Time-domain heart rate dynamics in the prognosis of progressive atherosclerosis.

BACKGROUND AND AIM: The regular uptake of a high-fat diet (HFD) with changing lifestyle causes atherosclerosis leading to cardiovascular diseases and autonomic dysfunction. Therefore, the current study aimed to investigate the correlation of autonomic activity to lipid and atherosclerosis markers. Further, the study proposes a support vector machine (SVM) based model in the prediction of atherosclerosis severity. METHODS AND RESULTS: The Lead-II electrocardiogram and blood markers were measured from both the control and the experiment subjects each week for nine consecutive weeks. The time-domain heart rate variability (HRV) parameters were derived, and the significance level was tested using a one-way Analysis of Variance. The correlation analysis was performed to determine the relation between autonomic parameters and lipid and atherosclerosis markers. The statistically significant time-domain values were used as features of the SVM. The observed results demonstrated the reduced time domain HRV parameters with the increase in lipid and atherosclerosis index markers with the progressive atherosclerosis severity. The correlation analysis revealed a negative association between time-domain HRV parameters with lipid and atherosclerosis parameters. The percentage accuracy increases from 86.58% to 98.71% with the increase in atherosclerosis severity with regular consumption of HFD. CONCLUSIONS: Atherosclerosis causes autonomic dysfunction with reduced HRV. The negative correlation between autonomic parameters and lipid profile and atherosclerosis indexes marker revealed the potential role of vagal activity in the prognosis of atherosclerosis progression. The support vector machine presented a respectable accuracy in the prediction of atherosclerosis severity from the control group.

Molecular characterization and in-depth genomic analysis to unravel the pathogenic features of an environmental isolate Enterobacter sp. S-33.

Enterobacter species represent widely distributed opportunistic pathogens, commonly associated with plants and humans. In the present study, we performed a detailed molecular characterization as well as genomic study of a type VI secretion system (T6SS) bacterium belonging to member of the family Enterobacteriaceae and named Enterobacter sp. S-33. The comparative sequence analysis of the 16S rRNA gene showed that the strain was closely related to other Enterobacter species. The complete genome of the strain with a genome size of 4.6 Mbp and GC-content of 55.63% was obtained through high-quality sequencing. The genomic analysis with online tools unravelled the various genes belonging to the bacterial secretion system, antibiotic resistance, virulence, efflux pumps, etc. The isolate showed the motility behavior that contributes to Enterobacter persistence in a stressed environment and further supports infections. PCR amplification and further sequencing confirmed the presence of drug-efflux genes acrA, acrB, and outer membrane genes, viz. OmpA, OmpC, and OmpF. The cell surface hydrophobicity and co-aggregation assay against different bacterial strains illustrated its putative pathogenic nature. Genome mining identified various biosynthetic gene clusters (BGCs) corresponding to non-ribosomal proteins (NRPS), siderophore, and arylpolyene production. Briefly, genome sequencing and detailed characterization of environmental Enterobacter isolate will assist in understanding the epidemiology of Enterobacter species, and the further prevention and treatment of infectious diseases caused by these broad-host range species.

Secretome analysis of an environmental isolate Enterobacter sp. S-33 identifies proteins related to pathogenicity.

Enterobacter species are responsible for causing infections of the lower respiratory tract, urinary tract, meninges, etc. Proteins secreted by these species may act as determinants of host-pathogen interaction and play a role in virulence. Among the secreted proteins, the Type VI secretion system (T6SS) acts as a molecular nanomachine to deliver many effector proteins directly into prey cells in a contact-dependent manner. The secreted proteins may provide an idea for the interaction of bacteria to their environment and an understanding of the role of these proteins for their role in bacterial physiology and behaviour. Therefore, aim of this study was to characterize the secreted proteins in the culture supernatant by a T6SS bacterium Enterobacter sp. S-33 using nano-LC-MS/MS tool. Using a combined mass spectrometry and bioinformatics approach, we identified a total of 736 proteins in the secretome. Bioinformatics analysis predicting subcellular localization identified 110 of the secreted proteins possessed signal sequences. By gene ontology analysis, more than 80 proteins of the secretome were classified into biological or molecular functions. More than 20 percent of secretome proteins were virulence proteins including T6SS proteins, proteins involved in adherence and fimbriae formation, molecular chaperones, outer membrane proteins, serine proteases, antimicrobial, biofilm, exotoxins, etc. In summary, the results of the present study of the S-33 secretome provide a basis for understanding the possible pathogenic mechanisms and future investigation by detailed experimental approach will provide a confirmation of secreted virulence proteins in the exact role of virulence using the in vivo model.

Heart rate dynamics in the prediction of coronary artery disease and myocardial infarction using artificial neural network and support vector machine.

BACKGROUND: Atherosclerosis leads to coronary artery disease (CAD) and myocardial infarction (MI), a major cause of morbidity and mortality worldwide. The computer-aided prognosis of atherosclerotic events with the electrocardiogram (ECG) derived heart rate variability (HRV) can be a robust method in the prognosis of atherosclerosis events. METHODS: A total of 70 male subjects aged 55 ± 5 years participated in the study. The lead-II ECG was recorded and sampled at 200 Hz. The tachogram was obtained from the ECG signal and used to extract twenty-five HRV features. The one-way Analysis of variance (ANOVA) test was performed to find the significant differences between the CAD, MI, and control subjects. Features were used in the training and testing of a two-class artificial neural network (ANN) and support vector machine (SVM). RESULTS: The obtained results revealed depressed HRV under atherosclerosis. Accuracy of 100% was obtained in classifying CAD and MI subjects from the controls using ANN. Accuracy was 99.6% with SVM, and in the classification of CAD from MI subjects using SVM and ANN, 99.3% and 99.0% accuracy was obtained respectively. CONCLUSIONS: Depressed HRV has been suggested to be a marker in the identification of atherosclerotic events. The good accuracy observed in classification between control, CAD, and MI subjects, revealed it to be a non-invasive cost-effective approach in the prognosis of atherosclerotic events.

Heart rate variability time domain features in automated prediction of diabetes in rat.

Diabetes is a very common occurring disease, diagnosed by hyperglycemia. The established mode of diagnosis is the analysis of blood glucose level with the help of a hand-held glucometer. Nowadays, it is also known for affecting multi-organ functions, particularly the microvasculature of the cardiovascular system. In this work, an alternative diagnostic system based on the heart rate variability (HRV) analysis and artificial neural network (ANN) and support vector machine (SVM) have been proposed. The experiment and data recording has been performed on male Wister rats of 10-12 week of age and 200 ± 20 gm of weight. The digital lead-I electrocardiogram (ECG) data are recorded from control (n = 5) and Streptozotocin-induced diabetic rats (n = 5). Nine time-domain linear HRV parameters are computed from 60 s of ECG data epochs and used for the training and testing of backpropagation ANN and SVM. Total 526 (334 Control and 192 diabetics) such datasets are computed for the testing of ANN for the identification of the diabetic conditions. The ANN has been optimized for architecture 9:5:1 (Input: hidden: output neurons, respectively) with the optimized learning rate parameter at 0.02. With this network, a very good classification accuracy of 96.2% is achieved. While similar accuracy of 95.2% is attained using SVM. Owing to the successful implementation of HRV parameters based automated classifiers for diabetic conditions, a non-invasive, ECG based online prognostic system can be developed for accurate and non-invasive prediction of the diabetic condition.

Time-domain heart rate variability-based computer-aided prognosis of lung cancer.

OBJECTIVE: Incidence of lung cancer (LC) is increasing day by day with exposure to smoke, radiation, and chemicals; LC is one of the leading causes of death. The major difficulty in treatment was delayed diagnosis. This study aims to propose a time-domain heart rate variability (HRV) feature-based automated system in LC prediction and its staging. MATERIALS AND METHODS: HRV analysis was done using recorded electrocardiographic signal from 104 LC participants and 30 control volunteers. Artificial neural network (ANN) and support vector machine (SVM) were implemented on HRV time-domain features for early prognosis of the disorder. Statistical significance of HRV parameters was tested, and graphical user interface (GUI) was also implemented. RESULTS: It was revealed that progression of cancer causes low HRV. An accuracy of 89.64% and 100% was obtained with ANN and SVM, respectively, in automated cancer prediction. Statistical analysis suggested the significance of data at P < 0.05 between different performance statuses among patients. CONCLUSION: The severity of LC alters the sympathovagal balance through autonomic dysfunction. HRV analysis with an expert system was found useful for the early diagnosis of the disease, and thus, a noninvasive technique is of prognostic importance in classifying LC stages. The GUI designed for clinicians can help them to diagnose the Eastern Cooperative Oncology Group performance status scale of future patients.

Mechanistic electronic model to simulate and predict the effect of heat stress on the functional genomics of HO-1 system: Vasodilation.

The present work is concerned to model the molecular signalling pathway for vasodilation and to predict the resting young human forearm blood flow under heat stress. The mechanistic electronic modelling technique has been designed and implemented using MULTISIM 8.0 and an assumption of 1V/ degrees C for prediction of forearm blood flow and the digital logic has been used to design the molecular signalling pathway for vasodilation. The minimum forearm blood flow has been observed at 35 degrees C (0 ml 100 ml(-1)min(-1)) and the maximum at 42 degrees C (18.7 ml 100 ml(-1)min(-1)) environmental temperature with respect to the base value of 2 ml 100 ml(-1)min(-1). This model may also enable to identify many therapeutic targets that can be used in the treatment of inflammations and disorders due to heat-related illnesses.

Neural network detects the effects of p-CPA pre-treatment on brain electrophysiology in a rat model of focal brain injury.

OBJECTIVE: To examine the performance of Artificial Neural Network (ANN) in evaluation of the effects of pretreatment of para-Chlorophenylalanine (p-CPA), a serotonin blocker, in experimental brain injury. METHODS: Continuous 4 h digital electroencephalogram (EEG) recordings from male Charles Foster rats and its power spectrum analysis by using fast Fourier transform (FFT) were performed in two experimental (i) drug untreated injury group; (ii) p-CPA pretreated injury group as well as a control group. The EEG power spectrum data were tested by ANN containing 60 nodes in input layer, weighted from the digital values of power spectrum from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The effects of injury and of the drug pretreatment were confirmed with the help of calculation of edematous swelling in the brain. RESULTS: The changes in EEG spectral patterns were compared with the ANN and the accuracy was determined in terms of percent (%). Overall performance of the network was found the best in control group (97.9%) in comparison to p-CPA untreated injury group (96.3%) and p-CPA pretreated injury group (71.9%). The decrease in accuracy in p-CPA pretreated injury group of subjects have occurred due to increase in misclassified patterns due to faster recovery in brain cortical potentials. CONCLUSION: EEG spectrum analysis with ANN was found successful in identifying the changes due to brain swelling as well as the effect of pretreatment of p-CPA in focal brain injury condition. Thus, the training and testing of ANN with EEG power spectra can be used as an effective diagnostic tool for early prediction and monitoring of brain injury as well as the effects of drugs in this condition.

An unsupervised neural network to predict the level of heat stress.

Heat stress is known to induce high mortality rate due to multi-system illness, which demands urgent attention to reduce the fatality rate in such patients. Further, for the diagnosis and supportive therapy, one needs to define the severity of heat stress that can be distinguished as mild, intermediate and severe. The objective of this work is to develop an automated unsupervised artificial system to analyze the clinical outcomes of different levels of heat related illnesses. The Kohonen neural network program written in C++, which has seven normalized values of different clinical symptoms between 0-1 fed to the input layer of the network with 50 Kohonen output neurons, has been presented. The optimized initializing parameters such as neighborhood size and learning rate was set to 50 and 0.7, respectively, to simulate the network for 10 million iterations. The network was found smartly distinguishing all 51 patterns to three different states of heat illnesses. With the advent of these findings, it can be concluded that the Kohonen neural network can be used for automated classification of the severity of heat stress and other related psycho-patho-physiological disorders. However, to replace the expert clinicians with such type of smart diagnostic tool, extensive work is required to optimize the system with variety of known and hidden clinical and pathological parameters.

Computer simulation of heat transfer in different tissue layers of body extremities under heat stress in deep anesthetic condition.

Many mathematical models of thermoregulation in humans have been developed, so far. These models appeared to be very useful tools for studying temperature regulation in humans under adverse environmental conditions. However, no one discussed the heat transfer characteristics of denervated subjects. Thus, the present study is concerned with aspects of the passive system for denervated subjects: (1) modeling the human body extremities (2) modeling heat transport mechanism within the body and at its periphery. The present model was simulated using the software (Wintherm 8.0, Thermoanalytics, USA) for different body segments to predict the heat flow between body core and skin surface with changes in environmental temperature with fixed relative humidity and wind velocity. The simulated model for comparative study of internal temperature distribution of hand, arm, leg and feet segments yielded remarkably good results and observed to be in trends with previously cited work under ambient environmental condition and at controlled room temperature. Models could be used to measure the temperature distribution in human limbs during local hyperthermia and to investigate the interaction between limbs and the thermal environment.

Prediction of heat-illness symptoms with the prediction of human vascular response in hot environment under resting condition.

The thermoregulatory control of human skin blood flow is vital to maintain the body heat storage during challenges of thermal homeostasis under heat stress. Whenever thermal homeostasis disturbed, the heat load exceeds heat dissipation capacity, which alters the cutaneous vascular responses along with other body physiological variables. Whole body skin blood flow has been calculated from the forearm blood flow. Present model has been designed using electronics circuit simulator (Multisim 8.0, National Instruments, USA), is to execute a series of predictive equations for early prediction of physiological parameters of young nude subjects during resting condition at various level of dry heat stress under almost still air to avoid causalities associated with hot environmental. The users can execute the model by changing the environmental temperature in degrees C and exposure time in minutes. The model would be able to predict and detect the changes in human vascular responses along with other physiological parameters and from this predicted values heat related-illness symptoms can be inferred.

Neural network-based evaluation of chronic non-thermal effects of modulated 2450 MHz microwave radiation on electroencephalogram.

The effects of chronic exposure (2 h daily for 21 days) of 1 kHz square wave-modulated 2450 MHz microwave radiation (non-thermal) on sleep-EEG, open field behavior, and thyroid hormones (T(3), T(4), and TSH) have been analyzed in an animal model. Results revealed significant changes in these pathophysiological parameters (p < 0.05 or better), except body temperature, grooming behavior, and TSH levels. The sleep-EEG power spectrum data for slow wave sleep (SWS), rapid eye movement (REM) sleep, and awake (AWA) states in two experimental groups of rats (microwave exposed and the control) were tested by an artificial neural network (ANN), containing 60 nodes in input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The target output values for this network were determined with another five-layered neural network (with the structure of 6-14-1-14-6). The input and output of this network was assigned with the six confirmed pathophysiological changes. The most important feature for chronic exposure of 2450 MHz microwave exposure and for control subjects was extracted from the third layer single neuron and used as the target value for the three-layered ANN. The network was found effective in recognizing the EEG power spectra with an average of 71.93% for microwave exposure and 93.13% for control subjects, respectively. However, the lower percentage of pattern identification agreement in the microwave-exposed group in comparison to the control group suggest only mild effects of microwave exposure with this experimental setup.

Depletion of serotonin synthesis with p-CPA pretreatment alters EEG in urethane anesthetized rats under whole body hyperthermia.

BACKGROUND: Serotonin is believed as an important factor in brain function. The role of serotonin in cerebral psycho-patho-physiology has already been well established. However, the function of serotonin antagonist in anesthetized subjects under hyperthermia has not been studied properly. METHODS: Experiments were performed in three groups of urethane-anesthetized rats, such as: (i) control group, (ii) whole body hyperthermia group and (iii) p-CPA (para-Chlorophenylalanine) pretreated hyperthermia group. Hyperthermia was produced by subjecting the rats to high ambient temperature of 38 +/- 1 degrees C (relative humidity 45-50%). Each group was divided for EEG (electroencephalogram) study and for determination of edematous swelling in the brain. RESULTS: Urethane anesthetized rats under hyperthermia show highly significant reduction in their survival time. The body temperature recorded during the hyperthermia was observed with significant and linear rise with marked increase in brain water content, which was analyzed just after the death of the subjects. The results of the electroencephalographic study in urethane-anesthetized rats recorded before death indicate that brain function varies in systematic manner during hyperthermia as sequential changes in EEG patterns were observed. However, a serotonin antagonist, p-CPA pretreatment increases the survival time with significant reduction in edematous swelling in brain but it does not affect the relationship between the core body temperature and the brain cortical potentials as observed in urethane anesthetized subjects exposed to whole body hyperthermia. The core body temperature in p-CPA pretreated rats show non-linear relationship with respect to the exposure time as it was observed in drug untreated subjects. CONCLUSION: The findings of the present study indicate that although pretreatment of p-CPA in rats has a marked correlation between the extravasations of the blood-brain barrier under hyperthermia but shows minimum effect on the EEG in a model of hyperthermia under irreversible anesthesia.

Backpropagation ANN-based prediction of exertional heat illness.

Exertional heat illness is primarily a multi-system disorder results from the combined effect of exertional and thermoregulation stress. The severity of exertional heat illness can be classified as mild, intermediate and severe from non-specific symptoms like thirst, myalgia, poor concentration, hysteria, vomiting, weakness, cramps, impaired judgement, headache, diarrhea, fatigue, hyperventilation, anxiety, and nausea to more severe symptoms like exertional dehydration, heat cramps, heat exhaustion, heat injury, heatstroke, rhabdomyolysis, and acute renal failure. At its early stage, it is quite difficult to find out the severity of disease with manual screening because of overlapping of symptoms. Therefore, one need to classify automatically the disease based on symptoms. The 7:10:1 backpropagation artificial neural network model has been used to predict the clinical outcome from the symptoms that are routinely available to clinicians. The model has found to be effective in differentiating the different stages of exertional heat-illness with an overall performance of 100%.

Backpropagation artificial neural network classifier to detect changes in heart sound due to mitral valve regurgitation.

The phonocardiograph (PCG) can provide a noninvasive diagnostic ability to the clinicians and technicians to compare the heart acoustic signal obtained from normal and that of pathological heart (cardiac patient). This instrument was connected to the computer through the analog to digital (A/D) converter. The digital data stored for the normal and diseased (mitral valve regurgitation) heart in the computer were decomposed through the Coifman 4th order wavelet kernel. The decomposed phonocardiographic (PCG) data were tested by backpropagation artificial neural network (ANN). The network was containing 64 nodes in the input layer, weighted from the decomposed components of the PCG in the input layer, 16 nodes in the hidden layer and an output node. The ANN was found effective in differentiating the wavelet components of the PCG from mitral valve regurgitation confirmed person (93%) to normal subjects (98%) with an overall performance of 95.5%. This system can also be used to detect the defects in cardiac valves especially, and other several cardiac disorders in general.

Backpropagation artificial neural network detects changes in electro-encephalogram power spectra of syncopic patients.

This paper presents an effective application of backpropagation artificial neural network (ANN) in differentiating electroencephalogram (EEG) power spectra of syncopic and normal subjects. Digitized 8-channel EEG data were recorded with standard electrodes placement and amplifier settings from five confirmed syncopic and five normal subjects. The preprocessed EEG signals were fragmented in two-second artifact free epochs for calculation and analysis of changes due to syncope. The results revealed significant increase in percentage delta and alpha (p < 0.5 or better) with significant reduction in percentage theta activity (p < 0.05). The backpropagation ANN used for classification contains 60 nodes in input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The ANN was found effective in differentiating the EEG power spectra from syncopic EEG power spectra and the normal EEG power spectra with an accuracy of 88.87% (85.75% for syncopic and 92% for normal).