A novel convolutional neural network for reconstructing surface electrocardiograms from intracardiac electrograms and vice versa

A novel method for 12-lead ECG reconstruction

This paper presents a novel approach to synthesize a standard 12-lead electrocardiogram (ECG) from any three independent ECG leads using a patient-specific encoder-decoder convolutional neural network. The objective is to decrease the number of recording locations required to obtain the same information as a 12-lead ECG, thereby enhancing patients' comfort during the recording process. We evaluate the proposed algorithm on a dataset comprising fifteen patients, as well as a randomly selected cohort of patients from the PTB diagnostic database. To evaluate the precision of the reconstructed ECG signals, we present two metrics: the correlation coefficient and root mean square error. Our proposed method achieves superior performance compared to most existing synthesis techniques, with an average correlation coefficient of 0.976 and 0.97 for datasets, respectively. These results demonstrate the potential of our approach to improve the efficiency and comfort of ECG recording for patients, while maintaining high diagnostic accuracy.

Evidence-Based Analysis of the Emergency Temporary Cardiac Pacing (Electrical Stimulation from Metal Wire Electrode)

The patient's Cr (creatinine), BUN (blood urea nitrogen), HBG (hemoglobin), VT (ventricular tachycardia), pacing frequency, puncture point, emergency to permanent pacing time, pacing current (mA), pacing threshold current (mA), and admission diagnosis data were collected. The data were subjected to frequency statistics, curve regression analysis, PLS regression analysis, adjustment analysis, chi-square test, ridge regression analysis, discriminant analysis, negative binomial regression analysis, Poisson regression analysis, and stepwise regression analysis. Some findings include the following: (1) Cr has a significant positive effect on HBG, and BUN has a significant negative effect on HBG. (2) VT has a negative correlation with age and a positive correlation with CK-MB and CK (creatinine kinase). (3) Myocarditis has a negative correlation with age and a significant positive correlation with CTnI (cardiac troponin I). (4) AST (aspartate transaminase) and ALT (alanine aminotransferase) have a significant positive impact on DDI (D-dimer), while CTnI has a significant negative impact on DDI. MYO (myoglobin) has no impact relationship to DDI. (5) ALT has a significant positive relationship with APTT (partial thromboplastin time). (6) Alb (albumin) and TBIL (total bilirubin) have a significant positive effect on PLT (platelet) count, while pro-BNP (B-type natriuretic peptide) and MYO have a significant negative effect on PLT. (7) CK has a significant positive effect on INR (international normalized ratio). (8) The relationship between sinus node dysfunction and VT significantly affect the pacing frequency (beats/minute). For third-degree atrioventricular block, different samples of sinus node dysfunction showed significant differences. (9) There is a significant positive correlation between pacing current (mA) and pacing threshold current (mA). (10) There was a significant positive correlation between perceived voltage (mV) and the time from emergency to permanent pacing. Admission diagnosis has a significant positive impact on the time from emergency to permanent pacing. The change (increase) in time from emergency to permanent pacing was 1.137-fold when an additional condition was diagnosed on admission.