Autonomic cardiac control in animal models of cardiovascular diseases. I. Methods of variability analysis.

Analysis of heart rate variability (HRV) and blood pressure variability (BPV) and baroreceptor sensitivity (BRS) has become a proven tool in clinical cardiovascular diagnostics and risk stratification. In the present work, traditional and new methodological approaches for analysis of HRV, BPV, and BRS data are summarized. HRV, BPV, and BRS parameters were obtained from animal studies designed to study pathogenetic mechanisms of distinct cardiovascular diseases. Different non-linear approaches for HRV and BPV analysis are presented here, in particular measures of complexity based on symbolic dynamics. The dual sequence method (DSM) was employed for BRS analysis. In comparison to the classical measure of BRS using the average slope [ms/mm Hg], DSM offers additional information about the time-variant coupling between BPV and HRV. Since cardiovascular regulation shares common features among different species, data on HRV and BPV, as well as BRS, in animal models might be useful for understanding the pathogenetic mechanisms of cardiovascular diseases in humans and in the development of new diagnostic approaches.     

Motif-based protein sequence classification using neural networks.

We present a system for multi-class protein classification based on neural networks. The basic issue concerning the construction of neural network systems for protein classification is the sequence encoding scheme that must be used in order to feed the neural network. To deal with this problem we propose a method that maps a protein sequence into a numerical feature space using the matching scores of the sequence to groups of conserved patterns (called motifs) into protein families. We consider two alternative ways for identifying the motifs to be used for feature generation and provide a comparative evaluation of the two schemes. We also evaluate the impact of the incorporation of background features (2-grams) on the performance of the neural system. Experimental results on real datasets indicate that the proposed method is highly efficient and is superior to other well-known methods for protein classification.     

A Novel Hybrid Classification Model of Genetic Algorithms,Modified k-Nearest Neighbor and Developed Backpropagation Neural Network

Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher''s discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the proposed model in terms of classification accuracy is desirable, promising, and competitive to the existing state-of-the-art classification models.     

AUTONOMIC CONTROL OF HEART RATE AFTER EXERCISE IN TRAINED WRESTLERS

The objective of this study was to establish differences in vagal reactivation, through heart rate recovery and heart rate variability post exercise, in Brazilian jiu-jitsu wrestlers (BJJW). A total of 18 male athletes were evaluated, ten highly trained (HT) and eight moderately trained (MT), who performed a maximum incremental test. At the end of the exercise, the R-R intervals were recorded during the first minute of recovery. We calculated heart rate recovery (HRR_60s), and performed linear and non-linear (standard deviation of instantaneous beat-to-beat R-R interval variability – SD1) analysis of heart rate variability (HRV), using the tachogram of the first minute of recovery divided into four segments of 15 s each (0-15 s, 15-30 s, 30-45 s, 45-60 s). Between HT and MT individuals, there were statistically significant differences in HRR_60s (p <0.05) and in the non linear analysis of HRV from SD1_30-45s (p <0.05) and SD1_45-60s (p <0.05). The results of this research suggest that heart rate kinetics during the first minute after exercise are related to training level and can be used as an index for autonomic cardiovascular control in BJJW.     

Application of neural networks to the classification of pancreatic intraductal proliferative lesions.

The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and other tumours requiring pancreatic resection. Intraductal lesions were classified as low and high grade as previously described. The image analysis system consisted of a microscope, CCD camera combined with a PC and AnalySIS v. 2.11 software. The following texture characteristics were measured: variance of grey levels, features extracted from the grey levels correlation matrix and mean values, variance and standard deviation of the energy obtained from Laws matrices. Furthermore we used moments derived invariants and basic geometric data such as surface area, the minimum and maximum diameter and shape factor. The sets of data were randomly divided into training and testing groups. The training of the network using the back-propagation algorithm, and the final classification of data was carried out with a neural network simulator SNNS v. 4.1. We studied the efficacy of networks containing from one to three hidden layers. Using the best network, containing three hidden layers, the rate of correct classification of nuclei was 73%, and the rate of misdiagnosis was 3%; in 24% the network response was ambiguous. The present findings may serve as a starting point in search for methods facilitating early diagnosis of ductal pancreatic carcinoma.     

Sleep stages classification based on heart rate variability and random forest

An alternative technique for sleep stages classification based on heart rate variability (HRV) was presented in this paper. The simple subject specific scheme and a more practical subject independent scheme were designed to classify wake, rapid eye movement (REM) sleep and non-REM (NREM) sleep. 41 HRV features extracted from RR sequence of 45 healthy subjects were trained and tested through random forest (RF) method. Among the features, 25 were newly proposed or applied to sleep study for the first time. For the subject independent classifier, all features were normalized with our developed fractile values based method. Besides, the importance of each feature for sleep staging was also assessed by RF and the appropriate number of features was explored. For the subject specific classifier, a mean accuracy of 88.67% with Cohen's kappa statistic κ of 0.7393 was achieved. While the accuracy and κ dropped to 72.58% and 0.4627, respectively when the subject independent classifier was considered. Some new proposed HRV features even performed more effectively than the conventional ones. The proposed method could be used as an alternative or aiding technique for rough and convenient sleep stages classification.     

Wearable-Sensor-Based Classification Models of Faller Status in Older Adults

Wearable sensors have potential for quantitative, gait-based, point-of-care fall risk assessment that can be easily and quickly implemented in clinical-care and older-adult living environments. This investigation generated models for wearable-sensor based fall-risk classification in older adults and identified the optimal sensor type, location, combination, and modelling method; for walking with and without a cognitive load task. A convenience sample of 100 older individuals (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Participants also completed the Activities-specific Balance Confidence scale, Community Health Activities Model Program for Seniors questionnaire, six minute walk test, and ranked their fear of falling. Fall risk classification models were assessed for all sensor combinations and three model types: multi-layer perceptron neural network, naïve Bayesian, and support vector machine. The best performing model was a multi-layer perceptron neural network with input parameters from pressure-sensing insoles and head, pelvis, and left shank accelerometers (accuracy = 84%, F1 score = 0.600, MCC score = 0.521). Head sensor-based models had the best performance of the single-sensor models for single-task gait assessment. Single-task gait assessment models outperformed models based on dual-task walking or clinical assessment data. Support vector machines and neural networks were the best modelling technique for fall risk classification. Fall risk classification models developed for point-of-care environments should be developed using support vector machines and neural networks, with a multi-sensor single-task gait assessment.     

Evaluating and comparing performance of feature combinations of heart rate variability measures for cardiac rhythm classification

Automatic classification of cardiac arrhythmias using heart rate variability (HRV) analysis has been an important research topic in recent years. Explorations reveal that various HRV feature combinations can provide highly accurate models for some rhythm disorders. However, the proposed feature combinations lack a direct and carefully designed comparison. The goal of this work is to assess the various HRV feature combinations in classification of cardiac arrhythmias. In this setting, a total of 56 known HRV features are grouped in eight feature combinations. We evaluate and compare the combinations on a difficult problem of automatic classification between nine types of cardiac rhythms using three classification algorithms: support vector machines, AdaBoosted C4.5, and random forest. The effect of analyzed segment length on classification accuracy is also examined. The results demonstrate that there are three combinations that stand out the most, with total classification accuracy of roughly 85% on time segments of 20 s duration. A simple combination of time domain features is shown to be comparable to the more informed combinations, with only 1–4% worse results on average than the three best ones. Random forest and AdaBoosted C4.5 are shown to be comparably accurate, while support vector machines was less accurate (4–5%) on this problem. We conclude that the nonlinear features exhibit only a minor influence on the overall accuracy in discerning different arrhythmias. The analysis also shows that reasonably accurate arrhythmia classification lies in the range of 10–40 s, with a peak at 20 s, and a significant drop after 40 s.     

Are Complexity Metrics Reliable in Assessing HRV Control in Obese Patients During Sleep?

Obesity is associated with cardiovascular mortality. Linear methods, including time domain and frequency domain analysis, are normally applied on the heart rate variability (HRV) signal to investigate autonomic cardiovascular control, whose imbalance might promote cardiovascular disease in these patients. However, given the cardiac activity non-linearities, non-linear methods might provide better insight. HRV complexity was hereby analyzed during wakefulness and different sleep stages in healthy and obese subjects. Given the short duration of each sleep stage, complexity measures, normally extracted from long-period signals, needed be calculated on short-term signals. Sample entropy, Lempel-Ziv complexity and detrended fluctuation analysis were evaluated and results showed no significant differences among the values calculated over ten-minute signals and longer durations, confirming the reliability of such analysis when performed on short-term signals. Complexity parameters were extracted from ten-minute signal portions selected during wakefulness and different sleep stages on HRV signals obtained from eighteen obese patients and twenty controls. The obese group presented significantly reduced complexity during light and deep sleep, suggesting a deficiency in the control mechanisms integration during these sleep stages. To our knowledge, this study reports for the first time on how the HRV complexity changes in obesity during wakefulness and sleep. Further investigation is needed to quantify altered HRV impact on cardiovascular mortality in obesity.     

Selecting neural networks for a committee decision

To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. In contrast to the ordinary approach of utilizing all neural networks available to make a committee decision, we propose creating adaptive committees, which are specific for each input data point. A prediction network is used to identify classification neural networks to be fused for making a committee decision about a given input data point. The jth output value of the prediction network expresses the expectation level that the jth classification neural network will make a correct decision about the class label of a given input data point. The proposed technique is tested in three aggregation schemes, namely majority vote, averaging, and aggregation by the median rule and compared with the ordinary neural networks fusion approach. The effectiveness of the approach is demonstrated on two artificial and three real data sets.     

Analysis of heart rate variability for predicting cardiorespiratory events in infants

Cardiorespiratory events (CREs), including bradycardia and apnea, in infants are a major concern for physicians and families. Our hypothesis was that there is a difference in the heart rate variability (HRV) of infants who have CREs when compared to normal control infants. The purpose of this study was to develop CRE prediction models based on HRV measured during a polysomnographic (PSG) recording. ANCOVA analysis accounting for factors such as age and sleep state show a relationship between HRV variables and CRE. Prediction models, including neural networks and support vector machines, were developed to predict CRE within either (a) 1-week or (b) 1-month after the PSG. The support vector machine prediction accuracy, for CRE susceptibility one month after the PSG on an independent testing dataset, was 50.0% sensitivity and 82.6% specificity. Although the developed prediction models were not sufficiently accurate for clinical decision making, these results support the potential role of abnormalities in autonomic control of heart rate among infants at risk for CREs.     

A deep dense inception network for protein beta-turn prediction

Beta-turn prediction is useful in protein function studies and experimental design. Although recent approaches using machine-learning techniques such as support vector machine (SVM), neural networks, and K nearest neighbor have achieved good results for beta-turn prediction, there is still significant room for improvement. As previous predictors utilized features in a sliding window of 4-20 residues to capture interactions among sequentially neighboring residues, such feature engineering may result in incomplete or biased features and neglect interactions among long-range residues. Deep neural networks provide a new opportunity to address these issues. Here, we proposed a deep dense inception network (DeepDIN) for beta-turn prediction, which takes advantage of the state-of-the-art deep neural network design of dense networks and inception networks. A test on a recent BT6376 benchmark data set shows that DeepDIN outperformed the previous best tool BetaTPred3 significantly in both the overall prediction accuracy and the nine-type beta-turn classification accuracy. A tool, called MUFold-BetaTurn, was developed, which is the first beta-turn prediction tool utilizing deep neural networks. The tool can be downloaded at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldBetaTurn/download.html .     

Neural network schemes for detecting rare events in human genomic DNA

MOTIVATION: Many problems in molecular biology as well as other areas involve detection of rare events in unbalanced data. We develop two sample stratification schemes in conjunction with neural networks for rare event detection in such databases. Sample stratification is a technique for making each class in a sample have equal influence on decision making. The first scheme proposed stratifies a sample by adding up the weighted sum of the derivatives during the backward pass of training. The second scheme proposed uses a technique of modified bootstrap aggregating. After training neural networks with multiple sets of bootstrapped examples of the rare event classes and subsampled examples of common event classes, multiple voting for classification is performed. RESULTS: These two schemes make rare event classes have a better chance of being included in the sample used for training neural networks and thus improve the classification accuracy for rare event detection. The experimental performance of the two schemes using two sets of human DNA sequences as well as another set of Gaussian data indicates that proposed schemes have the potential of significantly improving accuracy of neural networks to recognize rare events.     

The labeled systems of multiple neural networks

This paper proposes an implementation scheme of K-class classification problem using systems of multiple neural networks. Usually, a multi-class problem is decomposed into simple sub-problems solved independently using similar single neural networks. For the reason that these sub-problems are not equivalent in their complexity, we propose a system that includes reinforced networks destined to solve complicated parts of the entire problem. Our approach is inspired from principles of the multi-classifiers systems and the labeled classification, which aims to improve performances of the networks trained by the Back-Propagation algorithm. We propose two implementation schemes based on both OAO (one-against-all) and OAA (one-against-one). The proposed models are evaluated using iris and human thigh databases.     

Impaired serotonergic regulation of heart rate may underlie reduced baroreflex sensitivity in an animal model of depression

Serotonin (5-HT) is crucial to normal reflex vagal modulation of heart rate (HR). Reduced baroreflex sensitivity [spontaneous baroreflex sensitivity (sBRS)] and HR variability (HRV) reflect impaired neural, particularly vagal, control of HR and are independently associated with depression. In conscious, telemetered Flinders-Sensitive Line (FSL) rats, a well-validated animal model of depression, we tested the hypothesis that cardiovascular regulatory abnormalities are present and associated with deficient serotonergic control of reflex cardiovagal function. In FSL rats and control Flinders-Resistant (FRL) and Sprague-Dawley (SD) rat strains, diurnal measurements of HR, arterial pressure (AP), activity, sBRS, and HRV were made. All strains had normal and similar diurnal variations in HR, AP, and activity. In FRL rats, HR was elevated, contributing to the reduced HRV and sBRS in this strain. In FSL rats, sBRS and high-frequency power HRV were reduced during the night, indicating reduced reflex cardiovagal activity. The ratio of low- to high-frequency bands of HRV was increased in FSL rats, suggesting a relative predominance of cardiac sympathetic and/or reflex activity compared with FRL and SD rats. These data show that conscious FSL rats have cardiovascular regulatory abnormalities similar to depressed humans. Acute changes in HR, AP, temperature, and sBRS in response to 8-hydroxy-2-(di-n-propylamino)tetralin, a 5-HT(1A), 5-HT(1B), and 5-HT(7) receptor agonist, were also determined. In FSL rats, despite inducing an exaggerated hypothermic effect, 8-hydroxy-2-(di-n-propylamino)tetralin did not decrease HR and AP or improve sBRS, suggesting impaired serotonergic neural control of cardiovagal activity. These data suggest that impaired serotonergic control of cardiac reflex function could be one mechanism linking reduced sBRS to increased cardiac risk in depression.     

An Efficient Automated Algorithm for Distinguishing Normal and Abnormal ECG Signal

ObjectiveThe present study aims to simulate an alarm system for online detecting normal electrocardiogram (ECG) signals from abnormal ECG so that an individual's heart condition can be accurately and quickly monitored at any moment, and any possible serious dangers can be prevented.Materials and methodsFirst, the data from Physionet database were used to analyze the ECG signal. The data were collected equally from both males and females, and the data length varied between several seconds to several minutes. The heart rate variability (HRV) signal, which reflects heart fluctuations in different time intervals, was used due to the low spatial accuracy of ECG signal and its time constraint, as well as the similarity of this signal with the normal signal in some diseases. In this study, the proposed algorithm provided a return map as well as extracted nonlinear features of the HRV signal, in addition to the application of the statistical characteristics of the signal. Then, artificial neural networks were used in the field of ECG signal processing such as multilayer perceptron (MLP) and support vector machine (SVM), as well as optimal features, to categorize normal signals from abnormal ones.ResultsIn this paper, the area under the curve (AUC) of the ROC was used to determine the performance level of introduced classifiers. The results of simulation in MATLAB medium showed that AUC for MLP and SVM neural networks was 89.3% and 94.7%, respectively. Also, the results of the proposed method indicated that the more nonlinear features extracted from the ECG signal could classify normal signals from the patient.ConclusionThe ECG signal representing the electrical activity of the heart at different time intervals involves some important information. The signal is considered as one of the common tools used by physicians to diagnose various cardiovascular diseases, but unfortunately the proper diagnosis of disease in many cases is accompanied by an error due to limited time accuracy and hiding some important information related to this signal from the physicians' vision leading to the risks of irreparable harm for patients. Based on the results, designing the proposed alarm system can help physicians with higher speed and accuracy in the field of diagnosing normal people from patients and can be used as a complementary system in hospitals.     

Comparing the HRV Time-Series Signals Acquired from Cannabis Consuming and Non-Consuming Indian Paddy-Field Workers by Recurrence Quantification Analysis

ObjectiveIn the last few decades, the consumption of cannabis-based products for recreational purposes has dramatically increased. Unfortunately, cannabis consumption has been associated with the incidences of cardiovascular diseases. Hence, there is a necessity for understanding the plausible mechanics of cardiophysiological changes due to cannabis consumption. Accordingly, the current study was designed to understand the suitability of the recurrence quantification analysis (RQA) method in detecting the changes in the heart rate variability (HRV) time-series signals due to the consumption of cannabis (bhang). Further, a machine learning model has been proposed for the automated detection of the cannabis takers.Materials and MethodsThe RQA of the HRV time-series signals from 200 healthy Indian male paddy-field workers were carried out. The obtained parameters were statistically analyzed using the Mann-Whitney U test. Further, the decision trees, weight-based feature ranking, and dimensionality reduction methods were employed for identifying the relevant features for the development of a suitable machine learning model.ResultsObservable changes in the patterns of the recurrence plots among the bhang consuming and non-consuming groups were noticed. However, there were no significant differences in the RQA parameters. Among the developed machine learning models, the SVM model obtained from the “Information gain ratio” feature selection method exhibited the highest accuracy (%) of 69.09 ± 9.33.ConclusionOur study suggests that the RQA method is not as effective as the time and frequency domain methods for detecting the alterations in the HRV time-series signals due to cannabis consumption. The SVM model was found to be the best model for the automated detection of cannabis takers. The selection of the features by the information gain ratio method played an important role in the development of the optimized SVM model.     

Learning vector quantizer in the investigation of thyroid lesions

OBJECTIVE: To investigate the capability of the learning vector quantizer (LVQ) in the discrimination of benign from malignant thyroid lesions. STUDY DESIGN: The study was performed on May-Grünwald-Giemsa-stained smears taken by fine needle aspiration (FNA). Using a custom image analysis system, 25 features that describe the size, shape and texture of approximately 100 nuclei were measured from each case. Statistical features were extracted from each case, and a linear regression analysis was performed to detect the statistically significant features. The cases were distributed by category, as follows: 100 cases of goiter and follicular adenomas, 11 cases of follicular carcinoma, 35 cases of papillary carcinoma, 24 cases of oncocytic adenoma, 8 cases of oncocytic carcinoma and 20 cases of Hashimoto thyroiditis. About 30% of the cases from each class were used for training two LVQ classifiers. The remaining 139 cases, out of a total of 198, were used as the test set. A classifier was used to discriminate into four classes and a second into two classes. RESULTS: The application of LVQ neural networks allows good discrimination between benign and malignant lesions (O.A. = 97.8). However, reliable discrimination of the cytologic types of the lesions was not obtained. CONCLUSION: These results indicate that the use of neural networks combined with image morphometry may offer useful information on the potential for malignancy of thyroid lesions and may improve the diagnostic accuracy of FNA of the thyroid gland, especially in cases of follicular neoplasms classified as suspicious for malignancy and in cases of oncocytic tumors.