Search

Electrocardiogram (ECG) is an important tool for the detection of acute ST-segment elevation myocardial infarction (STEMI). However, machine learning (ML) for the diagnosis of STEMI complicated with arrhythmia and infarct-related arteries is still underdeveloped based on real-world data. Therefore, we aimed to develop an ML model using the Least Absolute Shrinkage and Selection Operator (LASSO) to automatically diagnose acute STEMI based on ECG features. A total of 318 patients with STEMI and 502 control subjects were enrolled from Jan 2017 to Jun 2019. Coronary angiography was performed. A total of 180 automatic ECG features of 12-lead ECG were input into the model. The LASSO regression model was trained and validated by the internal training dataset and tested by the internal and external testing datasets. A comparative test was performed between the LASSO regression model and different levels of doctors. To identify the STEMI and non-STEMI, the LASSO model retained 14 variables with AUCs of 0.94 and 0.93 in the internal and external testing datasets, respectively. The performance of LASSO regression was similar to that of experienced cardiologists (AUC: 0.92) but superior (p < 0.05) to internal medicine residents, medical interns, and emergency physicians. Furthermore, in terms of identifying left anterior descending (LAD) or non-LAD, LASSO regression achieved AUCs of 0.92 and 0.98 in the internal and external testing datasets, respectively. This LASSO regression model can achieve high accuracy in diagnosing STEMI and LAD vessel disease, thus providing an assisting diagnostic tool based on ECG, which may improve the early diagnosis of STEMI.

Context Ginsenoside Rb1 (Rb1) exerts many beneficial effects and protects against cardiovascular disease. Objective To investigate whether Rb1 could attenuate age-related vascular impairment and identify the mechanism. Materials and methods Female C57BL/6J mice aged 2 and 18 months, randomly assigned to Young, Young + 20 mg/kg Rb1, Old + vehicle, Old + 10 mg/kg Rb1 and Old + 20 mg/kg Rb1 groups, were daily intraperitoneal injected with vehicle or Rb1 for 3 months. The thoracic aorta segments were used to inspect the endothelium-dependent vasorelaxation. Left thoracic aorta tissues were collected for histological or molecular expression analyses, including ageing-related proteins, markers relevant to calcification and fibrosis, and expression of Gas6/Axl. Results We found that in Old + vehicle group, the expression of senescence proteins and cellular adhesion molecules were significantly increased, with worse endothelium-dependent thoracic aorta relaxation (58.35% ± 2.50%) than in Young group (88.84% ± 1.20%). However, Rb1 treatment significantly decreased the expression levels of these proteins and preserved endothelium-dependent relaxation in aged mice. Moreover, Rb1 treatment also reduced calcium deposition, collagen deposition, and the protein expression levels of collagen I and collagen III in aged mice. Furthermore, we found that the downregulation of Gas6 protein expression by 41.72% and mRNA expression by 52.73% in aged mice compared with young mice was abrogated by Rb1 treatment. But there was no significant difference on Axl expression among the groups. Conclusions Our study confirms that Rb1 could ameliorate vascular injury, suggesting that Rb1 might be a potential anti-ageing related vascular impairment agent.

Nuclear factor-κB plays a critical role in endothelial senescence. However, the mechanisms remain unclear. We hypothesized that the alteration of S-Nitrosylation of NF-κB p65 may contribute to hydrogen peroxide-induced endothelial cell senescence. The human umbilical vein endothelial cells (