Automatic quantitative measurement of left atrial pressure using mitral regurgitation spectrum: clinical study on comparison with floating catheter.

INTRODUCTION: To explore how to measure LAPEq accurately and quantitatively, that is, the left atrial pressure (LAP) measured and calculated by equation method using mitral regurgitation spectrum. METHODS: The mitral regurgitation spectrum, pulmonary arteriolar wedge pressure (PAWP) and invasive arterial systolic pressure of radial artery of 28 patients were collected simultaneously, including 3 patients with rheumatic heart disease, 15 patients with mitral valve prolapse and 10 patients with coronary artery bypass grafting, patients with moderate or above aortic stenosis were excluded. LAPBp (Doppler sphygmomanometer method), LAPEq (Equation method) and LAPC (Catheter method) were measured synchronously, and the measurement results of the three methods were compared and analyzed. A special intelligent Doppler spectrum analysis software was self-designed to accurately measure LAPEq. This study had been approved by the ethics committee of the Northern Theater General Hospital (K-2019-17), and applied for clinical trial (No. Chictr 190023812). RESULTS: It was found that there was no significant statistical difference between the measurement results of LAPC and LAPEq (t = 0.954, P = 0.348), and significant correlation between the two methods [r = 0.908(0.844, 0.964), P < 0.001]. Although the measurement results of LAPC and LAPBP are consistent in the condition of non-severe eccentric mitral regurgitation, there are significant differences in the overall case and weak correlation between the two methods [r = 0.210, (-0.101, 0.510), P = 0.090]. In MVP patients with P1 or P3 prolapse, the peak pressure difference of MR was underestimated due to the serious eccentricity of MR, which affected the accuracy of LAPBP measurement. CONCLUSIONS: It was shown that there is a good correlation between LAPEq and LAPC, which verifies that the non-invasive and direct quantitative measurement of left atrial pressure based on mitral regurgitation spectrum is feasible and has a good application prospect.

An Appraisal of Incremental Learning Methods.

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.