Investigating the performance improvement of HRV Indices in CHF using feature selection methods based on backward elimination and statistical significance

EEG-based finger movement classification with intrinsic time-scale decomposition

Introduction

Brain-computer interfaces (BCIs) are systems that acquire the brain's electrical activity and provide control of external devices. Since electroencephalography (EEG) is the simplest non-invasive method to capture the brain's electrical activity, EEG-based BCIs are very popular designs. Aside from classifying the extremity movements, recent BCI studies have focused on the accurate coding of the finger movements on the same hand through their classification by employing machine learning techniques. State-of-the-art studies were interested in coding five finger movements by neglecting the brain's idle case (i.e., the state that brain is not performing any mental tasks). This may easily cause more false positives and degrade the classification performances dramatically, thus, the performance of BCIs. This study aims to propose a more realistic system to decode the movements of five fingers and the no mental task (NoMT) case from EEG signals.

Methods

In this study, a novel praxis for feature extraction is utilized. Using Proper Rotational Components (PRCs) computed through Intrinsic Time Scale Decomposition (ITD), which has been successfully applied in different biomedical signals recently, features for classification are extracted. Subsequently, these features were applied to the inputs of well-known classifiers and their different implementations to discriminate between these six classes. The highest classifier performances obtained in both subject-independent and subject-dependent cases were reported. In addition, the ANOVA-based feature selection was examined to determine whether statistically significant features have an impact on the classifier performances or not.

Results

As a result, the Ensemble Learning classifier achieved the highest accuracy of 55.0% among the tested classifiers, and ANOVA-based feature selection increases the performance of classifiers on five-finger movement determination in EEG-based BCI systems.

Discussion

When compared with similar studies, proposed praxis achieved a modest yet significant improvement in classification performance although the number of classes was incremented by one (i.e., NoMT).

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs

In recent studies, in the field of Brain-Computer Interface (BCI), researchers have focused on Motor Imagery tasks. Motor Imagery-based electroencephalogram (EEG) signals provide the interaction and communication between the paralyzed patients and the outside world for moving and controlling external devices such as wheelchair and moving cursors. However, current approaches in the Motor Imagery-BCI system design require effective feature extraction methods and classification algorithms to acquire discriminative features from EEG signals due to the non-linear and non-stationary structure of EEG signals. This study investigates the effect of statistical significance-based feature selection on binary and multi-class Motor Imagery EEG signal classifications. In the feature extraction process performed 24 different time-domain features, 15 different frequency-domain features which are energy, variance, and entropy of Fourier transform within five EEG frequency subbands, 15 different time-frequency domain features which are energy, variance, and entropy of Wavelet transform based on five EEG frequency subbands, and 4 different Poincare plot-based non-linear parameters are extracted from each EEG channel. A total of 1,364 Motor Imagery EEG features are supplied from 22 channel EEG signals for each input EEG data. In the statistical significance-based feature selection process, the best one among all possible combinations of these features is tried to be determined using the independent t-test and one-way analysis of variance (ANOVA) test on binary and multi-class Motor Imagery EEG signal classifications, respectively. The whole extracted feature set and the feature set that contain statistically significant features only are classified in this study. We implemented 6 and 7 different classifiers in multi-class and binary (two-class) classification tasks, respectively. The classification process is evaluated using the five-fold cross-validation method, and each classification algorithm is tested 10 times. These repeated tests provide to check the repeatability of the results. The maximum of 61.86 and 47.36% for the two-class and four-class scenarios, respectively, are obtained with Ensemble Subspace Discriminant among all these classifiers using selected features including only statistically significant features. The results reveal that the introduced statistical significance-based feature selection approach improves the classifier performances by achieving higher classifier performances with fewer relevant components in Motor Imagery task classification. In conclusion, the main contribution of the presented study is two-fold evaluation of non-linear parameters as an alternative to the commonly used features and the prediction of multiple Motor Imagery tasks using statistically significant features.

Integrative Nomogram of Computed Tomography Radiomics, Clinical, and Tumor Immune Features for Analysis of Disease-Free Survival of NSCLC Patients with Surgery

To improve prognosis of cancer patients and determine the integrative value for analysis of disease-free survival prediction, a clinic investigation was performed involving with 146 non-small cell lung cancer (NSCLC) patients (83 men and 73 women; mean age: 60.24 years ± 8.637) with a history of surgery. Their computed tomography (CT) radiomics, clinical records, and tumor immune features were firstly obtained and analyzed in this study. Histology and immunohistochemistry were also performed to establish a multimodal nomogram through the fitting model and cross-validation. Finally, Z test and decision curve analysis (DCA) were performed to evaluate and compare the accuracy and difference of each model. In all, seven radiomics features were selected to construct the radiomics score model. The clinicopathological and immunological factors model, including T stage, N stage, microvascular invasion, smoking quantity, family history of cancer, and immunophenotyping. The C-index of the comprehensive nomogram model on the training set and test set was 0.8766 and 0.8426 respectively, which was better than that of the clinicopathological-radiomics model (Z test, P =0.041<0.05), radiomics model and clinicopathological model (Z test, P =0.013<0.05 and P =0.0097<0.05). Integrative nomogram based on computed tomography radiomics, clinical and immunophenotyping can be served as effective imaging biomarker to predict DFS of hepatocellular carcinoma after surgical resection.

Improved autoregressive integrated moving average model for COVID-19 prediction by using statistical significance and clustering techniques

Purpose

The COVID-19 pandemic has affected more than 192 countries. The condition results in a respiratory illness (e.g., influenza) with signs and symptoms such as cold, cough, fever, and breathing difficulties. Predicting new instances of COVID-19 is always a challenging task.

Methods

This study improved the autoregressive integrated moving average (ARIMA)-based time series prediction model by incorporating statistical significance for feature selection and k-means clustering for outlier detection. The accuracy of the improved model (ARIMAI) was examined using World Health Organization's official data on the COVID-19 pandemic worldwide and compared with that of many modern, cutting-edge algorithms.

Results

The ARIMAI model (RSS score = 0.279, accuracy = 97.75%) outperformed the current ARIMA model (RSS score = 0.659, accuracy = 93%).

Conclusions

The ARIMAI model is not only an efficient but also a rapid and simple technique to forecast COVID-19 trends. The usage of this model enables the prediction of any disease that will affect patients in the future pandemics.

A Study on the Association between Korotkoff Sound Signaling and Chronic Heart Failure (CHF) Based on Computer-Assisted Diagnoses

Background

Korotkoff sound (KS) is an important indicator of hypertension when monitoring blood pressure. However, its utility in noninvasive diagnosis of Chronic heart failure (CHF) has rarely been studied.

Purpose

In this study, we proposed a method for signal denoising, segmentation, and feature extraction for KS, and a Bayesian optimization-based support vector machine algorithm for KS classification.

Methods

The acquired KS signal was resampled and denoised to extract 19 energy features, 12 statistical features, 2 entropy features, and 13 Mel Frequency Cepstrum Coefficient (MFCCs) features. A controlled trial based on the VALSAVA maneuver was carried out to investigate the relationship between cardiac function and KS. To classify these feature sets, the K-Nearest Neighbors (KNN), decision tree (DT), Naive Bayes (NB), ensemble (EM) classifiers, and the proposed BO-SVM were employed and evaluated using the accuracy (Acc), sensitivity (Se), specificity (Sp), Precision (Ps), and F1 score (F1).

Results

The ALSAVA maneuver indicated that the KS signal could play an important role in the diagnosis of CHF. Through comparative experiments, it was shown that the best performance of the classifier was obtained by BO-SVM, with Acc (85.0%), Se (85.3%), and Sp (84.6%).

Conclusions

In this study, a method for noise reduction, segmentation, and classification of KS was established. In the measured data set, our method performed well in terms of classification accuracy, sensitivity, and specificity. In light of this, we believed that the methods described in this paper can be applied to the early, noninvasive detection of heart disease as well as a supplementary monitoring technique for the prognosis of patients with CHF.

Functional Brain Imaging Reliably Predicts Bimanual Motor Skill Performance in a Standardized Surgical Task

Currently, there is a dearth of objective metrics for assessing bi-manual motor skills, which are critical for high-stakes professions such as surgery. Recently, functional near-infrared spectroscopy (fNIRS) has been shown to be effective at classifying motor task types, which can be potentially used for assessing motor performance level. In this work, we use fNIRS data for predicting the performance scores in a standardized bi-manual motor task used in surgical certification and propose a deep-learning framework 'Brain-NET' to extract features from the fNIRS data. Our results demonstrate that the Brain-NET is able to predict bi-manual surgical motor skills based on neuroimaging data accurately ( R2=0.73). Furthermore, the classification ability of the Brain-NET model is demonstrated based on receiver operating characteristic (ROC) curves and area under the curve (AUC) values of 0.91. Hence, these results establish that fNIRS associated with deep learning analysis is a promising method for a bedside, quick and cost-effective assessment of bi-manual skill levels.

Machine learning based congestive heart failure detection using feature importance ranking of multimodal features

In this study, we ranked the Multimodal Features extracted from Congestive Heart Failure (CHF) and Normal Sinus Rhythm (NSR) subjects. We categorized the ranked features into 1 to 5 categories based on Empirical Receiver Operating Characteristics (EROC) values. Instead of using all multimodal features, we use high ranking features for detection of CHF and normal subjects. We employed powerful machine learning techniques such as Decision Tree (DT), Naïve Bayes (NB), SVM Gaussian, SVM RBF and SVM Polynomial. The performance was measured in terms of Sensitivity, Specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), Accuracy, False Positive Rate (FPR), and area under the Receiver Operating characteristic Curve (AUC). The highest detection performance in terms of accuracy and AUC was obtained with all multimodal features using SVM Gaussian with Sensitivity (93.06%), Specificity (81.82%), Accuracy (88.79%) and AUC (0.95). Using the top five ranked features, the highest performance was obtained with SVM Gaussian yields accuracy (84.48%), AUC (0.86); top nine ranked features using Decision Tree and Naïve Bayes got accuracy (84.48%), AUC (0.88); last thirteen ranked features using SVM polynomial obtained accuracy (80.17%), AUC (0.84). The findings indicate that proposed approach with feature ranking can be very useful for automatic detection of congestive heart failure patients and can be very helpful for further decision making by the clinicians and physicians in order to decrease the mortality rate.

Detecting Congestive Heart Failure by Extracting Multimodal Features and Employing Machine Learning Techniques

The adaptability of heart to external and internal stimuli is reflected by the heart rate variability (HRV). Reduced HRV can be a predictor of negative cardiovascular outcomes. Based on the nonlinear, nonstationary, and highly complex dynamics of the controlling mechanism of the cardiovascular system, linear HRV measures have limited capability to accurately analyze the underlying dynamics. In this study, we propose an automated system to analyze HRV signals by extracting multimodal features to capture temporal, spectral, and complex dynamics. Robust machine learning techniques, such as support vector machine (SVM) with its kernel (linear, Gaussian, radial base function, and polynomial), decision tree (DT), k-nearest neighbor (KNN), and ensemble classifiers, were employed to evaluate the detection performance. Performance was evaluated in terms of specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC). The highest performance was obtained using SVM linear kernel (TA = 93.1%, AUC = 0.97, 95% CI [lower bound = 0.04, upper bound = 0.89]), followed by ensemble subspace discriminant (TA = 91.4%, AUC = 0.96, 95% CI [lower bound 0.07, upper bound = 0.81]) and SVM medium Gaussian kernel (TA = 90.5%, AUC = 0.95, 95% CI [lower bound = 0.07, upper bound = 0.86]). The results reveal that the proposed approach can provide an effective and computationally efficient tool for automatic detection of congestive heart failure patients.

Automated detection of shockable and non-shockable arrhythmia using novel wavelet-based ECG features

Malignant arrhythmia can lead to sudden cardiac death (SCD). Shockable arrhythmia can be terminated with device electrical shock therapies. Ventricular-tachycardia (VT) and ventricular fibrillation (VF) are responsive to electrical anti-tachycardia pacing therapy and defibrillation which help to restore normal electrical and mechanical function of the heart. In contrast, non-shockable arrhythmia like asystole and bradycardia are not responsive to electric shock therapy. Distinguishing between shockable and non-shockable arrhythmia is an important diagnostic challenge that has practical clinical relevance. It is difficult to accurately differentiate between these two types of arrhythmia by manual inspection of electrocardiogram (ECG) segments within the short time duration before triggering the device for electrical therapy. Automated defibrillators are equipped with automatic shockable arrhythmia detection algorithms based on ECG morphological features, which may possess variable diagnostic performance depending on machine models. In our work, we have designed a robust system using wavelet decomposition filter banks for extraction of features from the ECG signal and then classifying the features. We believe this method will improve the accuracy of discriminating between shockable and non-shockable arrhythmia compared with existing conventional algorithms. We used a novel three channel orthogonal wavelet filter bank, which extracted features from ECG epochs of duration 2 s to distinguish between shockable and non-shockable arrhythmia. The fuzzy, Renyi and sample entropies are extracted from the various wavelet coefficients and fed to support vector machine (SVM) classifier for automated classification. We have obtained an accuracy of 98.9%, sensitivity and specificity of 99.08% and 97.11.9%, respectively, using 10-fold cross validation. The area under the receiver operating characteristic has been found to be 0.99 with F1-score of 0.994. The system developed is more accurate than the existing algorithms. Hence, the proposed system can be employed in automated defibrillators inside and outside hospitals for emergency revival of patients suffering from SCD. These automated defibrillators can also be implanted inside the human body for automatic detection of potentially fatal shockable arrhythmia and to deliver an appropriate electric shock to the heart.

Multiscale Entropy Analysis with Low-Dimensional Exhaustive Search for Detecting Heart Failure

Multiscale entropy (MSE) is widely used to analyze heartbeat signals. Even though cardiologists do not use MSE to diagnose heart failure at present, these studies are of importance and have potential clinical applications. In previous studies, MSE discrimination between old congestive heart failure (CHF) and healthy individuals has remained controversial. Few studies have been published on the discrimination between them, using only MSE with machine learning for automatic multidimensional analysis, with reported testing accuracies of less than 86%. In this study, we determined the optimal MSE scales for discrimination by using a low-dimensional exhaustive search along with three classifiers—linear discriminant analysis (LDA), support vector machine (SVM), and k-nearest neighbor (KNN). In younger people (<55 years), the results showed an accuracy of up to 95.5% with two optimal MSE scales (2D) and up to 97.7% with four optimal MSE scales (4D) in discriminating between young CHF and healthy participants. In older people (≥55 years), the discrimination accuracy reached 90.1% using LDA in 2D, SVM in 3D (three optimal MSE scales), and KNN in 5D (five optimal MSE scales). LDA with a 3D exhaustive search also achieved 94.4% accuracy in older people. Therefore, the results indicate that MSE analysis can differentiate between CHF and healthy individuals of any age.

Diagnosing Various Severity Levels of Congestive Heart Failure Based on Long-Term HRV Signal

Previous studies have attempted to find autonomic differences of the cardiac system between the congestive heart failure (CHF) disease and healthy groups using a variety of algorithms of pattern recognition. By comparing previous literature, we have found that there are two shortcomings: 1) Previous studies have focused on improving the accuracy of models, but the number of features used has mostly exceeded 10, leading to poor generalization performance; 2) Previous works rarely distinguish the severity levels of CHF disease. In order to make up for these two shortcomings, we proposed two models: model A was used for distinguishing CHF patients from the normal people; model B was used for diagnosing the four severity levels of CHF disease. Based on long-term heart rate variability (HRV) (40000 intervals–8h) signals, we extracted linear and non-linear features from the inter-beat-interval (IBI) series. After that, the sequence forward selection algorithm (SFS) reduced the feature dimension. Finally, models with the best performance were selected through the leave-one-subject-out validation. For a total of 113 samples of the dataset, we applied the support vector machine classifier and five HRV features for CHF discrimination and obtained an accuracy of 97.35%. For a total of 41 samples of the dataset, we applied k-nearest-neighbor (K = 1) classifier and four HRV features for diagnosing four severity levels of CHF disease and got an accuracy of 87.80%. The contribution in this work was to use the fewer features to optimize our models by the leave-one-subject-out validation. The relatively good generalization performance of our models indicated their value in clinical application.

Computer-aided diagnosis of congestive heart failure using ECG signals - A review

The heart muscle pumps blood to vital organs, which is indispensable for human life. Congestive heart failure (CHF) is characterized by the inability of the heart to pump blood adequately throughout the body without an increase in intracardiac pressure. The symptoms include lung and peripheral congestion, leading to breathing difficulty and swollen limbs, dizziness from reduced delivery of blood to the brain, as well as arrhythmia. Coronary artery disease, myocardial infarction, and medical co-morbidities such as kidney disease, diabetes, and high blood pressure all take a toll on the heart and can impair myocardial function. CHF prevalence is growing worldwide. It afflicts millions of people globally, and is a leading cause of death. Hence, proper diagnosis, monitoring and management are imperative. The importance of an objective CHF diagnostic tool cannot be overemphasized. Standard diagnostic tests for CHF include chest X-ray, magnetic resonance imaging (MRI), nuclear imaging, echocardiography, and invasive angiography. However, these methods are costly, time-consuming, and they can be operator-dependent. Electrocardiography (ECG) is inexpensive and widely accessible, but ECG changes are typically not specific for CHF diagnosis. A properly designed computer-aided detection (CAD) system for CHF, based on the ECG, would potentially reduce subjectivity and provide quantitative assessment for informed decision-making. Herein, we review existing CAD for automatic CHF diagnosis, and highlight the development of an ECG-based CAD diagnostic system that employs deep learning algorithms to automatically detect CHF.

HEARTEN KMS - A knowledge management system targeting the management of patients with heart failure

The aim of this work is to present the HEARTEN Knowledge Management System, one of the core modules of the HEARTEN platform. The HEARTEN platform is an mHealth collaborative environment enabling the Heart Failure patients to self-manage the disease and remain adherent, while allowing the other ecosystem actors (healthcare professionals, caregivers, nutritionists, physical activity experts, psychologists) to monitor the patient's health progress and offer personalized, predictive and preventive disease management. The HEARTEN Knowledge Management System is a tool which provides multiple functionalities to the ecosystem actors for the assessment of the patient's condition, the estimation of the patient's adherence, the prediction of potential adverse events, the calculation of Heart Failure related scores, the extraction of statistics, the association of patient clinical and non-clinical data and the provision of alerts and suggestions. The innovation of this tool lays in the analysis of multi-parametric personal data coming from different sources, including for the first time breath and saliva biomarkers, and the use of machine learning techniques. The HEARTEN Knowledge Management System consists of nine modules. The accuracy of the KMS modules ranges from 78% to 95% depending on the module/functionality.

Unobtrusive Mattress-Based Identification of Hypertension by Integrating Classification and Association Rule Mining

Hypertension is one of the most common cardiovascular diseases, which will cause severe complications if not treated in a timely way. Early and accurate identification of hypertension is essential to prevent the condition from deteriorating further. As a kind of complex physiological state, hypertension is hard to characterize accurately. However, most existing hypertension identification methods usually extract features only from limited aspects such as the time-frequency domain or non-linear domain. It is difficult for them to characterize hypertension patterns comprehensively, which results in limited identification performance. Furthermore, existing methods can only determine whether the subjects suffer from hypertension, but they cannot give additional useful information about the patients’ condition. For example, their classification results cannot explain why the subjects are hypertensive, which is not conducive to further analyzing the patient’s condition. To this end, this paper proposes a novel hypertension identification method by integrating classification and association rule mining. Its core idea is to exploit the association relationship among multi-dimension features to distinguish hypertensive patients from normotensive subjects. In particular, the proposed method can not only identify hypertension accurately, but also generate a set of class association rules (CARs). The CARs are proved to be able to reflect the subject’s physiological status. Experimental results based on a real dataset indicate that the proposed method outperforms two state-of-the-art methods and three common classifiers, and achieves 84.4%, 82.5% and 85.3% in terms of accuracy, precision and recall, respectively.

Paroxysmal atrial fibrillation prediction based on HRV analysis and non-dominated sorting genetic algorithm III

This paper presents a method that able to predict the paroxysmal atrial fibrillation (PAF). The method uses shorter heart rate variability (HRV) signals when compared to existing methods, and achieves good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to electrically stabilize and prevent the onset of atrial arrhythmias with different pacing techniques. We propose a multi-objective optimization algorithm based on the non-dominated sorting genetic algorithm III for optimizing the baseline PAF prediction system, that consists of the stages of pre-processing, HRV feature extraction, and support vector machine (SVM) model. The pre-processing stage comprises of heart rate correction, interpolation, and signal detrending. After that, time-domain, frequency-domain, non-linear HRV features are extracted from the pre-processed data in feature extraction stage. Then, these features are used as input to the SVM for predicting the PAF event. The proposed optimization algorithm is used to optimize the parameters and settings of various HRV feature extraction algorithms, select the best feature subsets, and tune the SVM parameters simultaneously for maximum prediction performance. The proposed method achieves an accuracy rate of 87.7%, which significantly outperforms most of the previous works. This accuracy rate is achieved even with the HRV signal length being reduced from the typical 30 min to just 5 min (a reduction of 83%). Furthermore, another significant result is the sensitivity rate, which is considered more important that other performance metrics in this paper, can be improved with the trade-off of lower specificity.

Informative Nature and Nonlinearity of Lagged Poincaré Plots Indices in Analysis of Heart Rate Variability

Lagged Poincaré plots have been successful in characterizing abnormal cardiac function. However, the current research practices do not favour any specific lag of Poincaré plots, thus complicating the comparison of results of different researchers in their analysis of heart rate of healthy subjects and patients. We researched the informative nature of lagged Poincaré plots in different states of the autonomic nervous system. It was tested in three models: different age groups, groups with different balance of autonomous regulation, and in hypertensive patients. Correlation analysis shows that for lag l = 6, SD1/SD2 has weak (r = 0.33) correlation with linear parameters of heart rate variability (HRV). For l more than 6 it displays even less correlation with linear parameters, but the changes in SD1/SD2 become statistically insignificant. Secondly, surrogate data tests show that the real SD1/SD2 is statistically different from its surrogate value and the conclusion could be made that the heart rhythm has nonlinear properties. Thirdly, the three models showed that for different functional states of the autonomic nervous system (ANS), SD1/SD2 ratio varied only for lags l = 5 and 6. All of this allow to us to give cautious recommendation to use SD1/SD2 with lags 5 and 6 as a nonlinear characteristic of HRV. The received data could be used as the basis for continuing the research in standardisation of nonlinear analytic methods.

Automated detection of atrial fibrillation episode using novel heart rate variability features

Atrial fibrillation (AF) is one of the most common life-threatening arrhythmia affecting around six million adults in the US. Typical detection of AF requires tedious and manual analysis of ECG which can often delay medical intervention. With the advent of wearable devices that can accurately record the time interval between two heartbeats (RR interval), automated and timely detection of AF is now possible. In this paper, we engineer novel heart rate variability features based on linear and non-linear dynamics of RR intervals. Unlike complex features extracted from ECG signals, these features can be easily obtained using wearable sensors. We propose automated classifiers to detect AF episodes and also compare the performance of different classifiers. Our proposed classifier has a very high sensitivity (98%) and specificity (95%) and outperforms prior published works.

Multiscale Entropy Analysis of the Differential RR Interval Time Series Signal and Its Application in Detecting Congestive Heart Failure

Cardiovascular systems essentially have multiscale control mechanisms. Multiscale entropy (MSE) analysis permits the dynamic characterization of the cardiovascular time series for both short-term and long-term processes, and thus can be more illuminating. The traditional MSE analysis for heart rate variability (HRV) is performed on the original RR interval time series (named as MSE_RR). In this study, we proposed an MSE analysis for the differential RR interval time series signal, named as MSE_dRR. The motivation of using the differential RR interval time series signal is that this signal has a direct link with the inherent non-linear property of electrical rhythm of the heart. The effectiveness of the MSE_RR and MSE_dRR were tested and compared on the long-term MIT-Boston’s Beth Israel Hospital (MIT-BIH) 54 normal sinus rhythm (NSR) and 29 congestive heart failure (CHF) RR interval recordings, aiming to explore which one is better for distinguishing the CHF patients from the NSR subjects. Four RR interval length for analysis were used ( N = 500 , N = 1000 , N = 2000 and N = 5000 ). The results showed that MSE_RR did not report significant differences between the NSR and CHF groups at several scales for each RR segment length type (Scales 7, 8 and 10 for N = 500 , Scales 3 and 10 for N = 1000 , Scales 2 and 3 for both N = 2000 and N = 5000 ). However, the new MSE_dRR gave significant separation for the two groups for all RR segment length types except N = 500 at Scales 9 and 10. The area under curve (AUC) values from the receiver operating characteristic (ROC) curve were used to further quantify the performances. The mean AUC of the new MSE_dRR from Scales 1–10 are 79.5%, 83.1%, 83.5% and 83.1% for N = 500 , N = 1000 , N = 2000 and N = 5000 , respectively, whereas the mean AUC of MSE_RR are only 68.6%, 69.8%, 69.6% and 67.1%, respectively. The five-fold cross validation support vector machine (SVM) classifier reports the classification Accuracy ( A c c ) of MSE_RR as 73.5%, 75.9% and 74.6% for N = 1000 , N = 2000 and N = 5000 , respectively, while for the new MSE_dRR analysis accuracy was 85.5%, 85.6% and 85.6%. Different biosignal editing methods (direct deletion and interpolation) did not change the analytical results. In summary, this study demonstrated that compared with MSE_RR, MSE_dRR reports better statistical stability and better discrimination ability for the NSR and CHF groups.

Automated diagnosis of congestive heart failure using dual tree complex wavelet transform and statistical features extracted from 2s of ECG signals

Identification of alarming features in the electrocardiogram (ECG) signal is extremely significant for the prediction of congestive heart failure (CHF). ECG signal analysis carried out using computer-aided techniques can speed up the diagnosis process and aid in the proper management of CHF patients. Therefore, in this work, dual tree complex wavelets transform (DTCWT)-based methodology is proposed for an automated identification of ECG signals exhibiting CHF from normal. In the experiment, we have performed a DTCWT on ECG segments of 2s duration up to six levels to obtain the coefficients. From these DTCWT coefficients, statistical features are extracted and ranked using Bhattacharyya, entropy, minimum redundancy maximum relevance (mRMR), receiver-operating characteristics (ROC), Wilcoxon, t-test and reliefF methods. Ranked features are subjected to k-nearest neighbor (KNN) and decision tree (DT) classifiers for automated differentiation of CHF and normal ECG signals. We have achieved 99.86% accuracy, 99.78% sensitivity and 99.94% specificity in the identification of CHF affected ECG signals using 45 features. The proposed method is able to detect CHF patients accurately using only 2s of ECG signal length and hence providing sufficient time for the clinicians to further investigate on the severity of CHF and treatments.

Heart Failure: Diagnosis, Severity Estimation and Prediction of Adverse Events Through Machine Learning Techniques

Heart failure is a serious condition with high prevalence (about 2% in the adult population in developed countries, and more than 8% in patients older than 75 years). About 3-5% of hospital admissions are linked with heart failure incidents. Heart failure is the first cause of admission by healthcare professionals in their clinical practice. The costs are very high, reaching up to 2% of the total health costs in the developed countries. Building an effective disease management strategy requires analysis of large amount of data, early detection of the disease, assessment of the severity and early prediction of adverse events. This will inhibit the progression of the disease, will improve the quality of life of the patients and will reduce the associated medical costs. Toward this direction machine learning techniques have been employed. The aim of this paper is to present the state-of-the-art of the machine learning methodologies applied for the assessment of heart failure. More specifically, models predicting the presence, estimating the subtype, assessing the severity of heart failure and predicting the presence of adverse events, such as destabilizations, re-hospitalizations, and mortality are presented. According to the authors' knowledge, it is the first time that such a comprehensive review, focusing on all aspects of the management of heart failure, is presented.

Paroxysmal atrial fibrillation prediction method with shorter HRV sequences

This paper proposes a method that predicts the onset of paroxysmal atrial fibrillation (PAF), using heart rate variability (HRV) segments that are shorter than those applied in existing methods, while maintaining good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to stabilize (electrically) and prevent the onset of atrial arrhythmias with different pacing techniques. We investigate the effect of HRV features extracted from different lengths of HRV segments prior to PAF onset with the proposed PAF prediction method. The pre-processing stage of the predictor includes QRS detection, HRV quantification and ectopic beat correction. Time-domain, frequency-domain, non-linear and bispectrum features are then extracted from the quantified HRV. In the feature selection, the HRV feature set and classifier parameters are optimized simultaneously using an optimization procedure based on genetic algorithm (GA). Both full feature set and statistically significant feature subset are optimized by GA respectively. For the statistically significant feature subset, Mann-Whitney U test is used to filter non-statistical significance features that cannot pass the statistical test at 20% significant level. The final stage of our predictor is the classifier that is based on support vector machine (SVM). A 10-fold cross-validation is applied in performance evaluation, and the proposed method achieves 79.3% prediction accuracy using 15-minutes HRV segment. This accuracy is comparable to that achieved by existing methods that use 30-minutes HRV segments, most of which achieves accuracy of around 80%. More importantly, our method significantly outperforms those that applied segments shorter than 30 minutes.

Assessing heart rate variability through wavelet-based statistical measures

Because of its utility in the investigation and diagnosis of clinical abnormalities, heart rate variability (HRV) has been quantified with both time and frequency analysis tools. Recently, time-frequency methods, especially wavelet transforms, have been applied to HRV. In the current study, a complementary computational approach is proposed wherein continuous wavelet transforms are applied directly to ECG signals to quantify time-varying frequency changes in the lower bands. Such variations are compared for resting and lower body negative pressure (LBNP) conditions using statistical and information-theoretic measures, and compared with standard HRV metrics. The latter confirm the expected lower variability in the LBNP condition due to sympathetic nerve activity (e.g. RMSSD: p=0.023; SDSD: p=0.023; LF/HF: p=0.018). Conversely, using the standard Morlet wavelet and a new transform based on windowed complex sinusoids, wavelet analysis of the ECG within the observed range of heart rate (0.5-1.25Hz) exhibits significantly higher variability, as measured by frequency band roughness (Morlet CWT: p=0.041), entropy (Morlet CWT: p=0.001), and approximate entropy (Morlet CWT: p=0.004). Consequently, this paper proposes that, when used with well-established HRV approaches, time-frequency analysis of ECG can provide additional insights into the complex phenomenon of heart rate variability.

Computation of nonlinear parameters of heart rhythm using short time ECG segments

We propose the method to compute the nonlinear parameters of heart rhythm (correlation dimension D₂ and correlation entropy K₂) using 5-minute ECG recordings preferred for screening of population. Conversion of RR intervals' time series into continuous function x(t) allows getting the new time series with different sampling rate dt. It has been shown that for all dt (250, 200, 125, and 100 ms) the cross-plots of D₂ and K₂ against embedding dimension m for phase-space reconstruction start to level off at m = 9. The sample size N at different sampling rates varied from 1200 at dt = 250 ms to 3000 at dt = 100 ms. Along with, the D₂ and K₂ means were not statistically different; that is, the sampling rate did not influence the results. We tested the feasibility of the method in two models: nonlinear heart rhythm dynamics in different states of autonomous nervous system and age-related characteristics of nonlinear parameters. According to the acquired data, the heart rhythm is more complex in childhood and adolescence with more influential parasympathetic influence against the background of elevated activity of sympathetic autonomous nervous system.