Deep learning-mediated prediction of concealed accessory pathway based on sinus rhythmic electrocardiograms.

BACKGROUND: Concealed accessory pathway (AP) may cause atrial ventricular reentrant tachycardia impacting the health of patients. However, it is asymptomatic and undetectable during sinus rhythm. METHODS: To detect concealed AP with electrocardiography (ECG) images, we collected normal sinus rhythmic ECG images of concealed AP patients and healthy subjects. All ECG images were randomly allocated to the training and testing datasets, and were used to train and test six popular convolutional neural networks from ImageNet pre-training and random initialization, respectively. RESULTS: We screened 152 ECG recordings in concealed AP group and 600 ECG recordings in control group. There were no statistically significant differences in ECG characteristics between control group and concealed AP group in terms of PR interval and QRS interval. However, the QT interval and QTc were slightly higher in control group than in concealed AP group. In the testing set, ResNet26, SE-ResNet50, MobileNetV3_large_100, and DenseNet169 achieved a sensitivity rate more than 87.0% with a specificity rate above 98.0%. And models trained from random initialization showed similar performance and convergence with models trained from ImageNet pre-training. CONCLUSION: Our study suggests that deep learning could be an effective way to predict concealed AP with normal sinus rhythmic ECG images. And our results might encourage people to rethink the possibility of training from random initialization on ECG image tasks.

[Cathepsin B promoted the apoptosis of vascular smooth muscle cells as induced by tumor necrosis factor-α].

OBJECTIVE: To establish the cathepsin B over-expression group and cathepsin B gene-silencing group so as to investigate whether cathepsin B was capable of promoting the apoptosis of VSMC (vascular smooth muscle cell) induced by TNF-α/act D. METHODS: Human aortic smooth muscle cell (HA-VSMC) was transfected with pcDNA3.1-cathepsin B and pSilencer2.1-cathepsin B plasmids by lipofection to establish the over-expression and gene-silencing groups. Through TNF-α induced apoptosis, the cell viability was observed by MTT assay, morphological observation and assays of apoptotic proteins as indicators of apoptosis. RESULTS: The cathepsin B over-expression and gene-silencing group were successfully established. MTT assay showed no significant difference between the transfected cell and blank control. After the intervention of TNF-α, the HA-VSMC viability decreased significantly. As compared with control group, the over-expression group significantly decreased (9.98% ± 1.04% vs 14.60% ± 1.34%). As compared with the over-expression group, the E64d and CA-074ME groups (18.23% ± 1.05%, 17.40% ± 1.03%) increased significantly while the silent group (21.30% ± 2.37%) significantly increased. The analysis of acridine orange/ethidium bromide staining showed similar results. Western blot showed the Bcl-2 protein were significantly higher in the silent group than that in the control group. And the over-expression group was significantly lower than the control group. The E64d and CA-074ME groups were significantly higher than that in the over-expression group. But the Bax protein level had no significant difference among all groups. CONCLUSION: The over-expression of cathepsin B promotes TNF-α-induced VSMC apoptosis while Cathepsin B gene silencing and the addition of cathepsin inhibitor in over-expression group inhibit the TNF-α induced VSMC apoptosis.

[Study on the association of ABCA1 gene common variants with the risk of coronary atherosclerotic heart disease].

OBJECTIVE: To investigate the association of R219K and M883I polymorphisms of ATP binding cassette transporter 1 gene with lipid metabolism and the susceptibility to coronary atherosclerotic heart disease in Chinese population. METHODS: Genotypes were determined by PCR-restriction fragment length polymorphism and Primer introduced restriction analysis-PCR techniques, respectively, in 248 unrelated CHD-free controls and 224 CHD cases. RESULTS: Smoking, high blood pressure and high serum glucose were independent risk factors for CHD. Multivariate logistic regression analysis revealed that individuals carrying at least one 219K variant allele (RK + KK genotypes) had a significantly decreased risk for CHD (adjusted OR = 0.41; 95% CI = 0.27-0.61) compared with the wild-type genotype (219RR) and only 883II homozygotes displayed a decreased risk for CHD (adjusted OR = 0.54; 95% CI = 0.26-1.11) compared with 883MM and 883MI genotypes. Furthermore, compared with individuals with both wild genotypes (219 RR and 883 MM or 883 MI) other individuals with all other assembly genotypes had a significantly decreased risk (adjusted OR = 0.39, 95% CI = 0.26-0.60). Plasma HDL-C in 219K allele carriers were markedly higher than those in 219 K non-carriers in controls (P = 0.037). CONCLUSION: The ABCA1 R219K polymorphism may be involved in the variability of serum HDL-C and the susceptibility to coronary artery disease.