[1]张 岩,孙成建,张照龙,等.基于机器学习的前交通动脉瘤破裂预测模型的构建[J].介入放射学杂志,2021,30(04):412-417.
 ZHANG Yan,SUN Chengjian,ZHANG Zhaolong,et al.Construction of prediction model for anterior communicating aneurysm rupture based on machine learning technique[J].journal interventional radiology,2021,30(04):412-417.
点击复制

基于机器学习的前交通动脉瘤破裂预测模型的构建()

PDF下载中关闭

分享到:

《介入放射学杂志》[ISSN:1008-794X/CN:31-1796/R]

卷:
30
期数:
2021年04
页码:
412-417
栏目:
教学园地
出版日期:
2021-05-04

文章信息/Info

Title:
Construction of prediction model for anterior communicating aneurysm rupture based on machine learning technique
作者:
张 岩 孙成建 张照龙 谢宜兴 徐 锐 刘国平 赵晓龙 邵黎明 王振光
Author(s):
ZHANG Yan SUN Chengjian ZHANG Zhaolong XIE Yixing XU Rui LIU Guoping ZHAO Xiaolong SHAO Liming WANG Zhenguang.
School of Basic Medicine, Qingdao University; Department of Interventional Medicine, Affiliated Hospital of Qingdao University; PET/CT Center of Affiliated Hospital of Qingdao University, Qingdao, Shandong Province 266000, China
关键词:
【关键词】 前交通动脉瘤 机器学习 破裂 预测模型
文献标志码:
A
摘要:
【摘要】 目的 利用决策树、随机森林、梯度提升的机器学习方法建立前交通动脉瘤破裂的预测模型。方法 回顾性纳入2012年12月至2020年4月期间在青岛大学附属医院诊治的临床及影像学资料完整的前交通动脉瘤患者,符合纳入标准的有381例;其中破裂引起蛛网膜下腔出血患者244例,未破裂前交通动脉瘤患者137例。收集患者的年龄、性别、吸烟史、高血压病史、蛛网膜下腔出血病史和影像学特征,包括前交通动脉瘤的高度、瘤颈宽度、是否有A1优势、动脉瘤是否规则、动脉瘤朝向。利用机器学习方法纳入上述特征建立预测模型,并通过受试者工作特征(ROC)曲线评价预测模型。结果 对比破裂组与未破裂组年龄、动脉瘤高度、瘤颈宽度、动脉瘤不规则及A1优势征差异有统计学意义。决策树预测模型ROC曲线下面积为0.737(95% CI:0.637~0.837),准确率为73.15%;随机森林预测模型ROC曲线下面积为0.675(95%CI:0.569~0.7806),准确率为68.52%;梯度提升模型ROC中曲线下面积为0.758(95%CI:0.6569~0.8587),准确率为77.78%。结论 通过机器学习方法建立的预测模型能够较好地进行前交通动脉瘤破裂的预测。

参考文献/References:

[1] Brown RD, Broderick JP. Unruptured intracranial aneurysms: epidemiology,natural history,management options,and familial screening[J]. Lancet Neurol, 2014, 13: 393-404.
[2] Cai W, Hu C, Gong J, et al. Anterior communicating artery aneurysm morphology and the risk of rupture[J]. World Neurosurg, 2018, 109: 119-126.
[3] Brzegowy P, Kucybala I, Krupa K, et al. Angiographic and clinical results of anterior communicating artery aneurysm endovascular treatment[J]. Wideochir Inne Tech Maloinwazyjne, 2019, 14: 451- 460.
[4] Greving JP, Wermer MJ, Brown J, et al. Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies[J]. Lancet Neurol, 2014, 13: 59-66.
[5] Kim MC, Hwang SK. The rupture risk of aneurysm in the anterior communicating artery: a single center study[J]. J Cerebrovasc Endovasc Neurosurg, 2017, 19: 36- 43.
[6] 谭华桥,李明华,朱悦琦,等. 前交通动脉瘤破裂的临床和放射解剖学危险因素[J]. 介入放射学杂志, 2016, 25:562-567.
[7] UCAS Japan Investigators, Morita A, Kirino T, et al. The natural course of unruptured cerebral aneurysms in a Japanese cohort[J]. N Engl J Med, 2012, 366: 2474-2482.
[8] Mocco J, Brown RJ, Torner JC, et al. Aneurysm morphology and prediction of rupture:an international study of unruptured intracranial aneurysms analysis[J]. Neurosurgery, 2018, 82: 491- 496.
[9] Li M, Hu S, Yu N, et al. Association between meteorological factors and the rupture of intracranial aneurysms[J]. J Am Heart Assoc, 2019, 8: e012205.
[10] Ma X, Yang Y, Liu D, et al. Demographic and morphological characteristics associated with rupture status of anterior commu-nicating artery aneurysms[J]. Neurosurg Rev, 2020, 43: 589-595.
[11] Tateshima S, Murayama Y, Villablanca JP, et al. Intraaneurysmal flow dynamics study featuring an acrylic aneurysm model manu-factured using a computerized tomography angiogram as a mold[J]. J Neurosurg, 2001, 95: 1020-1027.
[12] Matsukawa H, Uemura A, Fujii M, et al. Morphological and clinical risk factors for the rupture of anterior communicating artery aneurysms[J]. J Neurosurg, 2013, 118: 978-983.
[13] Xu T, Lin B, Liu S, et al. Larger size ratio associated with the rupture of very small(≤3 mm) anterior communicating artery aneurysms[J]. J Neurointerv Surg, 2017, 9: 278-282.
[14] Xu L, Zhang F, Wang H, et al. Contribution of the hemody-namics of A1 dysplasia or hypoplasia to anterior communicating artery aneurysms: a 3- dimensional numerical simulation study[J]. J Comput Assist Tomogr, 2012, 36: 421- 426.
[15] Detmer FJ, Chung BJ, Jimenez C, et al. Associations of hemody-namics, morphology, and patient characteristics with aneurysm rupture stratified by aneurysm location[J]. Neuroradiology, 2019, 61: 275-284.
[16] Yu HY, Li HY, Liu J, et al. An approach to quantitative assessment of hemodynamic differences between unruptured and ruptured ophthalmic artery aneurysms[J]. Comput Methods Biomech Biomed Engin, 2016, 19: 1456-1461.
[17] Zhang X, Karuna T, Yao ZQ, et al. High wall shear stress beyond a certain range in the parent artery could predict the risk of anterior communicating artery aneurysm rupture at follow- up[J]. J Neurosurg, 2018, 131: 868-875.
[18] Wermer MJ, van der Schaaf IC, Algra A, et al. Risk of rupture of unruptured intracranial aneurysms in relation to patient and aneurysm characteristics: an updated meta- analysis[J]. Stroke, 2007, 38: 1404-1410.
[19] Liu J, Chen Y, Lan L, et al. Prediction of rupture risk in anterior communicating artery aneurysms with a feed- forward artificial neural network[J]. Eur Radiol, 2018, 28: 3268-3275.
[20] Chen G, Lu M, Shi Z, et al. Development and validation of machine learning prediction model based on computed tomography angiography- derived hemodynamics for rupture status of intracranial aneurysms: a Chinese multicenter study[J]. Eur Radiol, 2020, 30: 5170-5182.
[21] 温凌字,陈 曦,雷 毅,等. 基于形态学分析的后交通动脉瘤破裂风险评分预测模型[J]. 介入放射学杂志, 2018, 27:919- 923.

相似文献/References:

[1]陈亚奇,侍海存,宋维根.微弹簧圈栓塞前交通动脉瘤效果评价[J].介入放射学杂志,2015,(07):568.
 CHEN Ya- qi,SHI Hai- cun,SONG Wei- gen.The use of micro- coils in obstructing anterior communicating artery aneurysms: evaluation of its effect[J].journal interventional radiology,2015,(04):568.
[2]李俊君,路 华.不同介入栓塞技术对前交通动脉瘤破裂患者认知功能的影响[J].介入放射学杂志,2016,(05):374.
 LI Jun- jun,LU Hua.The influence of different interventional embolization techniques on the cognitive function of patients with ruptured anterior communicating artery aneurysm[J].journal interventional radiology,2016,(04):374.
[3]吴虹霖,雷丽程,杨茂江,等.支持向量机CT引导下肺穿刺活检气胸预测模型的研究[J].介入放射学杂志,2018,27(06):572.
 WU Honglin,LEI Licheng,YANG Maojiang,et al.The establishment and application of pneumothorax prediction model for CT- guided percutaneous transthoracic lung biopsy based on support vector machine[J].journal interventional radiology,2018,27(04):572.
[4]张清平,魏强国,李宝民,等.前交通动脉瘤介入术中胼胝体下动脉保护与前交通动脉综合征相关性研究 [J].介入放射学杂志,2020,29(03):296.
 ZHANG Qingping,WEI Qiangguo,LI Baomin,et al.Correlation between the protection of subcallosal artery and the anterior communicating artery syndrome in interventional embolization of anterior communicating aneurysm[J].journal interventional radiology,2020,29(04):296.
[5]翟義胲,林 雪,蒲圆金,等.基于机器学习的肝动脉化疗栓塞术后栓塞综合征预测模型构建和比较[J].介入放射学杂志,2023,32(09):886.
 ZHAI Yihai,LIN Xue,PU Yuanjin,et al.Construction of the model based on machine learning algorithm technique used for predicting post-embolization syndrome after hepatic artery chemoembolization[J].journal interventional radiology,2023,32(04):886.
[6]何梓君,孔 健.人工智能在介入放射学中的运用前景及挑战[J].介入放射学杂志,2023,32(12):1251.
 HE Zijun,KONG Jian..The application prospects and challenges of artificial intelligence in interventional radiology[J].journal interventional radiology,2023,32(04):1251.

备注/Memo

备注/Memo:
(收稿日期:2020- 07-24)
(本文编辑:俞瑞纲)
更新日期/Last Update: 2021-05-01