[1]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):572-577.
 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(06):572-577.
点击复制

支持向量机CT引导下肺穿刺活检气胸预测模型的研究()

PDF下载中关闭

分享到:

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

卷:
27
期数:
2018年06期
页码:
572-577
栏目:
临床研究
出版日期:
2018-06-25

文章信息/Info

Title:
The establishment and application of pneumothorax prediction model for CT- guided percutaneous transthoracic lung biopsy based on support vector machine
作者:
吴虹霖 雷丽程 杨茂江 蒋小凤 王 朗 李 杨 杨汉丰
Author(s):
WU Honglin LEI Licheng YANG Maojiang JIANG Xiaofeng WANG Lang LI Yang YANG Hanfeng
Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan Province 637000, China
关键词:
【关键词】 支持向量机 机器学习 预测模型 气胸 CT引导下肺穿刺活检
文献标志码:
A
摘要:
【摘要】 目的 基于患者基本信息、病变及手术相关因素,采用支持向量机(SVM),联合特征选择算法,建立CT引导下经皮胸腔肺穿刺活检(PTNB)气胸预测模型。方法 回顾性分析经CT引导下PTNB患者94例(气胸组/非气胸组:43/51)。于PACS系统上获取患者基本信息、肺部病变及穿刺活检术中的相关风险因素。采用特征选择的方法选取与气胸发生相关性较大的风险因素,采用SVM模型,并同神经网络(NN)、随机森林(RF)机器学习模型进行对比,建立气胸预测模型。结果 特征选择得到气胸风险因素按重要性大小排序:病灶深度、年龄、病灶大小、进针深度、穿刺针经过通气肺组织的长度、进针角度、穿刺针过胸膜凹陷及性别。与NN和RF相比,SVM预测性能最好,其准确度为88.9%、灵敏度为71.4%、特异度为100%。结论 机器学习方法可用于建立CT引导下PTNB气胸预测模型,SVM能构建预测气胸的最优模型, 辅助临床诊断。

参考文献/References:

[1] 许 彪, 陈 刚, 韦 璐. 多层螺旋CT引导BARD活检枪经皮肺穿刺活检的临床应用[J]. 介入放射学杂志, 2009, 18: 51- 53.
[2] Laspas F, Roussakis A, Efthimiadou R, et al. Percutaneous CT- guided fine- needle aspiration of pulmonary lesions: results and complications in 409 patients[J]. J Med Imaging Radiat Oncol, 2008, 52: 458- 462.
[3] Wallace MJ, Krishnamurthy S, Broemeling LD, et al. CT- guided percutaneous fine- needle aspiration biopsy of small(≤1- cm) pulmonary lesions[J]. Radiology, 2002, 225: 823- 828.
[4] Arabasadi Z, Alizadehsani R, Roshanzamir M, et al. Computer aided decision making for heart disease detection using hybrid neural network- genetic algorithm[J]. Comput Methods Programs Biomed, 2017, 141: 19- 26.
[5] 李 梅, 张 伟, 李永忠, 等. 支持向量机神经网络在判别前列腺癌中的应用研究[J]. 四川大学学报?医学版, 2013, 44: 666- 668.
[6] Gupta S, Tran T, Luo W, et al. Machine- learning prediction of cancer survival: a retrospective study using electronic administrative records and a cancer registry[J]. BMJ Open, 2014, 4: e004- e007.
[7] 尹祖钰. 基于主成分分析和递归特征消除的支持向量机分类方法研究[D]. 哈尔滨工业大学, 2016.
[8] Abreu PH, Santos MS, Abreu MH. Predicting breast cancer recurrence using machine learning techniques: a systematic review[J]. ACM Comput Surv, 2016, 49: 1- 40.
[9] 许泽兵, 翟昭华, 何 菲, 等. CT引导下经皮肺穿刺活检并发症的相关因素Logistic分析[J]. 川北医学院学报, 2011, 26: 167- 171.
[10] Anzidei M, Sacconi B, Fraioli F, et al. Development of a prediction model and risk score for procedure- related complications in patients undergoing percutaneous computed tomography- guided lung biopsy[J]. Eur J Cardiothorac Surg, 2015, 48: e1- e6.
[11] Chiappetta M, Rosella F, Dall’armi V, et al. CT guided fineneedle agobiopsy of pulmonary nodules: predictive factors for diagnosis and pneumothorax occurrence[J]. Radiol Med, 2016, 121: 635- 643.
[12] 陈万海, 沈晓文, 孙新刚, 等. 经皮肺活检常见并发症风险因素分析[J]. 介入放射学杂志, 2012, 21: 168- 171.
[13] 何 闯, 李 扬, 杨 丽, 等. CT引导下肺实性结节切割活检术后出血与气胸的多因素分析[J]. 介入放射学杂志, 2017, 26: 654- 659.
[14] 朱 柠, 何 剑, 夏敬文, 等. CT引导下经皮肺穿刺并发症的影响因素[J]. 临床肺科杂志, 2014, 19: 483- 485.
[15] 陈克敏, 黄 蔚, 吴志远. CT引导下肺活检和并发症的预防[J]. 介入放射学杂志, 2011, 20: 163- 165.
[16] 李国栋, 周正荣, 李文涛, 等. CT导引下经皮肺组织活检术常见并发症及穿刺体会[J]. 介入放射学杂志, 2007, 16: 847- 849.
[17] Min L, Xu X, Song Y, et al. Breath- hold after forced expiration before removal of the biopsy needle decreased the rate of pneumothorax in CT- guided transthoracic lung biopsy[J]. Eur J Radiol, 2013, 82: 187- 190.
[18] Akkermans R. 2013 annual congress of the European Respiratory Society[J]. Lancet Respir Med, 2013, 1: 594- 595.
[19] Yeow KM, Su IH, Pan KT, et al. Risk factors of pneumothorax and bleeding- multivariate analysis of 660 CT- guided coaxial cutting needle lung biopsies[J]. Chest, 2004, 126: 748- 754.
[20] Niu XK, Bhetuwal A, Yang HF. CT- guided core needle biopsy of pleural lesions: evaluating diagnostic yield and associated complications[J]. Korean J Radiol, 2015, 16: 206- 212.
[21] Cox JE, Chiles C, McManus CM, et al. Transthoracic needle aspiration biopsy: variables that affect risk of pneumothorax[J]. Radiology, 1999, 212: 165- 168.
[22] Rizzo S, Preda L, Raimondi S, et al. Risk factors for complications of CT- guided lung biopsies[J]. Radiol Med, 2011, 116: 548- 563.
[23] 杨肖华, 黄新宇, 汪国祥. CT引导下经皮肺穿刺活检术并发症的影响因素分析[J]. 介入放射学杂志, 2013, 22: 658- 662.
[24] Nour- Eldin NE, Alsubhi M, Emam A, et al. Pneumothorax complicating coaxial and non- coaxial CT- guided lung biopsy: comparative analysis of determining risk factors and management of pneumothorax in a retrospective review of 650 patients[J]. Cardiovasc Intervent Radiol, 2016, 39: 261- 270.
[25] Kakizawa H, Toyota N, Hieda M, et al. Risk factors for severity of pneumothorax after CT- guided percutaneous lung biopsy using the single- needle method[J]. Hiroshima J Med Sci, 2010, 59: 43- 50.
[26] Saji H, Nakamura H, Tsuchida T, et al. The incidence and the risk of pneumothorax and chest tube placement after percutaneous CT- guided lung biopsy: the angle of the needle trajectory is a novel predictor[J]. Chest, 2002, 121: 1521- 1526.

相似文献/References:

[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.
 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(06):412.
[2]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(06):886.
[3]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(06):1251.

备注/Memo

备注/Memo:
(收稿日期:2017-09-17)
(本文编辑:俞瑞纲)
更新日期/Last Update: 2018-06-09