Objective To investigate the effect of prostaglandin E1 (PGE1) on serum vascular endothelial growth factor(VEGF) in patient with pulmonary hypertension secondary to congenital heart disease and its relation to different pathologic gradings of pulmonary arterioles. Methods Fifty three patients suffering from pulmonary hypertension secondary to congenital heart disease were chosen at random to undergo active tissue test of lung, including 6 patients suffering from severe cyanosis. All of them were intravenously dripped with PGE 1 for 15 days at the speed of 10 15 ng /kg·min, 12 hours a day. Venous blood was taken for study in the morning on the day before infusion, on the 5th day, the 10th day, and the 15th day after infusion. Then the concentration of VEGF was measured by enzyme linked immunosorbent assay (ELISA). Lung biopsy was taken from each patient and pathologic grading performed according to Heath and Edwards pathologic grading. Results Fifty three patients were classified into Grade Ⅴ:9 of them belonged to Grade Ⅰ, 14 to Grade Ⅱ, 19 to Grade Ⅲ, 5 to Grade Ⅳ, the other 6 with severe cyanosis belonged to Grade Ⅴ or even severe than Grade Ⅴ. Before administration of PGE 1, serum VEGF reached the peak while the pathologic grading of pulmonary arteriole was Grade Ⅲ, VEGF level markedly decreased in Grade Ⅳ and Ⅴ. After administration of PGE 1 serum VEGF in Grade Ⅰ showed no difference with that before administration of PGE 1( P gt;0.05), VEGF decreased in GradeⅡ and Ⅲ ( P lt;0.01), slightly decreased in Grade Ⅳ ( P lt; 0.05), while patients greater or equivalent to Grade Ⅴ showed no VEGF change during the course of PGE 1 administration ( P gt;0.05). Conclusions PGE 1 can lower the VEGF level, but the extent closely relates to the degree of pathologic change in pulmonary arteriole. It might be a pre operative parameter for pathologic grading of pulmonary arteriole.
Cardiotocography (CTG) is a non-invasive and important tool for diagnosing fetal distress during pregnancy. To meet the needs of intelligent fetal heart monitoring based on deep learning, this paper proposes a TWD-MOAL deep active learning algorithm based on the three-way decision (TWD) theory and multi-objective optimization Active Learning (MOAL). During the training process of a convolutional neural network (CNN) classification model, the algorithm incorporates the TWD theory to select high-confidence samples as pseudo-labeled samples in a fine-grained batch processing mode, meanwhile low-confidence samples annotated by obstetrics experts were also considered. The TWD-MOAL algorithm proposed in this paper was validated on a dataset of 16 355 prenatal CTG records collected by our group. Experimental results showed that the algorithm proposed in this paper achieved an accuracy of 80.63% using only 40% of the labeled samples, and in terms of various indicators, it performed better than the existing active learning algorithms under other frameworks. The study has shown that the intelligent fetal heart monitoring model based on TWD-MOAL proposed in this paper is reasonable and feasible. The algorithm significantly reduces the time and cost of labeling by obstetric experts and effectively solves the problem of data imbalance in CTG signal data in clinic, which is of great significance for assisting obstetrician in interpretations CTG signals and realizing intelligence fetal monitoring.