Machine learning in a real-world PFO study: analysis of data from multi-centers in China.

PURPOSE: The association of patent foreman ovale (PFO) and cryptogenic stroke has been studied for years. Although device closure overall decreases the risk for recurrent stroke, treatment effects varied across different studies. In this study, we aimed to detect sub-clusters in post-closure PFO patients and identify potential predictors for adverse outcomes. METHODS: We analyzed patients with embolic stroke of undetermined sources and PFO from 7 centers in China. Machine learning and Cox regression analysis were used. RESULTS: Using unsupervised hierarchical clustering on principal components, two main clusters were identified and a total of 196 patients were included. The average age was 42.7 (12.37) years and 64.80% (127/196) were female. During a median follow-up of 739 days, 12 (6.9%) adverse events happened, including 6 (3.45%) recurrent stroke, 5 (2.87%) transient ischemic attack (TIA) and one death (0.6%). Compared to cluster 1 (n = 77, 39.20%), patients in cluster 2 (n = 119, 60.71%) were more likely to be male, had higher systolic and diastolic blood pressure, higher body mass index, lower high-density lipoprotein cholesterol and increased proportion of presence of atrial septal aneurysm. Using random forest survival (RFS) analysis, eight top ranking features were selected and used for prediction model construction. As a result, the RFS model outperformed the traditional Cox regression model (C-index: 0.87 vs. 0.54). CONCLUSIONS: There were 2 main clusters in post-closure PFO patients. Traditional cardiovascular profiles remain top ranking predictors for future recurrence of stroke or TIA. However, whether maximizing the management of these factors would provide extra benefits warrants further investigations.

Fluid upstream shear stress of rabbit aortic stenosis inhibits neointimal hyperplasia by promoting endothelization after balloon injury.

BACKGROUND: Atherosclerosis is associated with disturbed blood flow characterized by low and oscillatory shear stress (SS), however, few study directly links SS to neointimal hyperplasia in animal model. This study was focused on the effects of changed SS upon the neointimal hyperplasia which responded to balloon injury in a novel rabbit model with partially-constricted abdominal aorta. METHODS: We established a rabbit model subjected to partial abdominal aortic constriction with a cylinder-shaped cannula as a model of disturbed flow, which was similar to the hemodynamic features of stenosis caused by atherosclerosis plaque. Further, balloon injury was performed to investigate the relationship between SS and neointimal hyperplasia. Four weeks later, the abdominal aorta was assessed with digital subtraction angiography (DSA) and intravascular ultrasound (IVUS). The vascular sections were embedded in paraffin blocks for morphometric analysis to evaluate neointimal hyperplasia, and anti-CD31 immunohistochemical staining was for endothelialization ratio. RESULTS: In upstream the stenosis, the changed SS leads to neointimal hyperplasia compared with normal SS (11,729 ± 1205 vs 8418 ± 737, P = 0.023). However, the upstream SS of the stenosis can promote vascular re-endothelialization after balloon injury compared with normal SS, verified by endothelialization ratio (0.36 ± 0.03 vs 0.32 ± 0.03, P = 0.017), thereby attenuate neointimal hyperplasia (64,851 ± 3995 vs 68,335 ± 3867, P = 0.018). CONCLUSION: The upstream SS of stenosis, not downstream SS, inhibits the neointimal hyperplasia after balloon injury by promoting vascular re-endothelializtion.