脑卒中患者误吸风险预测模型的构建与初步验证

doi:10.3761/j.issn.2096-7446.2026.08.003

摘要/Abstract

摘要：

目的构建脑卒中患者误吸风险预测模型，筛选最优模型，为误吸风险患者提供预测工具。方法系统回顾脑卒中患者误吸相关文献提炼风险因子，结合专家函询形成风险因素调查问卷；收集浙江省某三级甲等医院515例脑卒中患者数据，经单因素、多因素分析确定核心因子；采用Logistic回归、极端梯度提升、随机森林、支持向量机、人工神经网络构建模型，通过曲线下面积、Brier分数、准确度等指标及10折交叉验证评价模型。结果确定年龄、格拉斯哥昏迷评分、进食体位等14项误吸独立风险因子；极端梯度提升模型综合性能最优，测试集曲线下面积=0.8071、Brier分数=0.123、F1=0.5994，10折交叉验证后稳定性良好（曲线下面积=0.792）；核心预测因子为进食体位（半坐卧位）、年龄、美国国立卫生院卒中量表评分。结论极端梯度提升模型可精准识别脑卒中误吸高危患者，核心因子为临床干预提供明确靶点，未来需多中心外部验证提升泛化能力。

关键词: 脑卒中, 误吸, 风险预测模型, 机器学习, Logistic回归, 极端梯度提升算法, 护理

Abstract:

Objective To construct a prediction model for aspiration risk in stroke patients，identify the optimal model，and provide a predictive tool for patients at risk of aspiration. Methods A systematic review of literature on aspiration in stroke patients was conducted to identify risk factors，which were then incorporated into a risk factor questionnaire developed with expert consultation. Data from 515 stroke patients at a tertiary hospital in Zhejiang Province were collected. Core factors were determined through univariable and multivariable analyses. Models were constructed using logistic regression，extreme gradient boosting，random forest，support vector machine，and artificial neural network. Model performance was evaluated using area under the curve，Brier score，accuracy，and 10-fold cross-validation. Results Fourteen independent aspiration risk factors were identified，including age，Glasgow Coma Scale score，and feeding position. The extreme gradient boosting model demonstrated optimal overall performance，AUC=0.8071，Brier score=0.123，F1=0.5994 in test set，with good stability after 10-fold cross-validation（AUC=0.792）. Core predictors included feeding position（semi-recumbent），age，and NIHSS score. Conclusion Extreme gradient boosting accurately identifies stroke patients at high risk for aspiration. Core factors provide clear targets for clinical intervention. Future multicenter external validation is needed to enhance generalization capability.

Key words: Stroke, Aspiration, Risk Prediction Model, Machine Learning, Logistic Regression, Extreme Gradient Boosting Algorithm, Nursing Care

冯盼铮, 柳春波, 张波, 刘雪兰. 脑卒中患者误吸风险预测模型的构建与初步验证[J]. 中华急危重症护理杂志, 2026, 7(8): 916-922.

FENG Panzheng, LIU Chunbo, ZHANG Bo, LIU Xuelan. Development and preliminary validation of a prediction model for aspiration risk in stroke patients[J]. Chinese Journal of Emergency and Critical Care Nursing, 2026, 7(8): 916-922.

图/表 7

表1

表2

表3

表4

图1

图2

图3

参考文献 18

[1]	王陇德, 吉训明, 康德智, 等. 《中国卒中中心报告2020》概要[J]. 中国脑血管病杂志, 2021, 18(11):737-743.
	Wang LD, Ji XM, Kang DZ, et al. Summary of China stroke center report 2020[J]. Chin J Cerebrovasc Dis, 2021, 18(11):737-743.
[2]	徐金娟, 吴丽萍. 卒中误吸风险分析及预测模型的构建与验证[J]. 重庆医学, 2023, 52(23):3638-3642,3647.
	Xu JJ, Wu LP. Construction and validation of stroke with aspiration risk analysis and prediction model[J]. Chongqing Med, 2023, 52(23):3638-3642,3647.
[3]	Oliveira AR, Costa AG, Morais, Huana Carolina Candido, et al. Clinical factors predicting risk for aspiration and respiratory aspiration among patients with Stroke[J]. Revista Latino-Americana de Enfermagem, 2015, 23(2),2545.
[4]	2021年版中国脑卒中诊治指南[J]. 中华神经科杂志, 2021, 54(9):893-945.
	Chinese guidelines for the diagnosis and treatment of stroke,2021 edition[J]. Chin J Neurol, 2021, 54(9):893-945.
[5]	董晓曦. 早期摄食训练监测指导下在缺血性脑卒中伴吞咽障碍患者康复护理中的应用研究[D]. 长春: 长春中医药大学, 2023.
	Dong XX. A Study on the application of early feeding training monitoring guidance in rehabilitation care for patients with ischemic stroke and dysphagia[D]. Changchun: Changchun University of Chinese Medicine, 2023.
[6]	Park D, Son SI, Kim MS, et al. Machine learning predictive model for aspiration screening in hospitalized patients with acute stroke[J]. Sci Rep, 2023, 13(1):7835. doi: 10.1038/s41598-023-34999-8 pmid: 37188793
[7]	于跃. 基于机器学习的急性缺血性脑卒中后癫痫预测模型构建与评价[D]. 青岛: 青岛大学, 2023.
	Yu Y. Construction and evaluation of epilepsy prediction model after acute ischemic stroke based on machine learning[D]. Qingdao: Qingdao University, 2023.
[8]	Efthimiou O, Seo M, Chalkou K, et al. Developing clinical prediction models:a step-by-step guide[J]. BMJ, 2024, 386:e078276. doi: 10.1136/bmj-2023-078276
[9]	王爱华. ICU鼻饲患者误吸预防及管理的循证实践[D]. 成都: 成都医学院, 2024.
	Wang AH. Evidence-based practice on prevention and management of aspiration of nasal feeding patients in ICU[D]. Chengdu: Chengdu Medical College, 2024.
[10]	肖艳华. 基于机器学习的气管切开患者意外脱管预测模型的构建及验证[D]. 赣州: 赣南医科大学, 2025.
	Xiao YH. Construction and verification of predictive model for unexpected detaching of tracheostomy patients based on machine learning[D]. Ganzhou: Gannan Medical University, 2025.
[11]	洪显钗, 舒美春, 林碎丽, 等. 基于3种机器学习算法构建脑卒中患者隐性误吸风险预测模型[J]. 护理与康复, 2025, 24(6):1-6.
	Hong XC, Shu MC, Lin SL, et al. Construction of a risk prediction model for silent aspiration in stroke patients based on three machine learning algorithms[J]. J Nurs Rehabil, 2025, 24(6):1-6.
[12]	GS Collins, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis(TRIPOD):the TRIPOD statement[J]. BMJ, 2015, 350:7594-7601.
[13]	Garavelli F, Ghelfi AM, Kilstein JG. Usefulness of NIHSS score as a predictor of non-neurological in-hospital complications in stroke[J]. Med Clin, 2021, 157(9):434-437. doi: 10.1016/j.medcli.2020.07.034
[14]	曹新志, 沈君姝, 王杰. 基于XGBoost算法的免疫性甲状腺功能异常预测模型构建[J]. 中国卫生信息管理杂志, 2023, 20(5):833-837.
	Cao XZ, Shen JS, Wang J. Construction of immune thyroid dysfunction prediction model based on XGBoost algorithm[J]. Chin J Health Inform Manag, 2023, 20(5):833-837.
[15]	Schartz DA, Ellens NR, Kohli GS, et al. A meta-analysis of combined aspiration catheter and stent retriever versus stent retriever alone for large-vessel occlusion ischemic stroke[J]. AJNR Am J Neuroradiol, 2022, 43(4):568-574. doi: 10.3174/ajnr.A7459
[16]	田雅琦, 邱立欣, 谷媛媛, 等. 脑卒中吞咽困难病人吞咽造影特点及其对误吸的预测价值研究[J]. 中西医结合心脑血管病杂志, 2023, 21(23):4421-4428.
	Tian YQ, Qiu LX, Gu YY, et al. Study on the characteristics of swallowing radiography in patients with dysphagia after stroke and its predictive value for aspiration[J]. Chin J Integr Med Cardio Cerebrovasc Dis, 2023, 21(23):4421-4428.
[17]	李孝红, 张婷, 杨欣, 等. 脑卒中吞咽障碍患者发生误吸的危险因素研究进展[J]. 西北国防医学杂志, 2021, 42(5):397-400.
	Li XH, Zhang T, Yang X, et al. Research progress of risk factors for aspiration in stroke patients with dysphagia[J]. Med J Natl Defending Forces Northwest China, 2021, 42(5):397-400.
[18]	林美凤, 钟丽华, 刘新娣, 等. 实施个性化评估联合全面护理模式对脑卒中吞咽障碍患者误吸预防的价值研究[J]. 基层医学论坛, 2025, 29(22):145-148,156.
	Lin MF, Zhong LH, Liu XD, et al. Study on the value of individualized evaluation combined with comprehensive nursing mode in preventing aspiration of patients with dysphagia after stroke[J]. Med Forum, 2025, 29(22):145-148,156.