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.

Regression analysis for detecting epileptic seizure with different feature extracting strategies.

Due to the excitability of neurons in the brain, a neurological disorder is produced known as epilepsy. The brain activity of patients suffering from epilepsy is monitored through electroencephalography (EEG). The multivariate nature of features from time domain, frequency domain, complexity and wavelet entropy based, and the statistical features were extracted from healthy and epileptic subjects using the Bonn University database and seizure and non-seizure intervals using the CHB MIT database. The robust machine learning regression methods based on regression, support vector regression (SVR), regression tree (RT), ensemble regression, Gaussian process regression (GPR) were employed for detecting and predicting epileptic seizures. Performance was measured in terms of root mean square error (RMSE), squared error, mean square error (MSE) and mean absolute error (MAE). Moreover, detailed optimization was performed using a RT to predict the selected features from each feature category. A deeper analysis was conducted on features and tree regression methods where optimal RMSE and MSE results were obtained. The best optimal performance was obtained using the ensemble boosted regression tree (BRT) and exponential GPR with an RMSE of 0.47, an MSE (0.22), an R Square (RS) (0.25) and an MAE (0.30) using the Bonn University database and support vector machine (SVM) fine Gaussian with RMSE (0.63634), RS (0.03), MSE (0.40493) and MAE (0.31744); squared exponential GPR and rational quadratic GPR with an RMSE of 0.63841, an RS (0.03), an MSE (0.40757) and an MAE (0.3472) was obtained using the CHB MIT database. A further deeper analysis for the prediction of selected features was performed on an RT to compute the optimal feasible point, observed and estimated function values, function evaluation time, objective function evaluation time and overall elapsed time.

Detecting Brain Tumor using Machines Learning Techniques Based on Different Features Extracting Strategies.

BACKGROUND: Brain tumor is the leading cause of death worldwide. It is obvious that the chances of survival can be increased if the tumor is identified and properly classified at an initial stage. MRI (Magnetic Resonance Imaging) is one source of brain tumors detection tool and is extensively used in the diagnosis of brain to detect blood clots. In the past, many researchers developed Computer-Aided Diagnosis (CAD) systems that help the radiologist to detect the abnormalities in an efficient manner. OBJECTIVE: The aim of this research is to improve the brain tumor detection performance by proposing a multimodal feature extracting strategy and employing machine learning techniques. METHODS: In this study, we extracted multimodal features such as texture, morphological, entropybased, Scale Invariant Feature Transform (SIFT), and Elliptic Fourier Descriptors (EFDs) from brain tumor imaging database. The tumor was detected using robust machine learning techniques such as Support Vector Machine (SVM) with kernels: polynomial, Radial Base Function (RBF), Gaussian; Decision Tree (DT), and Naïve Bayes. Most commonly used Jack-knife 10-fold Cross- Validation (CV) was used for testing and validation of dataset. RESULTS: The performance was evaluated in terms of specificity, sensitivity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), False Positive Rate (FPR), Total Accuracy (TA), Area under the receiver operating Curve (AUC), and P-value. The highest performance of 100% in terms of Specificity, Sensitivity, PPV, NPV, TA, AUC using Naïve Bayes classifiers based on entropy, morphological, SIFT and texture features followed by Decision Tree classifier with texture features (TA=97.81%, AUC=1.0) and SVM polynomial kernel with texture features (TA=94.63%). The highest significant p-value was obtained using SVM polynomial with texture features (P-value 2.65e-104) followed by SVM RB with texture features (P-value 1.96e-98). CONCLUSION: The results reveal that Naïve Bayes followed by Decision Tree gives highest detection accuracy based on entropy, morphological, SIFT and texture features.

Studying the dynamics of interbeat interval time series of healthy and congestive heart failure subjects using scale based symbolic entropy analysis.

Considerable interest has been devoted for developing a deeper understanding of the dynamics of healthy biological systems and how these dynamics are affected due to aging and disease. Entropy based complexity measures have widely been used for quantifying the dynamics of physical and biological systems. These techniques have provided valuable information leading to a fuller understanding of the dynamics of these systems and underlying stimuli that are responsible for anomalous behavior. The single scale based traditional entropy measures yielded contradictory results about the dynamics of real world time series data of healthy and pathological subjects. Recently the multiscale entropy (MSE) algorithm was introduced for precise description of the complexity of biological signals, which was used in numerous fields since its inception. The original MSE quantified the complexity of coarse-grained time series using sample entropy. The original MSE may be unreliable for short signals because the length of the coarse-grained time series decreases with increasing scaling factor τ, however, MSE works well for long signals. To overcome the drawback of original MSE, various variants of this method have been proposed for evaluating complexity efficiently. In this study, we have proposed multiscale normalized corrected Shannon entropy (MNCSE), in which instead of using sample entropy, symbolic entropy measure NCSE has been used as an entropy estimate. The results of the study are compared with traditional MSE. The effectiveness of the proposed approach is demonstrated using noise signals as well as interbeat interval signals from healthy and pathological subjects. The preliminary results of the study indicate that MNCSE values are more stable and reliable than original MSE values. The results show that MNCSE based features lead to higher classification accuracies in comparison with the MSE based features.

Prostate cancer detection using machine learning techniques by employing combination of features extracting strategies.

Prostate is a second leading causes of cancer deaths among men. Early detection of cancer can effectively reduce the rate of mortality caused by Prostate cancer. Due to high and multiresolution of MRIs from prostate cancer require a proper diagnostic systems and tools. In the past researchers developed Computer aided diagnosis (CAD) systems that help the radiologist to detect the abnormalities. In this research paper, we have employed novel Machine learning techniques such as Bayesian approach, Support vector machine (SVM) kernels: polynomial, radial base function (RBF) and Gaussian and Decision Tree for detecting prostate cancer. Moreover, different features extracting strategies are proposed to improve the detection performance. The features extracting strategies are based on texture, morphological, scale invariant feature transform (SIFT), and elliptic Fourier descriptors (EFDs) features. The performance was evaluated based on single as well as combination of features using Machine Learning Classification techniques. The Cross validation (Jack-knife k-fold) was performed and performance was evaluated in term of receiver operating curve (ROC) and specificity, sensitivity, Positive predictive value (PPV), negative predictive value (NPV), false positive rate (FPR). Based on single features extracting strategies, SVM Gaussian Kernel gives the highest accuracy of 98.34% with AUC of 0.999. While, using combination of features extracting strategies, SVM Gaussian kernel with texture + morphological, and EFDs + morphological features give the highest accuracy of 99.71% and AUC of 1.00.

Quantifying the dynamics of electroencephalographic (EEG) signals to distinguish alcoholic and non-alcoholic subjects using an MSE based K-d tree algorithm.

In this paper, we have employed K-d tree algorithmic based multiscale entropy analysis (MSE) to distinguish alcoholic subjects from non-alcoholic ones. Traditional MSE techniques have been used in many applications to quantify the dynamics of physiological time series at multiple temporal scales. However, this algorithm requires O(N2), i.e. exponential time and space complexity which is inefficient for long-term correlations and online application purposes. In the current study, we have employed a recently developed K-d tree approach to compute the entropy at multiple temporal scales. The probability function in the entropy term was converted into an orthogonal range. This study aims to quantify the dynamics of the electroencephalogram (EEG) signals to distinguish the alcoholic subjects from control subjects, by inspecting various coarse grained sequences formed at different time scales, using traditional MSE and comparing the results with fast MSE (fMSE). The performance was also measured in terms of specificity, sensitivity, total accuracy and receiver operating characteristics (ROC). Our findings show that fMSE, with a K-d tree algorithmic approach, improves the reliability of the entropy estimation in comparison with the traditional MSE. Moreover, this new technique is more promising to characterize the physiological changes having an affect at multiple time scales.

Symbolic time series analysis of electroencephalographic (EEG) epileptic seizure and brain dynamics with eye-open and eye-closed subjects during resting states.

OBJECTIVE: Epilepsy is a neuronal disorder for which the electrical discharge in the brain is synchronized, abnormal and excessive. To detect the epileptic seizures and to analyse brain activities during different mental states, various methods in non-linear dynamics have been proposed. This study is an attempt to quantify the complexity of control and epileptic subject with and without seizure as well as to distinguish eye-open (EO) and eye-closed (EC) conditions using threshold-based symbolic entropy. METHODS: The threshold-dependent symbolic entropy was applied to distinguish the healthy and epileptic subjects with seizure and seizure-free intervals (i.e. interictal and ictal) as well as to distinguish EO and EC conditions. The original time series data was converted into symbol sequences using quantization level, and word series of symbol sequences was generated using a word length of three or more. Then, normalized corrected Shannon entropy (NCSE) was computed to quantify the complexity. The NCSE values were not following the normal distribution, and the non-parametric Mann-Whitney-Wilcoxon (MWW) test was used to find significant differences among various groups at 0.05 significance level. The values of NCSE were presented in a form of topographic maps to show significant brain regions during EC and EO conditions. The results of the study were compared to those of the multiscale entropy (MSE). RESULTS: The results indicated that the dynamics of healthy subjects are more complex compared to epileptic subjects (during seizure and seizure-free intervals) in both EO and EC conditions. The comparison of the dynamics of epileptic subjects revealed that seizure-free intervals are more complex than seizure intervals. The dynamics of healthy subjects during EO conditions are more complex compared to those during EC conditions. Further, the results clearly demonstrated that threshold-dependent symbolic entropy outperform MSE in distinguishing different physiological and pathological conditions. CONCLUSION: The threshold symbolic entropy has provided improved accuracy in quantifying the dynamics of healthy and epileptic subjects during EC an EO conditions for each electrode compared to the MSE.