Yogender Aggarwal

Backpropagation Artificial Neural Network Classifier to Detect Changes in Heart Sound due to Mitral Valve Regurgitation

The phonocardiograph (PCG) can provide a non-invasive 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.

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 °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.

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%.

Eye Gaze–Induced Mental Stress Alters the Heart Rate Variability Analysis

The objective of this work was to investigate mental stress produced under eye fixation through the analysis of heart rate variability (HRV). The multichannel electrophysiological data (electrocardiogram, pulse plethysmogram along with electro-oculogram) were acquired from young, healthy male volunteers (aged 20-30 years; weight, 55-65 kg), and 20 trials per subject were recorded for 30 seconds of eye gaze followed by 10 seconds of relaxation. The parameters for HRV were calculated, analyzed, and compared before the feature extraction and classification of eye gaze from rest using “fuzzy C means clustering” and “Kohonen neural network.” Only HRV data were considered for final feature extraction and classification purposes as the pulse rate variability represented similar variations as HRV. Irrespective to subject and condition, analyses show changes in all the parameters, but with contradiction in 1 of 2 subjects that showed no change in at least 1 parameter. Furthermore, on the extracted features from frequency spectrum of HRV data (100 gaze and 100 relax), fuzzy C means clustering and Kohonen neural network were found to be efficient with an accuracy of 98%. This high accuracy in features classification strongly supports its practical implementation in the evaluation of mental stress level.

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.

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.

Electrocardiogram in Lung Cancer Patients Envisage as Pseudo-Myocardial Infarction and Ischemic Heart Disease

Lung cancer subjects undergo fatigue because of chronic stress, which affects their autonomic nervous system activity. The appearance of pseudo-myocardial infarction and T-wave inversion with no clinical symptoms were also detected in lung cancer condition. The present work aims to identify any variation in electrocardiogram (ECG) of lung cancer subjects in comparison with that of healthy controls. The lead II ECG (band-pass filtered from 0.5 to 35 Hz and sampled at 200 Hz) was recorded for 5 minutes using MP45 (Biopac System Inc, Goleta, CA) from 110 consecutive lung cancer subjects and 30 healthy controls in supine position. Acknowledge 4.0 (Biopac System Inc) software was used to study the ECG parameters. ST-segment elevation of 0.2 and 1 mV and T-wave inversion was found in ECG of lung cancer subjects without any clinical history of cardiac disorder. Subjects 1 and 2 were observed with ST-segment elevation. Subject 3 exhibited biphasic T-waveform, and subjects 4 to 8 revealed T-wave inversion in ECG. The ECG of lung cancer subjects varies from healthy controls’ ECG. ST-segment elevation similar to myocardial infarction and T-wave inversion existed in a few subjects who had no cardiac anomaly. These unique changes in ECG suggested a high level of fatigue due to a higher amount of cholinergic and adrenergic neurotransmitters secreted, leading to increased sympathetic activity and decreased parasympathetic activity.

Electronic Simulation of Neuronal Degeneration in Parkinson Disease

The present work aimed to simulate the degeneration of dopaminergic neurons of the subcortical region of brain, which plays a major role in the genesis of Parkinson disease (PD) with age. The model is designed to predict how protein aggregation and Lewy body formation leads to dopamine toxicity and leading to cell death. The electronic model has been designed and implemented using MULTISIM 8.0 (National Instruments, Austin, Texas). The electronic network is initiated through an analog comparator circuit that compares the long-term environmental alterations with the cellular set point level of the molecular kinetics. The pattern of neuronal firing and death has been simulated. The results show a slow progressive rise in &agr;-synuclein/Lewy body/dopamine toxicity level within the neuronal cells, which is comparable to published experimental and modeling studies associated with PD. Finally, cell death is demonstrated, which leads to neurodegeneration. It is believed that the hypotheses expressed in this model, when studied independently and tested on experimental data, will play an important role in understanding PD occurrence.

ELECTRONIC ANALOGY TO SIMULATE AND PREDICT THE DYNAMICS OF CELLULAR MECHANISM OF PARKINSON’S DISEASE STIMULATED BY ENVIRONMENTAL FACTORS

The present work aims to simulate and predict the molecular pathway of Parkinson’s disease (PD) initiated by environmental stress. It is designed to predict how protein aggregation and Lewy body (LB) formation leads to dopamine toxicity finally leading to cell death. The Mechanistic electronic modeling using Digital-Analog hybrid technique has been designed and implemented using MULTISIM 8.0 (National Instruments, USA) to simulate and predict the dynamics of PD pathway under environmental stress condition. The electronic network is initiated through an analog comparator circuit that compares the long-term environmental alterations with the cellular set point level of the molecular kinetics. The pattern of neuronal firing is simulated with the help of analog electronic circuit. The simulation results show a slow progressive rise in α-synuclein/LB/dopamine toxicity level within the neuronal cells, which is comparable to published experimental and modeling studies associated with PD. Finally, cell death is demonstrated, which leads to neurodegeneration. In conclusion, our model allows a straightforward implementation of qualitative representation for systems where the network topology or pathway is at least moderately known.

K-Nearest Neighborhood Approach to Identify Level of Left Ventricular Ejection Fraction From Phonocardiogram

Phonocardiographic data with different left ventricular ejection fraction (LVEFs) levels (5 subjects with reduced LVEF and 3 normal subjects) were acquired from a specialized cardiac hospital. The data were preprocessed, and 50 epochs of complete cardiac cycles were extracted from each subject for frequency spectrum analysis and were classified through the K-nearest neighborhood approach. Two cases of classification were carried out: (1) 3 classes, 2 levels of LVEF (60%-65% and 50%) and normal, and (2) 4 classes, 3 levels of LVEF (63%-65%, 60%, and 50%) and normal. The K-nearest neighborhood classifier presents good classification accuracy with these data (93.5% for 3 classes and 85.5% for 4 classes).