椎动脉支架内再狭窄的人工神经网络分析

doi:10.3969/j.issn.0258-8021. 2015. 04.004

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (756 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要探讨椎动脉狭窄支架植入术后再狭窄的危险因素，并利用人工神经网络对椎动脉支架内再狭窄（ISR）进行预测分析。首先，随访97例临床患者，对 12种可能影响椎动脉支架内再狭窄的因素进行单因素分析，总结出具有统计学意义的相关因素。然后，利用BP神经网络建立影响因素样本集与对应的ISR之间的隐性联系模型。最后，利用神经网络预测患者是否会发生支架内再狭窄，并对预测准确率进行评估。结果表明，置入支架后，再狭窄组中支架长度平均值为15 mm，无再狭窄组患者中支架长度平均值为17 mm，两者具有显著差异(P=0.005)；再狭窄组患者平均扩张比为1.15，无再狭窄组患者平均扩张比为1.17，两者具有显著差异（P=0.01）；再狭窄组和无再狭窄组患者椎动脉侧别也具有显著差异（P=0.045）。同时，评估结果显示，BP神经网络模型预测结果令人满意，不会发生ISR的确诊率q175%，会发生ISR确诊率q2=100%。支架长度、椎动脉侧别和支架扩张比对椎动脉ISR具有显著性影响。BP神经网络模型可用于预测椎动脉ISR的发生。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	乔爱科^{#* }彭坤牛静

关键词 ：血管内支架, 动脉粥样硬化, 统计分析, 人工神经网络

Abstract：The purpose of this paper is to analyze risk factors causing the vertebral artery instent restenosis (ISR). Applying the artificial neural network (ANN), we further tried to give predictions on the occurrence of ISR. The first step of our strategy was to follow up 97 randomly picked clinical patients, figuring out the statistical relevance for each of the 12 possible factors leading to ISR. We then established a model to connect the factors with ISR using the back propagation (BP) neural network. The last procedure was to assess our results by comparing our predictions with the actual occurrence of ISR. Our observations show that, the average length of stent is (15±1.52) mm for ISR patients, and（17±1.50）mm for nonISR patients. The value of P=0.005 indicates a statistical significance. The average stent expansion is 1.17±0.16 for ISR patients and 115±025 for nonISR patients. P=0.01 exhibits a statistical significance. The side of vertebral artery for both ISR and nonISR patients is of statistical significance P=0.045. Moreover, the assessments show that the BP neural network prediction model is efficient. Diagnosis rate of nonISR is q1>=75%, while that of ISR is q2=100%. Stent length, vertebral sides and stent expansion are significant factors for the vertebral artery ISR. BP neural networks can be used to predict the occurrence of the vertebral artery ISR.

基金资助:国家自然科学基金（81171107）

引用本文:

乔爱科^{#* }彭坤牛静. 椎动脉支架内再狭窄的人工神经网络分析[J]. 中国生物医学工程学报, 2015, 34(4): 407-412.
Qiao Aike^#*Peng Kun Niu Jing. Artificial Neural Network Analysis for Vertebral Artery InStent Restenosis. journal1, 2015, 34(4): 407-412.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2015. 04.004 或 http://cjbme.csbme.org/CN/Y2015/V34/I4/407

［1］Vajda Z, Miloslavski E, Güthe T, et al. Treatment of stenoses of vertebral artery origin using short drugeluting coronary stents: improved followup results［J］. American Journal of Neuroradiology, 2009, 30(9): 1653-1656.
［2］Thompson MC, Issa MA, Lazzaro MA, et al. The natural history of vertebral artery origin stenosis［J］. Journal of Stroke and Cerebrovascular Diseases, 2014, 23(1): e1-e4.［3］赵慧玭, 李慎茂, 张广平. 椎动脉起始部支架置入术后再狭窄的病因及防治［J］. 介入放射学杂志, 2010 (12): 1000-1003.
［4］Haghighi AB, Edgell RC, CruzFlores S, et al. Vertebral artery origin stenosis and its treatment［J］. Journal of Stroke and Cerebrovascular Diseases, 2011, 20(4): 369-376.［5］SSYLVIA Study Investigators. Stenting of symptomatic atherosclerotic lesions in the vertebral or intracranial arteries (SSYLVIA) study results［J］. Stroke, 2004, 35(6): 1388-1392.
［6］Albuquerque FC, Levy EI, Turk AS, et al. Angiographic patterns of wingspan instent restenosis ［J］. Neurosurgery, 2008, 63(1): 23-28.
［7］Lee MS, Jurewitz D, Aragon J, et al. Stent fracture associated with drugeluting stents: Clinical characteristics and implications［J］. Catheterization and Cardiovascular Interventions, 2007, 69(3): 387-394.
［8］Schillinger M, Exner M, Mlekusch W, et al. Acutephase response after stent implantation in the carotid artery: association with 6-month instent restenosis［J］. Radiology, 2003, 227(2): 516-521.
［9］Albuquerque FC, Fiorella D, Han P, et al. A reappraisal of angioplasty and stenting for the treatment of vertebral origin stenosis［J］. Neurosurgery, 2003, 53(3): 607-616.
［10］张赟, 乔爱科. 优化设计颅内动脉瘤用梯形截面支架底边长度［J］. 医用生物力学, 2012, 3: 012.
［11］Zhao D, Wang Y, Luo D, et al. PMirP: A premicroRNA prediction method based on structure\|sequence hybrid features［J］. Artificial Intelligence in Medicine, 2010, 49(2): 127-132.
［12］徐锋, 王崇倡, 张飞. 粒子群-BP 神经网络模型在大坝变形监测中的应用［J］. 测绘科学, 2012, 37(004): 181-183.
［13］雷松林. 基于 BP 网络和遗传算法的岩爆预测研究［D］. 上海：同济大学, 2008.
［14］喻宗泉, 喻晗. 神经网络控制［M］. 陕西: 西安电子科技大学出版社, 2009.
［15］Van Ooyen A, Nienhuis B. Improving the convergence of the backpropagation algorithm［J］. Neural Networks, 1992, 5(3): 465-471.
［16］从爽. 面向 Matlab 工具箱的神经网络理论与应用［M］. 合肥：中国科技大学出版社，2002.
［17］王勇, 卓金武, 魏永生, 等. Matlab 在数学建模中的应用［M］. 北京：北京航空航天大学出版社, 2011.
［18］徐锋, 王崇倡, 张飞. 粒子群-BP 神经网络模型在大坝变形监测中的应用［J］. 测绘科学, 2012, 37(4): 181-183.
［19］王继宗, 倪鸿光, 何锦云, 等. 混凝土强度预测和模拟的智能化方法［J］. 土木工程学报, 2003, 10(36): 24-29.
［20］Buckenham TM, Wright IA. Ultrasound of the extracranial vertebral artery ［J］. The British Journal of Radiology. 2004, 77: 15-20.
［21］Ederle J, Bonati L H, Dobson J, et al. Endovascular treatment with angioplasty or stenting versus endarterectomy in patients with carotid artery stenosis in the Carotid and Vertebral Artery Transluminal Angioplasty Study (CAVATAS): longterm followup of a randomised trial［J］. The Lancet Neurology, 2009, 8(10): 898-907.
［22］Mauri L, O’Malley AJ, Cutlip DE, et al. Effects of stent length and lesion length on coronary restenosis［J］. The American Journal of Cardiology, 2004, 93(11): 1340-1346.
［23］石进, 张英谦, 吕强, 等. 血管内支架成形术治疗椎动脉开口部狭窄的临床观察［J］. 中华老年心脑血管病杂志, 2007, 9(9): 611-614.
［24］Lederman RJ, Mendelsohn FO, Santos R, et al. Primary renal artery stenting: characteristics and outcomes after 363 procedures［J］. American Heart Journal, 2001, 142(2): 314-323.
［25］蔡学礼, 高峰. 椎动脉狭窄血管成形术后再狭窄因素及处理［J］. 临床放射学杂志, 2013, 32(9): 1327-1331.