[1]陈爱国.基于随机森林算法的颈动脉支架植入术后残留预测模型构建分析[J].卒中与神经疾病杂志,2022,29(04):338-343.[doi:10.3969/j.issn.1007-0478.2022.04.007]
　Chen Aiguo..Construction and analysis of prediction model for residual stenosis after carotid artery stenting based on random forest algorithm[J].Stroke and Nervous Diseases,2022,29(04):338-343.[doi:10.3969/j.issn.1007-0478.2022.04.007]
点击复制

基于随机森林算法的颈动脉支架植入术后残留预测模型构建分析()
分享到：

《卒中与神经疾病》杂志[ISSN:1007-0478/CN:42-1402/R]

卷:
第29卷
期数:
2022年04期
页码:
338-343
栏目:
论著
出版日期:
2022-09-10

文章信息/Info

Title:
Construction and analysis of prediction model for residual stenosis after carotid artery stenting based on random forest algorithm
文章编号:
1007-0478(2022)04-0338-06
作者:
陈爱国
101300 北京市顺义区医院神经外科
Author(s):
Chen Aiguo.
Neurosurgery, Shunyi District Hospital, Beijing 101300
关键词:
颈动脉支架植入术; 随机森林算法; 斑块特征; 残留狭窄
Keywords:
Carotid artery stenting Random forest algorithm Plaque features Residual stenosis
分类号:
R743
DOI:
10.3969/j.issn.1007-0478.2022.04.007
文献标志码:
A
摘要:
目的 探讨基于随机森林算法的颈动脉支架植入术(Carotid artery stent,CAS)后残留预测模型构建。方法 回顾性选取2018年10月-2021年10月于本院接受CAS治疗的颈动脉狭窄患者181例作为研究对象,根据术后残留狭窄情况分为残留狭窄组(狭窄率≥30%)和非残留狭窄组(狭窄率<30%); 比较2组临床资料,采用多因素Logistic回归分析和随机森林算法分别构建影响CAS后残留狭窄形成的2个预测模型,比较2个预测模型的预测效能。结果 术后残留狭窄发生51例(28.18%)归为残留狭窄组,其余130例归为非残留狭窄组。2组术前体质量指数(Body mass index,BMI)、年龄、吸烟史、高血压病占比、术前狭窄处血管内径、支架类型、斑块形态、斑块钙化情况比较均有明显差异(P<0.05)。多因素Logistic回归分析显示,术前狭窄处血管内径(OR=0.012,95%CI=0.001～0.114)为CAS后残留狭窄的保护因素,高血压病(OR=1.057,95%CI=1.035～1.079)、闭环支架(OR=2.773,95%CI=1.067～7.202)、不规则斑块(OR=2.698,95%CI=1.079～6.750)、斑块钙化(OR=5.488,95%CI=2.073～14.525)为CAS后残留狭窄的危险因素(P均<0.05)。对随机森林模型各变量的重要程度进行排序,排名在前的重要预测变量为术前狭窄处血管内径、斑块形态、斑块钙化情况、高血压病、支架类型、BMI、年龄、吸烟史。基于随机森林算法构建的预测模型的诊断效能[曲线下面积(Area of the under curve,AUC)为0.884]高于基于多因素Logistic回归分析的预测模型的诊断效能(AUC为0.821)。结论 基于随机森林算法构建的预测模型能更有效预测CAS后残留狭窄风险,术前狭窄处血管内径、斑块形态、斑块钙化情况、高血压病、支架类型是CAS后残留狭窄风险的影响因素。
Abstract:
ObjectiveTo construct the prediction model for residual stenosis after carotid artery stenting(CAS)based on random forest algorithm.Methods A total of 181 patients with carotid artery stenosis who received CAS in our hospital from October 2018 to October 2021 were retrospectively selected as the research subjects, and they were divided into residual stenosis group(stenosis rate ≥30%)and non-residual stenosis group(stenosis rate <30%)according to the degree of residual stenosis after CAS. The clinical data of these two groups were collected, and multivariate logistic regression analysis and random forest algorithm were respectively applied to construct two predictive models for predicting occurance of residual stenosis after CAS. The predictive performances of these two models were assessed.Results 51 cases(28.18%)of postoperative residual stenosis were identified as the residual stenosis group, while the remaining 130 cases were identified as the non-residual stenosis group. There were significant differences between the two groups in preoperative body mass index(BMI), age, smoking, proportion of hypertension, diameter of preoperative stenosis artery, type of stent, plaque morphology, and plaque calcification(P<0.05).Multivariate logistic regression analysis showed that the diameter of preoperative stenosis artery(OR=0.012, 95%CI=0.001～0.114)was a protective factor for residual stenosis after CAS, but hypertension(OR=1.057, 95%CI=1.035～1.079), closed-loop stent(OR=2.773, 95%CI=1.067～7.202), irregular plaque surface(OR=2.698, 95%CI=1.079～6.750)and plaque calcification(OR=5.488, 95%CI=2.073～14.525)were risk factors for residual stenosis after CAS(P<0.05). All variables ranked by importance in the random forest algorithm were the diameter of preoperative stenosis artery, plaque morphology, plaque calcification, hypertension, type of stent, BMI, age, and smoking. The results showed that the diagnostic performance of the prediction model based on random forest algorithm(area under the curve(AUC)was 0.884)was better than that based on multivariate logistic regression analysis(AUC was 0.821).Conclusion The prediction model based on random forest algorithm could more effectively predict the risk of residual stenosis after CAS. The diameter of preoperative stenosis artery, plaque morphology, plaque calcification, hypertension, and the type of stent are the risk factors for predicting residual stenosis after CAS.

参考文献/References:

[1] Osteraas ND, Crowley RW, Panos N, et al. Eptifibatide use following emergent carotid stenting in acute anterior circulation ischemic stroke with tandem occlusion[J]. J Stroke Cerebrovasc Dis, 2020, 29(9): 105021.
[2] Demirel S, Böckler D, Storck M. Comparison of long-term results of carotid endarterectomy for asymptomatic carotid artery stenosis[J]. Gefasschirurgie, 2018, 23(Suppl 1): 1-7.
[3] Lal BK, Roubin GS, Jones M, et al. Influence of multiple stents on periprocedural stroke after carotid artery stenting in the Carotid Revascularization Endarterectomy versus Stent Trial(CREST)[J]. J Vasc Surg, 2019, 69(3): 800-806.
[4] Featherstone RL, Dobson J, Ederle J, et al. Carotid artery stenting compared with endarterectomy in patients with symptomatic carotid stenosis(International Carotid Stenting Study): a randomised controlled trial with cost-effectiveness analysis[J]. Health Technol Assess, 2016, 20(20): 1-94.
[5] Dakour-Aridi H, Mathlouthi A, Locham S, et al. Predictors of midterm high-grade restenosis after carotid revascularization in a multicenter National database[J]. J Vasc Surg, 2020, 71(6): 1972-1981.
[6] Chen JH, Wu MH, Luo CB, et al. Long-term imaging follow-up to evaluate restenosis in patients with carotid stenosis after angioplasty and stenting[J]. J Chin Med Assoc, 2021, 84(1): 87-94.
[7] Tekieli , Musiaek P, Kabak-Ziembicka A, et al. Severe, recurrent in-stent carotid restenosis: endovascular approach, risk factors. Results from a prospective academic registry of 2637 consecutive carotid artery stenting procedures(TARGET-CAS)[J]. Postepy Kardiol Interwencyjnej, 2019, 15(4): 465-471.
[8] Yamashita K, Kokuzawa J, Kuroda T, et al. In-stent hypodense area at two weeks following carotid artery stenting predicts neointimal hyperplasia after two years[J]. Neuroradiol J, 2018, 31(3): 280-287.
[9] 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.中国脑血管病一级预防指南2015[J].中华神经科杂志,2015,48(8):629-643.
[10] 中华医学会外科学分会血管外科学组.颈动脉狭窄诊治指南[J].中华血管外科杂志,2017,2(2):78-84.
[11] Lin K, Chen L, Wang Y, et al. Endovascular treatment of cerebrovascular stenosis with stent for patients with ischemic cerebrovascular disease[J]. Medicine(Baltimore), 2020, 99(47): e23313.
[12] Yaghi S, De HA, Rostanski S, et al. Carotid stenosis and recurrent ischemic stroke: a Post-Hoc analysis of the POINT trial[J]. Stroke, 2021, 52(7): 2414-2417.
[13] Dorigo W, Fargion A, Giacomelli E, et al. A propensity matched comparison for open and endovascular treatment of post-carotid endarterectomy restenosis[J]. Eur J Vasc Endovasc Surg, 2018, 55(2): 153-161.
[14] Mazurek A, Partyka L, Trystula M, et al. Highly-calcific carotid lesions endovascular management in symptomatic and increased-stroke-risk asymptomatic patients using the CGuardTM dual-layer carotid stent system: Analysis from the PARADIGM study[J]. Catheter Cardiovasc Interv, 2019, 94(1): 149-156.
[15] 陶昀璐,华扬,贾凌云,等.颈动脉狭窄血管结构特征与支架术后残余狭窄的相关性分析[J].中华超声影像学杂志,2017,26(6):490-493.
[16] Gijsen F, Vis B, Barrett HE, et al. Morphometric and mechanical analyses of calcifications and fibrous plaque tissue in carotid arteries for plaque rupture risk assessment[J]. IEEE Trans Biomed Eng, 2021, 68(4): 1429-1438.
[17] Xu X, Hua Y, Wang L, et al. Correlation between risk factors of cerebrovascular disease and calcified plaque characteristics in patients with atherosclerotic severe carotid stenosis[J]. Neurol Res, 2020, 42(1): 83-89.
[18] 于志强.颈动脉内膜切除术与颈动脉支架成形术治疗症状性颈动脉极重度狭窄的效果及安全性[J].中国实用医刊,2019,46(13):30-32.
[19] Zhang N, Liu X, Xiao J, et al. Plaque morphologic quantification reliability of 3D Whole-Brain vessel wall imaging in patients with intracranial atherosclerotic disease: a comparison with conventional 3D targeted vessel wall imaging[J]. J Magn Reson Imaging, 2021, 54(1): 166-174.
[20] Hamada O, Sakata N, Ogata T, et al. Contrast-enhanced ultrasonography for detecting histological carotid plaque rupture: Quantitative analysis of ulcer[J]. Int J Stroke, 2016, 11(7): 791-798.
[21] Gong X, Shi J, Huang J, et al. Comparison of hypertension in migrant and local patients with atherosclerotic diseases: a Cross-Sectional study in Shanghai, China[J]. Ann Glob Health, 2020, 86(1): 25.
[22] An D, Zhang J, Tang X, et al. Association of ATP2B1 common variants with asymptomatic intracranial and extracranial large artery stenosis in hypertension patients[J]. Clin Exp Hypertens, 2019, 41(4): 323-329.
[23] Haley W, Shawl F, Charles S3, et al. Non-Adherence to antihypertensive guidelines in patients with asymptomatic carotid stenosis[J]. J Stroke Cerebrovasc Dis, 2021, 30(8): 105918.
[24] Kobza II, Didenko OZ, Yavorskyi OG, et al. The dynamics of blood pressure of different age patients groups with hypertension and diabetes type ii after correction of carotid stenosis[J]. Wiad Lek, 2019, 72(5 cz 2): 1007-1011.
[25] Takao N, Hagiwara Y, Shimizu T, et al. Preprocedural carotid plaque echolucency as a predictor of In-Stent intimal restenosis after carotid artery stenting[J]. J Stroke Cerebrovasc Dis, 2020, 29(12): 105339.
[26] Müller MD, Gregson J, Mccabe D, et al. Stent design, restenosis and recurrent stroke after carotid artery stenting in the international carotid stenting study[J]. Stroke, 2019, 50(11): 3013-3020.
[27] Myouchin K, Takayama K, Wada T, et al. Carotid artery stenting using a Closed-Cell Stent-in-Stent technique for unstable plaque[J]. J Endovasc Ther, 2019, 26(4): 565-571.
[28] Machnik R, Paluszek P, Tekieli , et al. Mesh-covered(Roadsaver)stent as a new treatment modality for symptomatic or high-risk carotid stenosis[J]. Postepy Kardiol Interwencyjnej, 2017, 13(2): 130-134.

更新日期/Last Update: 2022-09-10