Set Of Electrocardiograms Research Articles

Secured ECG Signal Transmission Using Optimized EGC with Chaotic Neural Network in WBSN

In wireless body sensor network (WBSN), the set of electrocardiogram (ECG) data which is collected from sensor nodes and transmitted to the server remotely supports the experts to monitor the health of a patient. While transmitting these collected data some adversaries may capture and misuse it due to the compromise of security. So, the major aim of this work is to enhance secure transmission of ECG signal in WBSN. To attain this goal, we present Pity Beetle Swarm Optimization Algorithm (PBOA) based Elliptic Galois Cryptography (EGC) with Chaotic Neural Network. To optimize the key generation process in Elliptic Curve Cryptography (ECC) over Galois field or EGC, private key is chosen optimally using PBOA algorithm. Then the encryption process is enhanced by presenting chaotic neural network which is used to generate chaotic sequences or cipher data. Results of this work show that the proposed cryptography algorithm attains better encryption time, decryption time, throughput and SNR than the conventional cryptography algorithms.

Optimized Compressive Sensing Based ECG Signal Compression and Reconstruction

In wireless body sensor network (WBSN), the set of electrocardiograms (ECG) data which is collected from sensor nodes and transmitted to the server remotely supports the experts to monitor the health of a patient. However, due to the size of the ECG data, the performance of the signal compression and reconstruction is degraded. For efficient wireless transmission of ECG data, compressive sensing (CS) frame work plays significant role recently in WBSN. So, this work focuses to present CS for ECG signal compression and reconstruction. Although CS minimizes mean square error (MSE), compression rate and reconstruction probability of the CS is further to be improved. In this paper, we provide an efficient compressive sensing framework which strives to improve the reconstruction process, by adjusting the sensing matrix during the compression phase using the rain optimization algorithm (ROA). With the optimal sensing matrix, the compressed signal is reconstructed using Step Size optimized Sparsity Adaptive Matching Pursuit algorithm (SAMP). The results of this work demonstrate that the optimised CS framework achieves a higher compression rate and probability of reconstruction than the standard CS framework.

ECG Electrode Placements for Magnetohydrodynamic Voltage Suppression

This study aims to investigate a set of electrocardiogram (ECG) electrode lead locations to improve the quality of four-lead ECG signals acquired during magnetic resonance imaging (MRI). This was achieved by identifying electrode placements that minimized the amount of induced magnetohydrodynamic voltages (VMHD) in the ECG signals. Reducing VMHD can improve the accuracy of QRS complex detection in ECG as well as heartbeat synchronization between MRI and ECG during the acquisition of cardiac cine. A vector model based on thoracic geometry was developed to predict induced VMHD and to optimize four-lead ECG electrode placement for the purposes of improved MRI gating. Four human subjects were recruited for vector model establishment (Group 1), and five human subjects were recruited for validation of VMHD reduction in the proposed four-lead ECG (Group 2). The vector model was established using 12-lead ECG data recorded from Group 1 of four healthy subjects at 3 Tesla, and a gradient descent optimization routine was utilized to predict optimal four-lead ECG placement based on VMHD vector alignment. The optimized four-lead ECG was then validated in Group 2 of five healthy subjects by comparing the standard and proposed lead placements. A 43.41% reduction in VMHD was observed in ECGs using the proposed electrode placement, and the QRS complex was preserved. A VMHD-minimized electrode placement for four-lead ECG gating was presented and shown to reduce induced magnetohydrodynamic (MHD) signals, potentially allowing for improved cardiac MRI physiological monitoring.

Automated discrimination of proximal right coronary artery occlusion from middle-to-distal right coronary artery occlusion and left circumflex occlusion in ST-elevation myocardial infarction

BackgroundClassifying the location of an occlusion in the culprit artery during ST-elevation myocardial infarction (STEMI) is important for risk stratification to optimize treatment. We developed a new logistic regression (LR) algorithm for 3-group classification of occlusion location as proximal right coronary artery (RCA), middle-to-distal RCA or left circumflex (LCx) coronary artery with inferior myocardial infarction. We compared the performance of the new LR algorithm with the recently introduced decision tree classifier of Fiol et al (Ann Noninvasive Electrocardiol. 2004;4:383-388) in the classification of the same 3 categories. MethodsThe new algorithm was developed on a set of electrocardiograms from an emergency department setting (n = 64) and tested on a different set from a prehospital setting (n = 68). All patients met the current STEMI criteria with angiographic confirmation of culprit artery and occlusion location. Using LR, 4 ST-segment deviation features were chosen by forward stepwise selection. Final LR coefficients were obtained by averaging more than 200 bootstrap iterations on the training set. In addition, a separate 4-feature classifier was designed adding ST features of V4R and V8, only available in the training set. ResultsThe LR algorithm classified proximal RCA occlusion vs combined LCx occlusion and middle-to-distal RCA occlusion, with a sensitivity of 76% and specificity of 81% as compared with 71% and 62% for the Fiol classifier. The difference in specificity was statistically significant. The LR classifier trained with additional ST features of V4R and V8, but still limited to 4, improved the overall agreement in the training set from 65% to 70%. ConclusionDiscrimination of proximal RCA lesion location from LCx or middle-to-distal RCA using the new LR classifier shows improvement over decision tree–type classification criteria. Automated identification of proximal RCA occlusion could speed up the risk stratification of patients with STEMI. The addition of leads V4R and V8 should further improve the automated classification of the occlusion site in RCA and LCx.

Applying neural network analysis on heart rate variability data to assess driver fatigue

Long duration driving is a significant cause of fatigue related accidents on motorways. Fatigue caused by driving for extended hours can acutely impair driver’s alertness and performance. This papers presents an artificial intelligence based system which could detect early onset of fatigue in drivers using heart rate variability (HRV) as the human physiological measure. The detection performance of neural network was tested using a set of electrocardiogram (ECG) data recorded under laboratory conditions. The neural network gave an accuracy of 90%. This HRV based fatigue detection technique can be used as a fatigue countermeasure.

QRS width in right bundle branch block. Accuracy and reproducibility of manual measurement

Background: The QRS prolongation and its relation to malignant ventricular arrhythmias are topics of interest. Controversies exist about the methodology of measuring the QRS. The aim of this study was to assess the accuracy and reproducibility of manual measurement of the QRS in standard electrocardiograms in patients with right bundle branch block and compare results with computer reading. Methods and results: Five experienced cardiologists at different levels of training were required to measure QRS duration in 30 electrocardiograms with different degrees of right bundle branch block collected from 24 randomly selected patients who had had radical repairs of tetralogy of Fallot. In each set of electrocardiograms there were six records which had been duplicated. The observers were neither told the purpose of the study nor how the electrocardiograms had been obtained, nor informed that some of the electrocardiograms were duplicates. Photocopies were identified by number, covering the patient’s name and computerised measurement. Significant differences were found in the measurement of QRS in the same ECG calculated twice by the same observer (with an absolute variation up to 50 ms), within different observers ( P=0.037) and measured manually or by computer ( P=0.019). The width of the QRS did not influence the measurements as the biggest intra-observer variation (50 ms) was observed for relatively wide complex (median value between the two measurements 155 ms) and the biggest inter-observer (60 ms) for narrow complex (median value between the five measurements 110 ms). The QRS morphology appeared to influence the measurements, as the intra- and inter-observer variations were more consistent in the presence of obvious notching, slurrings and terminal slow vectors. Conclusions: Measurement of QRS is difficult, can be operator dependent and influenced by the presence of conduction abnormalities which reduce its accuracy and reproducibility.

The Delphi Method to Validate Diagnostic Knowledge in Computerized ECG Interpretation

We investigated the applicability of the Delphi method for increasing the agreement among multiple cardiologists on, firstly, their classifications of a set of electrocardiograms and, secondly, their reasons for these classifications. Five cardiologists were requested to judge the computer classifications of a set of thirty ECGs. If a cardiologist disagreed with the computer classification, he had to provide a new classification and a reason for this change. The results of this first round were compiled and anonymously fed back to the cardiologists. In a second round the cardiologists were asked once again to judge the ECGs and to rate the reasons provided in the first round. The level of agreement was estimated by means of the kappa statistic. The Delphi procedure substantially increased the agreement on the classifications among the cardiologists. The final agreement was very high and comparable with the intraobserver agreement. There was also a high level of agreement on the reasons provided by the cardiologists. However, their use in improving the program's performance is hampered by the qualitative nature of many of the reasons. Suggestions are given for a more formalized elicitation of knowledge.

Variability of the electrocardiogram in normal young men

Electrocardiograms were taken on twelve normal young men in the basal state on eleven different occasions over a period of two months. Three standard and three chest leads were used, and thirty-five electrocardiographic items were measured. In addition, one set of electrocardiograms was measured by the same assistant on three different occasions. The amount of variation contributed by interindividual differences, by day-to-day physiologic fluctuation, and by inaccuracy in measuring the records was determined statistically. The ratio of the intraindividual to the interindividual variance was used as the criterion of the consistency of repeated electrocardiographic determinations. Out of thirty-five electrocardiographic items, the consistency was very high (consistency coefficient ≧ 0.90) in fourteen, high (0.89 to 0.80) in seven, moderate (0.79 to 0.70) in three, low (0.69 to 0.60) in three, and very low (< 0.60) in eight. The consistency measures were corrected for the homogeneity of the sample of subjects by substituting estimates of interindividual variance based on much larger samples, and for the inaccuracy of measurement of the electrocardiographic records. The 90 per cent expectancy range of intraindividual variability was calculated. These data may be applied for interpretation of borderline electrocardiograms and for evaluation of degrees of deterioration or improvement in serial electrocardiograms.

The site of the cardiac lesion in two instances of intraventricular heart block

The hearts of two cases were examined in order to determine the site of the lesion associated with electrocardiograms suggesting partial block of either the right or the left branch of the auriculoventricular system. As the main deflections in the two sets of electrocardiograms were in opposite directions, it was to be expected that the lesions, if any, in the two instances, would be found on opposite sides of the heart. There has been considerable theoretical discussion as to which type of electrocardiogram is associated with right-sided and which with left-sided block.The first case showed electrocardiographically a main deflection inverted in lead I, upright in leads II and III, a marked widening of the foot-points of the Q.R.S. complex, and only moderate voltage; in addition there was auricular fibrillation. Microscopic examination of serial sections of the A.-V. system, showed that the right bundle branch became attenuated almost immediately after its origin from the main stem, and was surrounded by ...