Zhao Xinyi, Chen Xingmei, Wu Xulong, Zhu Lulu, Long Jianxiong, Su Li, Gu Lian
The First Affiliated Hospital of Guangxi University of Chinese Medicine.
School of Public Health, Guangxi Medical University.
J Stroke Cerebrovasc Dis. 2021 Aug;30(8):105825. doi: 10.1016/j.jstrokecerebrovasdis.2021.105825. Epub 2021 May 19.
Ischemic stroke (IS) is one of the leading causes of morbidity and mortality worldwide. Circulating microRNAs have a potential as minimally invasive biomarkers for disease prediction, diagnosis, and prognosis. In this study, we sought to use different machine learning algorithms to identify an optimal model of microRNA by integrating the expression data of pre-selected microRNAs for discriminating patients with IS from controls.
The expression level of microRNAs in the peripheral blood of 50 patients with IS and 50 matched controls were assessed through real-time polymerase chain reaction (qRT-PCR). Machine learning algorithms, including artificial neural network, random forest, extreme gradient boosting, and support vector machine (SVM) were employed via R 3.6.3 software to establish diagnostic models for IS.
The IS group had significantly increased expression levels of miR-19a (P < 0.001), miR-148a (P < 0.001), miR-320d (P = 0.003), and miR-342-3p (P < 0.001) compared with the control group. MiR-148a, miR-342-3p, miR-19a, and miR-320d yielded areas under the receiver operating characteristic curve (AUC) of 0.872, 0.844, 0.721, and 0.673, respectively, with 0.740, 0.940, 0.740, and 0.840 sensitivity and 0.920, 0.640, 0.600, and 0.440 specificity, respectively. Model miR-148a + miR-342-3p + miR-19a had the best predictive value when analyzed via SVM algorithm with AUC, sensitivity, and specificity values of 0.958, 0.937, and 0.889, respectively.
The diagnostic value of the combination of miR-148a, miR-342-3p, and miR-19a through SVM algorithm has the potential to serve as a feasible approach to promote the diagnosis of IS.
缺血性脑卒中（IS）是全球发病和死亡的主要原因之一。循环微RNA有潜力作为疾病预测、诊断和预后的微创生物标志物。在本研究中，我们试图通过整合预先选择的微RNA的表达数据，使用不同的机器学习算法来识别微RNA的最佳模型，以区分IS患者和对照组。
通过实时聚合酶链反应（qRT-PCR）评估50例IS患者和50例匹配对照组外周血中微RNA的表达水平。使用包括人工神经网络、随机森林、极端梯度提升和支持向量机（SVM）在内的机器学习算法，通过R 3.6.3软件建立IS的诊断模型。
与对照组相比，IS组中miR-19a（P < 0.001）、miR-148a（P < 0.001）、miR-320d（P = 0.003）和miR-342-3p（P < 0.001）的表达水平显著升高。MiR-148a、miR-342-3p、miR-19a和miR-320d的受试者工作特征曲线（AUC）下面积分别为0.872、0.844、0.721和0.673，敏感性分别为0.740、0.940、0.740和0.840，特异性分别为0.920、0.640、0.600和0.440。当通过SVM算法分析时，模型miR-148a + miR-342-3p + miR-19a具有最佳预测价值，AUC、敏感性和特异性值分别为0.958、0.937和0.889。
通过SVM算法联合miR-148a、miR-342-3p和miR-19a的诊断价值有可能成为促进IS诊断的可行方法。
