted a comprehensive comparative analysis of three popular pulse onset detection methods using a large annotated dataset of 92,794 CBFV pulses-collected from 108 subarachnoid hemorrhage patients admitted to UCLA Medical Center. We compared these methods not only in terms of their accuracy and computational complexity, but also for their sensitivity to the selection of their parameters' values. The results of this comprehensive study revealed that using optimal values of the parameters obtained from sensitivity analysis, one method can achieve the highest accuracy for CBFV pulse onset detection with true positive rate (TPR) of 97.06% and positive predictivity value (PPV) of 96.48%, when error threshold is set to just less than 10 ms. We conclude that the high accuracy and low computational complexity of this method (average running time of 4ms/pulse) makes it a reliable algorithm for CBFV pulse onset detection.

A Simple Unsupervised, Real-time Clustering Method for Arterial Blood Pressure Signal Classification.

Biomedical signal analysis often depends on methods to detect and distinguish abnormal or high noise/artifact signal from normal signal. A novel unsupervised clustering method suitable for resource constrained embedded computing contexts, classifies arterial blood pressure (ABP) beat cycles as normal or abnormal. A cycle detection algorithm delineates beat cycles, so that each cycle can be modeled by a continuous time Fourier series decomposition. The Fourier series parameters are a discrete vector representation for the cycle along with the cycle period. The sequence of cycle parameter vectors is a non-uniform discrete time representation for the ABP signal that provides feature input for a clustering algorithm. Clustering uses a weighted distance function of normalized cycle parameters to ignore cycle differences due to natural and expected physiological modulations, such as respiratory modulation, while accounting for differences due to other causes, such as patient movement artifact. Challenging cardiac surgery patient signal examples indicate effectiveness.

Quantitative measures of EEG for prediction of outcome in cardiac arrest subjects treated with hypothermia: a literature review.

Cardiac arrest (CA) is the leading cause of death and disability in the United States. Early and accurate prediction of CA outcome can help clinicians and families to make a better-informed decision for the patient's healthcare. Studies have shown that electroencephalography (EEG) may assist in early prognosis of CA outcome. However, visual EEG interpretation is subjective, labor-intensive, and requires interpretation by a medical expert, i.e., neurophysiologists. These limiting factors may hinder the applicability of such testing as the prognostic method in clinical settings. Automatic EEG pattern recognition using quantitative measures can make the EEG analysis more objective and less time consuming. It also allows to detect and display hidden patterns that may be useful for the prognosis over longer time periods of monitoring. Given these potential benefits, there have been an increasing interest over the last few years in the development and employment of EEG quantitative measures to predict CA outcome. This paper extensively reviews the definition and efficacy of various measures that have been employed for the prediction of outcome in CA subjects undergoing hypothermia (a neuroprotection method that has become a standard of care to improve the functional recovery of CA patients after resuscitation). The review details the State-of-the-Art and provides some perspectives on what seems to be promising for the early and accurate prognostication of CA outcome using the quantitative measures of EEG.

An adaptive prediction method for signal fusion.

Many biomedical signal processing applications include the significant challenge of sensor data fusion. In this work, an adaptive prediction method fuses a relatively higher bandwidth, lower absolute accuracy (fast) signal with a relatively lower bandwidth, higher absolute accuracy (accurate) signal of the same quantity into a combined signal that is both fast and accurate. Iterative estimates of model parameters minimize a regularized mean square prediction error that arises from using the fast signal to predict the accurate signal. We illustrate the method by fusing a lower bandwidth porcine thermal dilution cardiac output signal with a relatively higher bandwidth, less accurate peripheral arterial pressure pulse contour cardiac output signal. The combined cardiac output signal has both thermal dilution accuracy and pulse contour bandwidth.

A novel low-complexity digital filter design for wearable ECG devices.

Wearable and implantable Electrocardiograph (ECG) devices are becoming prevailing tools for continuous real-time personal health monitoring. The ECG signal can be contaminated by various types of noise and artifacts (e.g., powerline interference, baseline wandering) that must be removed or suppressed for accurate ECG signal processing. Limited device size, power consumption and cost are critical issues that need to be carefully considered when designing any portable health monitoring device, including a battery-powered ECG device. This work presents a novel low-complexity noise suppression reconfigurable finite impulse response (FIR) filter structure for wearable ECG and heart monitoring devices. The design relies on a recently introduced optimally-factored FIR filter method. The new filter structure and several of its useful features are presented in detail. We also studied the hardware complexity of the proposed structure and compared it with the state-of-the-art. The results showed that the new ECG filter has a lower hardware complexity relative to the state-of-the-art ECG filters.

Prediction of the outcome in cardiac arrest patients undergoing hypothermia using EEG wavelet entropy.

Cardiac arrest (CA) is the leading cause of death in the United States. Induction of hypothermia has been found to improve the functional recovery of CA patients after resuscitation. However, there is no clear guideline for the clinicians yet to determine the prognosis of the CA when patients are treated with hypothermia. The present work aimed at the development of a prognostic marker for the CA patients undergoing hypothermia. A quantitative measure of the complexity of Electroencephalogram (EEG) signals, called wavelet sub-band entropy, was employed to predict the patients' outcomes. We hypothesized that the EEG signals of the patients who survived would demonstrate more complexity and consequently higher values of wavelet sub-band entropies. A dataset of 16-channel EEG signals collected from CA patients undergoing hypothermia at Long Beach Memorial Medical Center was used to test the hypothesis. Following preprocessing of the signals and implementation of the wavelet transform, the wavelet sub-band entropies were calculated for different frequency bands and EEG channels. Then the values of wavelet sub-band entropies were compared among two groups of patients: survived vs. non-survived. Our results revealed that the brain high frequency oscillations (between 64100 Hz) captured from the inferior frontal lobes are significantly more complex in the CA patients who survived (p-value <; 0.02). Given that the non-invasive measurement of EEG is part of the standard clinical assessment for CA patients, the results of this study can enhance the management of the CA patients treated with hypothermia.

Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machine.

BACKGROUND: Atrial fibrillation (AF) is the most common cardiac arrhythmia, and a major public health burden associated with significant morbidity and mortality. Automatic detection of AF could substantially help in early diagnosis, management and consequently prevention of the complications associated with chronic AF. In this paper, we propose a novel method for automatic AF detection. METHOD: Stationary wavelet transform and support vector machine have been employed to detect AF episodes. The proposed method eliminates the need for P-peak or R-Peak detection (a pre-processing step required by many existing algorithms), and hence its performance (sensitivity, specificity) does not depend on the performance of beat detection. The proposed method has been compared with those of the existing methods in terms of various measures including performance, transition time (detection delay associated with transitioning from a non-AF to AF episode), and computation time (using MIT-BIH Atrial Fibrillation database). RESULTS: Results of a stratified 2-fold cross-validation reveals that the area under the Receiver Operative Characteristics (ROC) curve of the proposed method is 99.5%. Moreover, the method maintains its high accuracy regardless of the choice of the parameters' values and even for data segments as short as 10s. Using the optimal values of the parameters, the method achieves sensitivity and specificity of 97.0% and 97.1%, respectively. DISCUSSION: The proposed AF detection method has high sensitivity and specificity, and holds several interesting properties which make it a suitable choice for practical applications.

A novel statistical model for arterial blood pressure signals.

This paper introduces a novel arterial blood pressure (ABP) signal model that generates statistically accurate synthetic signals with known characteristics. Using parameter identification from real ABP signals to form base parameter templates, our model applies stochastic processes to modulate cardiac cycle period and shape. A real-time control component modulates model parameters between cycle boundaries to emulate properties of real cardiovascular signals, such as arrhythmia, ectopic beats, resonances in the heart-rate variability spectrum, and respiratory cycle modulation of ABP signal amplitude. We present several examples to illustrate the capability of the proposed model.

Pediatric heart sound segmentation using hidden Markov model.

Recent advances in technology have enabled automatic cardiac auscultation using digital stethoscopes. This in turn creates the need for development of algorithms capable of automatic segmentation of heart sounds. Pediatric heart sound segmentation is a challenging task due to various confounding factors including the significant influence of respiration on children's heart sounds. The current work investigates the application of homomorphic filtering and Hidden Markov Model for the purpose of segmenting pediatric heart sounds. The efficacy of the proposed method is evaluated on the publicly available Pascal Challenge dataset and its performance is compared with those of three other existing methods. The results show that our proposed method achieves an accuracy of 92.4%±1.1% and 93.5%±1.1% in identifying the first and second heart sound components, respectively, and is superior to three other existing methods in terms of accuracy or computational complexity.