脑出血患者静脉血栓栓塞症风险预测模型的构建及验证研究

doi:10.3761/j.issn.2096-7446.2025.09.003

摘要/Abstract

摘要：

目的构建及验证脑出血患者静脉血栓栓塞症（venous thromboembolism，VTE）风险预测模型，并与Caprini评分表比较预测性能。方法建模组回顾性选取2008年—2019年美国重症监护医学信息数据库Ⅳ中的脑出血患者，利用单因素和多因素分析确定危险因素，构建并评价预测模型。采用Bootstrap抽样法对模型进行内部验证。验证组回顾性选取2016年—2024年中国某三级甲等医院的脑出血患者，进行外部验证，并与Caprini评分表比较。结果 ICU入住时长（OR=1.064）、淋巴细胞绝对计数（OR=0.711）及BMI（OR=1.932）是脑出血患者发生VTE的独立危险因素。建模组受试者操作特征曲线下面积（area under curve，AUC）为0.767，灵敏度为0.718，特异度为0.684。Hosmer-Lemeshow检验结果显示，χ²=3.075，P=0.930。验证组模型的AUC为0.785，Caprini评分表的AUC为0.608。结论该预测模型具有良好的预测性能，可为临床医护人员早期识别脑出血患者中的VTE高危人群提供理论依据。

关键词: 脑出血, 静脉血栓栓塞症, 列线图, 风险预测模型, 护理

Abstract:

Objective To develop and validate a risk prediction model for venous thromboembolism（VTE） in patients with intracerebral hemorrhage（ICH） and compare its predictive ability with Caprini score. Methods The modeling group retrospectively selected ICH patients from the Medical Information Mart for Intensive Care-IV （MIMIC-IV） database（2008—2019）. Risk factors were identified using univariate and logistic regression analyses，and a risk prediction model was established. Internal validation was conducted using the bootstrap resampling method. The validation group retrospectively selected ICH patients in a tertiary hospital in China from 2016 to 2024 for external validation and compared it with the Caprini score. Results ICU length of stay（OR=1.064），absolute lymphocyte count（OR=0.711），and BMI（OR=1.932） were identified as the three independent risk factors for VTE in ICH patients. In the modeling group，the model demonstrated an AUC of 0.767，with a sensitivity of 0.718 and specificity of 0.684. The Hosmer-Lemeshow test indicated good calibration（χ²=3.075，P= 0.930）. In the external validation group，the model achieved an AUC of 0.785，AUC of the Caprini score was 0.608. Conclusion This prediction model has good predictive performance and can provide theoretical basis for clinical medical staff to early identify high-risk VTE populations in ICH patients.

Key words: Cerebral Hemorrhage, Venous Thromboembolism, Nomogram, Risk Prediction Model, Nursing

叶洪敏, 甘秀妮, 高燕, 张欢, 周雯, 李冬雪. 脑出血患者静脉血栓栓塞症风险预测模型的构建及验证研究[J]. 中华急危重症护理杂志, 2025, 6(9): 1042-1049.

YE Hongmin, GAN Xiuni, GAO Yan, ZHANG Huan, ZHOU Wen, LI Dongxue. Development and validation of a risk prediction model for venous thromboembolism in patients with intracerebral hemorrhage[J]. Chinese Journal of Emergency and Critical Care Nursing, 2025, 6(9): 1042-1049.

图/表 9

图1

表1

表2

表3

图2

图3

图4

图5

表4

参考文献 19

[1]	中华人民共和国国家卫生健康委员会. 脑血管病防治指南(2024年版)[J]. 磁共振成像, 2025, 16(1):1-8.
	National Health Commission of the People’s Republic of China. Guideline for prevention and treatment of cerebrovascular disease(2024 edition)[J]. Chin J Magn Reson Imag, 2025, 16(1):1-8.
[2]	Katan M, Luft A. Global burden of stroke[J]. Semin Neurol, 2018, 38(2):208-211. doi: 10.1055/s-0038-1649503 pmid: 29791947
[3]	Chu QH, Liao L, Wei WX, et al. Venous thromboembolism in ICU patients with intracerebral hemorrhage:risk factors and the prognosis after anticoagulation therapy[J]. Int J Gen Med, 2021, 14:5397-5404.
[4]	张萍. 神经重症患者危重病情的精准量化评估[D]. 武汉: 华中科技大学, 2018.
	Zhang P. Accurate quantitative evaluation of critical condition of patients with severe neurological diseases[D]. Wuhan: Huazhong University of Science and Technology, 2018.
[5]	Ding DL, Sekar P, Moomaw CJ, et al. Venous thromboembolism in patients with spontaneous intracerebral hemorrhage:a multicenter study[J]. Neurosurgery, 2019, 84(6):E304-E310.
[6]	Ji RJ, Wang LL, Liu XY, et al. A novel risk score to predict deep vein thrombosis after spontaneous intracerebral hemorrhage[J]. Front Neurol, 2022, 13:930500.
[7]	Johnson AEW, Bulgarelli L, Shen L, et al. MIMIC-IV,a freely accessible electronic health record dataset[J]. Sci Data, 2023, 10(1):1.
[8]	International Classification of Diseases(ICD)[EB/OL]. [2025-05-09]. https://www.who.int/standards/classifications/classification-of-diseases.
[9]	Riley RD, Ensor J, Snell KIE, et al. Calculating the sample size required for developing a clinical prediction model[J]. BMJ, 2020, 368:m441.
[10]	Caprini JA. Thrombosis risk assessment as a guide to quality patient care[J]. Dis Mon, 2005, 51(2/3):70-78.
[11]	O’brien RM. A caution regarding rules of thumb for variance inflation factors[J]. Qual Quant, 2007, 41(5):673-690.
[12]	汤厅均, 张翔, 耿保伟, 等. 脑出血术后下肢深静脉血栓形成的临床特点及危险因素[J]. 血管与腔内血管外科杂志, 2023, 9(2):250-253,256.
	Tang TJ, Zhang X, Geng BW, et al. Clinical features and risk factors of lower extremity deep venous thrombosis after cerebral hemorrhage[J]. J Vasc Endovasc Surg, 2023, 9(2):250-253,256.
[13]	Melmed KR, Boehme A, Ironside N, et al. Respiratory and blood stream infections are associated with subsequent venous thromboembolism after primary intracerebral hemorrhage[J]. Neurocrit Care, 2021, 34(1):85-91.
[14]	Zhang R, Wang L, Zhang JP, et al. Peripheral T cell immune repertoire is associated with the outcomes of acute spontaneous intracerebral hemorrhage[J]. Front Neurol, 2024, 15:1371830.
[15]	Morotti A, Marini S, Jessel MJ, et al. Lymphopenia,infectious complications,and outcome in spontaneous intracerebral hemorrhage[J]. Neurocrit Care, 2017, 26(2):160-166. doi: 10.1007/s12028-016-0367-2 pmid: 28004330
[16]	Wang L. The origin and onset of thrombus disease:collapsed balancing function of immune cells and triggering factors[M]. Singapore:Springer, 2018.1-26
[17]	高浩然, 王岩, 段雨晴, 等. 神经重症患者静脉血栓栓塞的发生率、危险因素及住院结局分析[J]. 中国卒中杂志, 2021, 16(7):694-698.
	Gao HR, Wang Y, Duan YQ, et al. Incidence,risk factors and in-hospital outcome of venous thromboembolism in neurocritical patients[J]. Chin J Stroke, 2021, 16(7):694-698.
[18]	王拥军, 李子孝, 谷鸿秋, 等. 中国卒中报告2020(中文版)(1)[J]. 中国卒中杂志, 2022, 17(5):433-447.
	Wang YJ, Li ZX, Gu HQ, et al. China stroke statistics 2020(Chinese version)(1)[J]. Chin J Stroke, 2022, 17(5):433-447.
[19]	张国忠, 杨琛腾, 左敏, 等. 静脉血栓栓塞症相关危险因素研究进展[J]. 河北医科大学学报, 2015, 36(7):858-862.
	Zhang GZ, Yang CT, Zuo M, et al. Research progress on related risk factors of venous thromboembolism[J]. J Hebei Med Univ, 2015, 36(7):858-862.