基于随机森林模型探讨PLCL2基因多态性与LAA型缺血性脑卒中发病风险预测-现代医学

基于随机森林模型探讨PLCL2基因多态性与LAA型缺血性脑卒中发病风险预测

单位：1. 新疆医科大学第二临床医学院, 新疆乌鲁木齐 830000;
2. 新疆医科大学第二附属医院神经内科, 新疆乌鲁木齐 830063;
3. 新疆医科大学第二附属医院新疆神经系统疾病研究重点实验室, 新疆乌鲁木齐 830063

分类号：R743.33

出版年·卷·期（页码）：2025·53·第七期（1025-1031）

摘要：

目的：基于随机森林(RF)算法探讨磷酸酯酶C-2(PLCL2)基因多态性与大动脉粥样硬化(LAA)型缺血性脑卒中发病风险并构建预测模型。方法：纳入2022年7月—2023年7月新疆医科大学第二附属医院收治的LAA型缺血性脑卒中患者及同期健康体检者，收集临床资料并检测PLCL2 rs10754555位点的基因型，构建RF模型并通过SHAP解释特征贡献。结果：共纳入病例组92例(男53例，女39例)和对照组90例(男46例，女44例)，两组性别分布无差异(P>0.05)。两组PLCL2 rs10754555基因型频数和等位基因频数差异具有统计学意义(P<0.05)。RF预测模型在训练集和测试集的AUC分别为0.964(95％CI 0.931~0.997)和0.947(95％CI 0.895~0.999)，具有良好的预测效能。SHAP分析显示，CRP、IL-6、DD等10项指标为危险因素，HDL为保护因素；PLCL2 rs10754555位点AG基因型显著提升发病风险，而AA/GG基因型降低风险。结论：PLCL2基因多态性与LAA型缺血性脑卒中的发病风险密切相关，整合多维度特征的RF预测模型具有良好预测效能，可为早期筛查提供参考。

Objective: To investigate the association between phospholipase C-like 2(PLCL2) gene polymorphisms and large-artery atherosclerotic(LAA) ischemic stroke using a random forest(RF) algorithm and to construct a risk prediction model.Methods: Patients with LAA ischemic stroke admitted to the Second Affiliated Hospital of Xinjiang Medical University from July 2022 to July 2023, along with healthy controls during the same period, were enrolled. Clinical data were collected, and genotypes of the PLCL2 rs10754555 locus were analyzed. A RF model was constructed, and feature contributions were interpreted using SHAP analysis. Results: A total of 92 cases(53 males, 39 females) and 90 controls(46 males, 44 females) were included, with no significant difference in gender distribution between the two groups(P>0.05). Significant differences were observed in the genotype and allele frequencies of the PLCL2 rs107545555 locus between the two groups(P<0.05). The RF prediction model achieved AUC values of 0.964(95%CI 0.931-0.997) in the training set and 0.947(95%CI 0.895-0.999) in the test set, demonstrating good predictive performance. SHAP analysis revealed that ten indicators, including CRP, IL-6, and D-D, were risk factors, while HDL was a protective factor. The AG genotype of the PLCL2 rs107545555 locus significantly increased the risk of disease, whereas the AA and GG genotypes reduced the risk. Conclusion: The polymorphisms of the PLCL2 gene are closely associated with the risk of LAA ischemic stroke. The RF prediction model integrating multidimensional features exhibits strong predictive performance, offering potential value for early screening.

参考文献：

[1] 万红燕，郝舒欣，刘婕，等.机器学习在脑卒中风险预测中的应用进展[J].中国基层医药，2024，31(8)：1275-1280.
[2] HIROKAWA M，MORITA H，TAJIMA T，et al.A genome-wide association study identifies PLCL2 and AP3D1-DOT1L-SF3A2 as new susceptibility loci for myocardial infarction in Japanese[J].Eur J Hum Genet，2015，23(3):374-380.
[3] HUANG X，YE Q，ZHANG Y，et al.Fine-mapping of the PLCL2 gene identifies candidate variants associated with ischaemic stroke risk in metabolic syndrome patients[J].Front Neurol，2021，12:743169.
[4] WANG K，JIANG Q，GAO M，et al.A clinical prediction model based on interpretable machine learning algorithms for prolonged hospital stay in acute ischemic stroke patients:a real-world study[J].Front Endocrinol(Lausanne)，2023，14:1165178.
[5] 田林，任绪泽，涂峥程.人工智能、机器学习和深度学习在医学诊断中的应用进展[J].现代医学，2024，52(9)：1480-1484.
[6] 张华，陶立元，赵一鸣.随机森林算法的原理及其在临床研究中的应用[J].中华儿科杂志，2021，59(9)：798.
[7] 中华医学会神经病学分会，中华医学会神经病学分会脑血管病学组.中国急性缺血性卒中诊治指南2023[J].中华神经科杂志，2024，57(6):523-559.
[8] ADAMS H P，BENDIXEN B H，KAPPELLE L J，et al.Classification of subtype of acute ischemic stroke.Definitions for use in a multicenter clinical trial.TOAST.Trial of Org 10172 in Acute Stroke Treatment[J].Stroke，1993，24(1):35-41.
[9] 俞梁，楼晶晶，陈苗，等.WMR对大动脉粥样硬化性卒中患者短期转归的影响及预测价值分析[J].中华全科医学，2020，18(1)：41-44.
[10] WU S，WU B，LIU M，et al.Stroke in China:advances and challenges in epidemiology，prevention，and management[J].Lancet Neurol，2019，18(4):394-405.
[11] VERHOEVEN J I，ALLACH Y，VAARTJES I C H，et al.Ambient air pollution and the risk of ischaemic and haemorrhagic stroke[J].Lancet Planet Health，2021，5(8):e542-e552.
[12] FREDMAN G，TABAS I.Boosting inflammation resolution in atherosclerosis:the next frontier for therapy[J].Am J Pathol，2017，187(6):1211-1221.
[13] CHEN C，GU L，CHEN L，et al.Neutrophil-to-lymphocyte ratio and platelet-to-lymphocyte ratio as potential predictors of prognosis in acute ischemic stroke[J].Front Neurol，2020，11:525621.
[14] LI Z，YU F，ZHOU X，et al.Promoter hypomethylation of microRNA223 gene is associated with atherosclerotic cerebral infarction[J].Atherosclerosis，2017，263:237-243.
[15] KIVIMäKI M，LAWLOR D A，JUONALA M，et al.Lifecourse socioeconomic position，C-reactive protein，and carotid intima-media thickness in young adults:the cardiovascular risk in Young Finns Study[J].Arterioscler Thromb Vasc Biol，2005，25(10):2197-2202.
[16] ABEDI V，GOYAL N，TSIVGOULIS G，et al.Novel Screening Tool for stroke using artificial neural network[J].Stroke，2017，48(6):1678-1681.
[17] 韩玉，施海龙，曲波，等.随机森林方法在医学中的应用[J].中国预防医学杂志，2014，15(1)：79-81.
[18] BOLICK D T，SKAFLEN M D，JOHNSON L E，et al.G2A deficiency in mice promotes macrophage activation and atherosclerosis[J].Circ Res，2009，104(3):318-327.
[19] CHEN Z，HE Y，SU Y，et al.Association of inflammatory and platelet volume markers with clinical outcome in patients with anterior circulation ischaemic stroke after endovascular thrombectomy[J].Neurol Res，2021，43(6):503-510.
[20] 张力维，李德鑫，王义成，等.颈动脉斑块SMI分级联合血清超敏C-反应蛋白在急性缺血性脑卒中风险评估中的应用价值[J].河北医科大学学报，2023，44(3)：329-333.
[21] 王学成，许晓红，王中新.C反应蛋白/清蛋白比值与急性缺血性脑卒中严重程度相关性分析[J].国际检验医学杂志，2023，44(6)：749-751.
[22] 易晓净，郑开明，王红胜，等.NLR联合MPV预测老年急性缺血性脑卒中病人静脉溶栓治疗预后的临床价值[J].实用老年医学，2023，37(3):274-277.
[23] SUN G，YANG Y，CHEN Z，et al.Neutrophil to lymphocyte ratio predicts outcome of stroke by cervicocranial arterial dissection[J].Front Med(Lausanne)，2020，7:598055.

服务与反馈：

【文章下载】【发表评论】【查看评论】【加入收藏】

提示：您还未登录，请登录！点此登录