Search

Background: Stent malapposition (SM) following percutaneous coronary intervention (PCI) for myocardial infarction continues to present significant clinical challenges. In recent years, machine learning (ML) models have demonstrated potential in disease risk stratification and predictive modeling. Hypothesis: ML models based on optical coherence tomography (OCT) imaging, laboratory tests, and clinical characteristics can predict the occurrence of SM. Methods: We studied 337 patients from the Affiliated Hospital of Zunyi Medical University, China, who had PCI and coronary OCT from May to October 2023. We employed nested cross‐validation to partition patients into training and test sets. We developed five ML models: XGBoost, LR, RF, SVM, and NB based on calcification features. Performance was assessed using ROC curves. Lasso regression selected features from 46 clinical and 21 OCT imaging features, which were optimized with the five ML algorithms. Results: In the prediction model based on calcification features, the XGBoost model and SVM model exhibited higher AUC values. Lasso regression identified five key features from clinical and imaging data. After incorporating selected features into the model for optimization, the AUC values of all algorithmic models showed significant improvements. The XGBoost model demonstrated the highest calibration accuracy. SHAP values revealed that the top five ranked features influencing the XGBoost model were calcification length, age, coronary dissection, lipid angle, and troponin. Conclusion: ML models developed using plaque imaging features and clinical characteristics can predict the occurrence of SM. ML models based on clinical and imaging features exhibited better performance. [ABSTRACT FROM AUTHOR]

Objective To investigate the regulatory effect of bone marrow mesenchymal stem cells (BMSCs) derived exosomes on intimal hyperplasia and expression of long non-coding RNAs (lncRNAs) in rat model of carotid artery balloon injury and its potential mechanism. Methods Rat BMSCs-derived exosomes were extracted from male SD rats by differential centrifugation, and then identified by Western blotting and transmission electron microscopy. Then a total of 36 male SD rats were randomly divided into sham-operation group, model group (carotid artery balloon injury), and model+exosome treatment group (in situ injection of 400 μL 0.25 μg/μL exosomes), with 12 rats in each group. In 14 d after the treatment, all rats were sacrificed to harvest the carotid artery. HE staining was used to observe the intima/media (I/M) area ratio of carotid artery. Immunohistochemical assay was used to detect the expression of PCNA, and Western blotting was applied for the expression of the proteins involved in the intimal proliferation and phenotypic transformation. LncRNA-mRNA co-expression microarray and bioinformatics analysis were employed to analyze the differentially expressed lncRNAs and mRNAs in carotid artery tissues of the rats from the sham operation group and the model group for the potential molecular mechanism. qRT-PCR was performed to detect the expression of candidate lncRNAs in the carotid artery tissues. Results Transmission electron microscopy displayed that the BMSCs-derived exosomes presented "coaster-like" changes. Western blotting results confirmed that CD63, Alix and HSP70 were expressed in the extracted exosomes. The treatment of BMSCs-derived exosomes resulted in significant reduce in the I/M area ratio of carotid artery (P < 0.05) and decreased expression of proliferation-related proteins PCNA and Cyclin D1 (P < 0.05). The results of lncRNA-mRNA co-expression microarray showed that there were 1 083 up- and 629 down-regulated lncRNAs, and 2 004 up- and 2 487 down-regulated mRNA (Fold change>2.0, P < 0.05) in the model group when compared with the sham operation group. Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis indicated that these multiple lncRNAs were correlated with mRNAs, and the corresponding target mRNAs are involved in many biological processes, such as vascular smooth muscle contraction, actin cytoskeleton regulation and cell cycle, which are related to the mechanism of vascular restenosis after balloon injury. In combination with bioinformatics analysis, qRT-PCR detected 7 lncRNAs with significant differential expression, and the results showed that XR_593268 was up-regulated (P < 0.05), and XR_602080, XR_602012 and XR_591017 were down-regulated (P < 0.05) in the exosome treatment group compared with the model group. Conclusion The BMSCs-derived exosomes inhibit intimal hyperplasia in rats after balloon injury of carotid artery. The potential mechanism may be related to the regulation of smooth muscle cell cycle changes by lncRNAs XR_602080 and XR_591017 through Gsk3b, Cdkn2b and Ccna2.

Objective To investigate the effect of long noncoding RNA (LncRNA) LOC100360491 on apoptosis of H9c2 cardiomyocytes induced by hypoxia-reoxygenation injury and explore the possible mechanism. Methods H9c2 cells were infected with lentiviral vectors carrying LOC100360491 gene or its inhibitor (shLncRNA) or with a negative control vector, and the changes in LOC100360491 expression in the cells were detected by qRT-PCR. The infected H9c2 cells were exposed to hypoxia for 24 h followed by reoxygenation for 6 h, and early apoptosis and reactive oxygen species (ROS) production of the cells were analyzed by flow cytometry. The expression of pro-caspase-3, cleaved caspase-3, Bax, and Bcl-2 proteins in the cells were detected using Western blotting; the cellular expression levels of PAK3 and CNNM2 mRNA were detected using qRT-PCR. Results The results of qRT-PCR confirmed successful overexpression or inhibition of LOC100360491 in H9c2 cells (P < 0.05). Compared with the cells infected with the control lentiviral vector, the cells with lentivirus-mediated LOC100360491 overexpression showed significantly decreased early apoptosis and ROS production with obviously down-regulated expressions of cleaved caspase-3 and Bax and up-regulated Bcl-2 expression following hypoxia-reoxygenation (P < 0.05). Inhibition of LOC100360491 in H9c2 cells resulted in the opposite changes, which were not significant compared with negative control group. Compared with the cells infected with the negative control vector, the cells with LOC100360491 suppression showed significantly down-regulated expressions of PAK3 and CNNM2 mRNA (P < 0.05), while LOC100360491 overexpression resulted in obviously up-regulated PAK3 expression (P < 0.05) without significantly affecting CNNM2 expression. Conclusion Overexpression of LOC100360491 inhibits apoptosis of H9c2 cells induced by hypoxia-reoxygenation possibly by inhibiting mitochondrial release of ROS through upregulating the transcription of PAK3.