BACKGROUND AND OBJECTIVES: The lack of medical facilities in isolated areas makes many patients remain aloof from quick and timely diagnosis of cardiovascular diseases, leading to high mortality rates. A deep learning based method for automatic diagnosis of multiple cardiac diseases from Phonocardiogram (PCG) signals is proposed in this paper. METHODS: The proposed system is a combination of deep learning based convolutional neural network (CNN) and power spectrogram Cardi-Net, which can extract deep discriminating features of PCG signals from the power spectrogram to identify the diseases. The choice of Power Spectral Density (PSD) makes the model extract highly discriminatory features significant for the multi-classification of four common cardiac disorders. RESULTS: Data augmentation techniques are applied to make the model robust, and the model undergoes 10-fold cross-validation to yield an overall accuracy of 98.879% on the test dataset to diagnose multi heart diseases from PCG signals. CONCLUSION: The proposed model is completely automatic, where signal pre-processing and feature engineering are not required. The conversion time of power spectrogram from PCG signals is very low range from 0.10 s to 0.11 s. This reduces the complexity of the model, making it highly reliable and robust for real-time applications. The proposed architecture can be deployed on cloud and a low cost processor, desktop, android app leading to proper access to the dispensaries in remote areas.
The goal of the research is to investigate the special effect of ovarian-menstrual cycle phases on the level of women's blood pressure and characteristics of Mayer waves. 77 women aged 18-19 were tested under condition close to the state of basal metabolism in follicular phase (I), ovulation (II) and luteal phase (III) of ovarian-menstrual cycle. In phases II and III, the increase of mean and diastolic blood pressure level, in comparison with phase I in the prone position at rest and with psycho-emotional loading, were observed. The distinctions between variation parameters of R-R interval duration, stroke volume and its synchronization in phases II and III, in comparison with phase I, were observed in the prone position at rest, during tilt-test and with psycho-emotional loading. The substantial level of relationship between the power of Mayer waves and mean and diastolic blood pressure, mainly in phase I under conditions of all types, is observed. The maximum peak amplitude of stroke volume spectrogram is associated with pressure levels in the range of 0.04-0.15 Hz (rho from -0.33 to -0.64). The obtained results indicate the possible participation of spontaneous baroreflex sensitivity characteristics in keeping blood pressure level in women.
- MeSH
- Baroreflex physiology MeSH
- Biological Clocks physiology MeSH
- Blood Pressure physiology MeSH
- Humans MeSH
- Menstrual Cycle physiology MeSH
- Adolescent MeSH
- Young Adult MeSH
- Oscillometry methods MeSH
- Reference Values MeSH
- Heart Rate physiology MeSH
- Stroke Volume physiology MeSH
- Check Tag
- Humans MeSH
- Adolescent MeSH
- Young Adult MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
