Detection and Classification of electrocardiography using hybrid deep learning models.

BACKGROUND: Electrocardiography (ECGs) has been a vital tool for cardiovascular disease (CVD) diagnosis, which visually depicts the heart's electrical activity. To enhance automatic classification between normal and diseased ECG, it is essential to extract consistent and qualitative features. METHODS: Precision of ECG classification through hybrid Deep Learning (DL) approach leverages both Convolutional Neural Network (CNN) architecture and Variational Autoencoder (VAE) techniques. By combining these methods, we aim to achieve more accurate and robust ECG interpretation. The method is trained and tested over PTB-XL dataset, which contains 21,799 with 12-lead ECGs from 18,869 patients, each spanning 10 seconds. The classification evaluation of 5 super-classes and 23 sub-classes of CVD, with the proposed CNN-VAE model is compared. RESULTS: The classification of various CVD had resulted with the highest accuracy of 98.51%, specificity of 98.12%, sensitivity 97.9% and F1-score 97.95%. We have also achieved the minimum false positive and false negative rates as 2.07 and 1.87 respectively during validation. The results are validated upon the annotations given by individual cardiologists, who assigned potentially multiple ECG statements to each record. CONCLUSION: When compared to other deep learning methods, our suggested CNN-VAE model performs significantly better in testing phase. This study proposes a new architecture of combining CNN-VAE for CVD classification from ECG data, this can help the clinicians to identify the disease earlier and carry further treatment. The CNN-VAE model can better characterize input signals due to its hybrid architecture.

Gender-Based Vegetarian and Nonvegetarian Dietary Impact on Cardiac Autonomic Function of Heart Rate Variability.

Objective: Cardiovascular disease is one among the major mortality threats throughout the world. Autonomic activity of the nervous system can be examined by heart rate variability (HRV) analysis. Association of sympathetic and parasympathetic activities is directly related to HRV modulation. The aim of the study is to determine variations in HRV parameters among adult/adolescent male and female subjects due to vegetarian and nonvegetarian diet.Method: Ninety undergraduate students in each male and female group (N = 180) volunteered for the study. Based upon food habits, male and female subjects were categorized into four groups. Short-term (5-minute) heart rate recordings were measured from the subjects in a seated position before breakfast with minimum of 12 hours' fasting. Two-way analysis of variance was performed among the time and frequency domain variables.Results: Time domain variables are observed as significant (p < 0.05) between vegetarian males and females and also (p < 0.05) between male vegetarian and female nonvegetarians for standard deviation of NN intervals. Frequency domain HRV indices such as low frequency (LF; p = 0.01), high frequency (HF; p = 0.0001), and LF/HF (p < 0.001) resulted between male and female vegetarians. Significance of LF (p = 0.02), HF (p < 0.0001), and LF/HF (p < 0.01) was measured between male vegetarians and female nonvegetarians. LF (p = 0.02), HF (p = 0.04), and LF/HF (p = 0.002) resulted between nonvegetarian males and females. HF (p = 0.05) was enumerated between male vegetarians and nonvegetarians.Conclusions: Significant predominance of sympathetic cardiac activity was observed among male nonvegetarian consumers more than female vegetarians. Analysis demonstrates that the gender-based influence of vegetarian and nonvegetarian diet has significant correlation under HRV measurements.