切换至 "中华医学电子期刊资源库"

中华脑血管病杂志(电子版) ›› 2023, Vol. 17 ›› Issue (05) : 464 -470. doi: 10.11817/j.issn.1673-9248.2023.05.007

临床研究

机器学习对预测颈内动脉非急性闭塞患者血管内再通术成功的潜在价值
王俊杰, 尹晓亮, 刘二腾, 陆军, 祁鹏, 胡深, 杨希孟, 陈鲲鹏, 张东, 王大明()   
  1. 100730 北京医院神经外科 国家老年医学中心 中国医学科学院老年医学研究院
    100191 北京大学第三医院神经外科
  • 收稿日期:2023-07-30 出版日期:2023-10-01
  • 通信作者: 王大明
  • 基金资助:
    首都卫生发展科研专项项目(首发2020-4-4053)

Predicting successful endovascular recanalization for non-acute occlusion of internal carotid artery: potential value of machine learning

Junjie Wang, Xiaoliang Yin, Erteng Liu, Jun Lu, Peng Qi, Shen Hu, Ximeng Yang, Kunpeng Chen, Dong Zhang, Daming Wang()   

  1. Department of Neurosurgery, Beijing Hospital National Center of Gerontology Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing 100730, China
    Department of Neurosurgery, Peking University Third Hospital, Beijing 100191, China
  • Received:2023-07-30 Published:2023-10-01
  • Corresponding author: Daming Wang
引用本文:

王俊杰, 尹晓亮, 刘二腾, 陆军, 祁鹏, 胡深, 杨希孟, 陈鲲鹏, 张东, 王大明. 机器学习对预测颈内动脉非急性闭塞患者血管内再通术成功的潜在价值[J/OL]. 中华脑血管病杂志(电子版), 2023, 17(05): 464-470.

Junjie Wang, Xiaoliang Yin, Erteng Liu, Jun Lu, Peng Qi, Shen Hu, Ximeng Yang, Kunpeng Chen, Dong Zhang, Daming Wang. Predicting successful endovascular recanalization for non-acute occlusion of internal carotid artery: potential value of machine learning[J/OL]. Chinese Journal of Cerebrovascular Diseases(Electronic Edition), 2023, 17(05): 464-470.

目的

使用机器学习算法预测模型探究影响颈内动脉非急性闭塞(NAOICA)血管内再通治疗成功的因素,并比较其与传统预测模型的预测效能。

方法

收集2016年1月至2021年12月因NAOICA在北京医院神经外科接受血管内再通术的患者的临床数据。采用包括正则化的Logistic回归(RLR)、支持向量机(SVM)、决策树(DT)、随机森林(RF)和极限梯度提升(XGBoost)在内的机器学习算法构建预测血管内再通技术成功的模型,评估其受试者工作特征曲线(ROC)的曲线下面积(AUC),并与基于变量筛选的传统Logistic回归模型比较其预测价值。

结果

共纳入NAOICA闭塞再通术患者69例(73例次),其中男性62例,年龄为(64.8±8.8)岁,技术成功率为67.1%。在预测血管内再通成功与否方面,表现最差的机器学习模型(DT)仍取得了与标准Logistic回归模型近似的效能(平均AUC分别为0.66和0.65),其他机器学习模型的表现均明显优于标准模型(平均AUC为0.74~0.84)。在大部分机器学习模型中,前交通动脉的代偿、亚急性闭塞、自发再通征象和闭塞段远端显影管腔部位是对模型贡献较大的重要预测变量。

结论

在NAOICA患者中,机器学习模型对血管内再通技术成功的预测效能要优于标准Logistic回归模型。

Objective

To explore the factors affecting the success of endovascular revascularization treatment for non-acute occlusion of the internal carotid artery (NAOICA) by machine learning predictive models, and to compare their predictive value with that of classic predictive models.

Methods

Patients who underwent endovascular revascularization for NAOICA at Department of Neurosurgery of Beijing Hospital from Jan. 2016 to Dec. 2021 were included. Machine learning algorithms including regularized Logistic regression, support vector machine, decision tree, random forest, and extreme gradient boosting were used to build models to predict the success of endovascular recanalization technology. Area under the ROC curves (AUC) and difference in mean AUC between the models were assessed.

Results

A total of 73 consecutive NAOICA recanalization attempts were performed in 69 patients [62 men; mean age of (64.8±8.8) years] with an overall technical success (primary outcome) rate of 67.1%. In terms of predicting endovascular recanalization success, even the worst prediction model based on machine learning had equivalent predictive ability to the standard Logistic regression model (mean AUC of 0.66 and 0.65, respectively), and all other machine learning models significantly outperformed the standard Logistic regression model (mean AUC of 0.74-0.84). Collateral blood flow from the anterior communicating artery, subacute occlusion, spontaneous recanalization, and segment of distal carotid visibility appeared as the crucial variables in most machine learning models.

Conclusion

In patients with NAOICA, machine learning algorithms can outperform classic Logistic regression model in predicting the technical success of endovascular revascularization.

图1 颈内动脉非急性闭塞患者数字减影血管成像颈总动脉造影侧位或斜位影像。黄色箭头示颈内动脉闭塞残端形态分型。图a为锥尖型;图b为截断型;图c为无残端
图2 颈内动脉非急性闭塞患者自发再通征的数字减影血管成像影像。示动脉中、晚期在闭塞颈内动脉管腔的原位置出现纤细、蜿蜒迂曲的微管样显影。图b为图a红色方框部分的放大图,更清晰显示微管样显影(黄色箭头)
表1 患者人口学信息和病变特征的分布
表2 标准Logistic回归分析预测闭塞再通成功与否的模型
表3 各模型对NAOICA血管内再通成功与否的预测效能比较(4折交叉验证)
表4 各预测模型中贡献最大的5个预测变量的分布情况
1
Wang YJ, Li ZX, Gu HQ, et al. China Stroke Statistics: an update on the 2019 report from the National Center for Healthcare Quality Management in Neurological Diseases, China National Clinical Research Center for Neurological Diseases, the Chinese Stroke Association, National Center for Chronic and Non-communicable Disease Control and Prevention, Chinese Center for Disease Control and Prevention and Institute for Global Neuroscience and Stroke Collaborations [J]. Stroke Vasc Neurol, 2022, 7(5): 415-450.
2
Benjamin EJ, Virani SS, Callaway CW, et al. Heart disease and stroke statistics-2018 update: a report from the American Heart Association [J]. Circulation, 2018, 137(12): e67-67e492.
3
Klijn CJ, Kappelle LJ, Tulleken CA, et al. Symptomatic carotid artery occlusion. A reappraisal of hemodynamic factors [J]. Stroke, 1997, 28(10): 2084-2093.
4
Flaherty ML, Flemming KD, McClelland R, et al. Population-based study of symptomatic internal carotid artery occlusion: incidence and long-term follow-up [J]. Stroke, 2004, 35(8): e349-352.
5
Powers WJ, Clarke WR, Grubb RL, et al. Extracranial-intracranial bypass surgery for stroke prevention in hemodynamic cerebral ischemia: the Carotid Occlusion Surgery Study randomized trial [J]. JAMA, 2011, 306(18): 1983-1992.
6
Grubb RLJr, Powers WJ, Clarke WR, et al. Surgical results of the carotid occlusion surgery study [J]. J Neurosurg, 2013, 118(1): 25-33.
7
Chen YH, Leong WS, Lin MS, et al. Predictors for successful endovascular intervention in chronic carotid artery total occlusion [J]. JACC Cardiovasc Interv, 2016, 9(17): 1825-1832.
8
Lee CW, Lin YH, Liu HM, et al. Predicting procedure successful rate and 1-year patency after endovascular recanalization for chronic carotid artery occlusion by CT angiography [J]. Int J Cardiol, 2016, 221: 772-776.
9
Kao HL, Hung CS, Li HY, et al. Long-term outcomes after endovascular recanalization in patients with chronic carotid artery occlusion [J]. Am J Cardiol, 2018, 122(10): 1779-1783.
10
Chao L, Qingbin M, Haowen X, et al. Imaging predictors for endovascular recanalization of non-acute occlusion of internal carotid artery based on 3D T1-SPACE MRI and DSA [J]. Front Neurol, 2021, 12: 692128.
11
Hamet P, Tremblay J. Artificial intelligence in medicine [J]. Metabolism, 2017, 69S: S36-36S40.
12
Mouridsen K, Thurner P, Zaharchuk G. Artificial intelligence applications in stroke [J]. Stroke, 2020, 51(8): 2573-2579.
13
Asadi H, Dowling R, Yan B, et al. Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy [J]. PLoS One, 2014, 9(2): e88225.
14
van Os H, Ramos LA, Hilbert A, et al. Predicting outcome of endovascular treatment for acute ischemic stroke: potential value of machine learning algorithms [J]. Front Neurol, 2018, 9: 784.
15
Nishi H, Oishi N, Ishii A, et al. Predicting clinical outcomes of large vessel occlusion before mechanical thrombectomy using machine learning [J]. Stroke, 2019, 50(9): 2379-2388.
16
Dönmez P. Introduction to Machine Learning, 2nd ed. [J]. Nat Lang Eng, 2013, 19(2): 285-288.
17
Cawley GC, Talbot NLC. On over-fitting in model selection and subsequent selection bias in performance evaluation [J]. J Mach Learn Res, 2010, 11: 2079-2107.
18
Trivedi UB, Bhatt M, Srivastava P, et al. Prevent Overfitting Problem in Machine Learning: A Case Focus on Linear Regression and Logistics Regression [A]. Proceedings of International Conference on ICRIHE [C]. India: Delhi, 2020: 345-349.
19
Lipton ZC. The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery [J]. Queue, 2018, 16(3): 31.
20
Olson RS, Cava W, Mustahsan Z, et al. Data-driven advice for applying machine learning to bioinformatics problems [J]. Pac Symp Biocomput, 2018, 23: 192-203.
[1] 洪玮, 叶细容, 刘枝红, 杨银凤, 吕志红. 超声影像组学联合临床病理特征预测乳腺癌新辅助化疗完全病理缓解的价值[J/OL]. 中华医学超声杂志(电子版), 2024, 21(06): 571-579.
[2] 明昊, 肖迎聪, 巨艳, 宋宏萍. 乳腺癌风险预测模型的研究现状[J/OL]. 中华乳腺病杂志(电子版), 2024, 18(05): 287-291.
[3] 庄燕, 戴林峰, 张海东, 陈秋华, 聂清芳. 脓毒症患者早期生存影响因素及Cox 风险预测模型构建[J/OL]. 中华危重症医学杂志(电子版), 2024, 17(05): 372-378.
[4] 黄鸿初, 黄美容, 温丽红. 血液系统恶性肿瘤患者化疗后粒细胞缺乏感染的危险因素和风险预测模型[J/OL]. 中华实验和临床感染病杂志(电子版), 2024, 18(05): 285-292.
[5] 奚玲, 仝瀚文, 缪骥, 毛永欢, 沈晓菲, 杜峻峰, 刘晔. 基于肌少症构建的造口旁疝危险因素预测模型[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(01): 48-51.
[6] 屈勤芳, 束方莲. 盆腔器官脱垂患者盆底重建手术后压力性尿失禁发生的影响因素及列线图预测模型构建[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2024, 18(06): 606-612.
[7] 公宇, 廖媛, 尚梅. 肝细胞癌TACE术后复发影响因素及预测模型建立[J/OL]. 中华肝脏外科手术学电子杂志, 2024, 13(06): 818-824.
[8] 王贝贝, 崔振义, 王静, 王晗妍, 吕红芝, 李秀婷. 老年股骨粗隆间骨折患者术后贫血预测模型的构建与验证[J/OL]. 中华老年骨科与康复电子杂志, 2024, 10(06): 355-362.
[9] 孙晗, 于冰, 武侠, 周熙朗. 基于循环肿瘤DNA 甲基化的结直肠癌筛查预测模型的构建与验证[J/OL]. 中华消化病与影像杂志(电子版), 2024, 14(06): 500-506.
[10] 韦巧玲, 黄妍, 赵昌, 宋庆峰, 陈祖毅, 黄莹, 蒙嫦, 黄靖. 肝癌微波消融术后中重度疼痛风险预测列线图模型构建及验证[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 715-721.
[11] 蔡晓雯, 李慧景, 丘婕, 杨翼帆, 吴素贤, 林玉彤, 何秋娜. 肝癌患者肝动脉化疗栓塞术后疼痛风险预测模型的构建及验证[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 722-728.
[12] 孙铭远, 褚恒, 徐海滨, 张哲. 人工智能应用于多发性肺结节诊断的研究进展[J/OL]. 中华临床医师杂志(电子版), 2024, 18(08): 785-790.
[13] 王誉英, 刘世伟, 王睿, 曾娅玲, 涂禧慧, 张蒲蓉. 老年乳腺癌新辅助治疗病理完全缓解的预测因素分析[J/OL]. 中华临床医师杂志(电子版), 2024, 18(07): 641-646.
[14] 董晟, 郎胜坤, 葛新, 孙少君, 薛明宇. 反向休克指数乘以格拉斯哥昏迷评分对老年严重创伤患者发生急性创伤性凝血功能障碍的预测价值[J/OL]. 中华临床医师杂志(电子版), 2024, 18(06): 541-547.
[15] 黄圣楷, 许斌, 苏健, 孙龙. 海南省2010~2020年乙型肝炎流行趋势的时间序列分析及预测[J/OL]. 中华临床医师杂志(电子版), 2024, 18(06): 555-561.
阅读次数
全文


摘要


AI


AI小编
你好!我是《中华医学电子期刊资源库》AI小编,有什么可以帮您的吗?