基于机器学习的缺血性卒中功能预后预测模型研究

doi:10.3969/j.issn.1673-5765.2021.09.005

摘要/Abstract

摘要： 目的建立基于机器学习的缺血性卒中功能预后预测模型，为患者分层管理提供科学依据。方法选取中国国家卒中登记Ⅱ（China National Stoke Registry Ⅱ，CNSRⅡ）数据库中发病7 d内的缺血性卒中患者为研究对象。logistic回归分析采用逐步回归方法筛选候选预测因子，机器学习采用Boruta 算法筛选特征。使用logistic回归和CatBoost、XGBoost、LightGBM三种机器学习方法构建功能预后预测模型，并比较这四种预测模型对缺血性卒中患者3个月功能预后（mRS＞2分为预后不良）的预测价值。结果本研究共纳入14 885例缺血性卒中患者，平均年龄64.34±11.71岁，其中男性占63.96% （9521/14 885）。患者按8∶2随机分为训练集（11 908例）和测试集（2977例），两组3个月功能预后不良率分别为17.36%和17.06%（P =0.7045）。多因素分析结果显示年龄（OR 1.05，95%CI 1.04～1.05， P <0.0001）、男性（OR 0.77，95%CI 0.69～0.86，P <0.0001）、糖尿病（OR 1.16，95%CI 1.00～1.35， P = 0.0497）、脑血管病史（O R 1.53，95%C I 1.37～1.70，P <0.0001）、合并肺炎（O R 2.4 5， 95%CI 2.03～2.95，P <0.0001）、入院时NIHSS评分（OR 1.14，95%CI 1.13～1.15，P <0.0001）、发病前 mRS（OR 3.11，95%CI 2.67～3.63，P <0.0001）、LDL-C（OR 1.07，95%CI 1.02～1.12，P =0.0057）、空腹血糖（OR 1.03，95%CI 1.01～1.06，P =0.0072）和白细胞计数（OR 1.07，95%CI 1.05～1.09，P <0.0001）可作为预测模型的预测因子。logistic回归、CatBoost、XGBoost、LightGBM预测模型预测缺血性卒中功能预后的AUC分别为0.815（0.801～0.829）、0.828（0.814～0.841）、0.826（0.812～0.839）和0.822 （0.808～0.836）。CatBoost（P =0.0023）和XGBoost（P =0.0182）建立的预测模型预测效果均优于传统 logistic回归模型。结论基于机器学习算法建立的缺血性卒中功能预后预测模型具有较高的预测价值。

文章导读： 本研究通过涵盖219家中心的CNSRⅡ数据库的大样本数据，检验了传统多因素logistic回归分析方法和基于
机器学习建立的缺血性卒中3个月预后模型的预测效能，结果提示通过CatBoost和XGBoost方法建立的预测模型预
测效果优于传统logistic回归模型。

关键词: 缺血性卒中; 预后; 预测模型; 机器学习

Abstract: Objective To establish machine learning-based models for prediction of functional outcome of ischemic stroke, and to provide scientific basis for stratified management of patients. Methods The patients with ischemic stroke within 7 days of onset in the China National Stroke Registry Ⅱ (CNSR Ⅱ) study were selected as the analyzed subjects. Predictors were screened by stepwise regression in logistic regression while by Boruta algorithm in machine learning. Then four outcome prediction models were constructed by three machine learning methods (CatBoost, XGBoost and LightGBM) and logistic regression, and the predictive value of the four models were

compared.

Results A total of 14 885 patients of ischemic stroke were included, with a mean age of 64.34±11.71 years old and 9521 males (63.96%). The patients were randomly divided into training set (n =11 908) and test set (n =2977) at a ratio of 8:2. The rate of poor functional outcome of the two sets were 17.36% and 17.06% (P =0.7045), respectively. Multivariate logistic regression analysis showed that predictors of the model were aged (OR 1.05, 95%CI 1.04-1.05, P <0.0001), male (OR 0.77, 95%CI 0.69-0.86, P <0.0001), history of diabetes (OR 1.16, 95%CI 1.00-1.35, P =0.0497) or cerebrovascular disease (OR 1.53, 95%CI 1.37-1.70, P <0.0001), complicated with pneumonia (OR 2.45, 95%CI 2.03-2.95, P <0.0001), NIHSS score at admission (OR 1.14, 95%CI 1.13-1.15, P <0.0001), premorbid mRS score (OR 3.11, 95%CI 2.67-3.63, P <0.0001), LDL-C (OR 1.07, 95%CI 1.02-1.12, P =0.0057), fasting blood glucose (OR 1.03, 95%CI 1.01-1.06, P =0.0072) and white blood cell count (OR 1.07, 95%CI 1.05-1.09, P <0.0001). The area under the ROC curve of CatBoost, XGBoost and LightGBM models, which was used to predict the functional outcome of ischemic stroke, were 0.828 (0.814- 0.841), 0.826 (0.812-0.839) and 0.822 (0.808-0.836), respectively, while that of logistic learning regression model was 0.815 (0.801-0.829). CatBoost (P =0.0023) and XGBoost (P =0.0182) models had better predictive function than logistic regression model. Conclusions The machine learning-based predictive models had high predictive value for functional outcome of ischemic stroke.

Key words: Ischemic stroke; Outcome; Predictive model; Machine learning

上官艺, 王孟, 王春娟, 谷鸿秋, 赵性泉, 王伊龙, 王拥军, 李子孝. 基于机器学习的缺血性卒中功能预后预测模型研究[J]. 中国卒中杂志, 2021, 16(09): 895-900.

SHANGGUAN Yi, WANG Meng, WANG Chun-Juan, GU Hong-Qiu, ZHAO Xing-Quan, WANG Yi-Long, WANG Yong-Jun, LI Zi-Xiao. Machine Learning-based Models for Prediction of Functional Outcome of Ischemic Stroke[J]. Chinese Journal of Stroke, 2021, 16(09): 895-900.

参考文献

[1] 王拥军，李子孝，谷鸿秋，等. 中国卒中报告2019（中
文版）（1）[J]. 中国卒中杂志，2020，15（10）：1037-
1043.
[2] WANG W Z，JIANG B，SUN H X，et al. Prevalence，
incidence，and mortality of stroke in China：results
from a nationwide population-based survey of
480 687 adults[J]. Circulation，2017，135（8）：759-
771.
[3] LLOYD-JONES D，ADAMS R，CARNETHON M，
et al. Heart disease and stroke statistics-2009 update：
a report from the American Heart Association
Statistics Committee and Stroke Statistics
Subcommittee[J]. Circulation，2009，119（3）：480-
486.
[4] FLINT A C，XIANG B，GUPTA R，et al. THRIVE
score predicts outcomes with a third-generation
endovascular stroke treatment device in the
TREVO-2 trial[J]. Stroke，2013，44（12）：3370-3375.
[5] ALI RAZA S，XIANG B，JOVIN T G，et al.
Pittsburgh response to endovascular therapy score as
a pre-treatment prognostic tool：external validation
in TREVO2[J]. Int J Stroke，2017，12（5）：494-501.
[6] ZHU Z B，GUO D S，ZHONG C K，et al. Serum
Dkk-1（Dickkopf-1）is a potential biomarker in the
prediction of clinical outcomes among patients with
acute ischemic stroke[J]. Arterioscler Thromb Vasc
Biol，2019，39（2）：285-293.
[7] BIVARD A，LEVI C，LIN L T，et al. Validating
a predictive model of acute advanced imaging
biomarkers in ischemic stroke[J]. Stroke，2017，48
（3）：645-650.
[8] BAIRD A E，DAMBROSIA J，JANKET S J，et al.
A three-item scale for the early prediction of stroke
recovery[J]. Lancet，2001，357（9274）：2095-2099.
[9] 覃伟，姜勇，刘宝花. 机器学习模型在急性缺血性卒
中并发症及预后预测中的研究进展[J]. 中国卒中杂
志，2020，15（6）：611-615.
[10] 史斌，王建立. 人工智能对肝癌患者预后预测的研
究进展[J]. 解放军医学院学报，2020，41（9）：922-
925，953.
[11] WHO Task Force on Stroke and Other
Cerebrovascular Disorders. Stroke-1989.
Recommendations on stroke prevention，diagnosis，
and therapy. Report of the WHO Task Force on
Stroke and other Cerebrovascular Disorders[J].
Stroke，1989，20（10）：1407-1431.
[12] KURSA M B，RUDNICKI W R. Feature selection
with the Boruta package[J]. J Stat Softw，2010，36
（11）：1-13.
[13] COUNSELL C，DENNIS M，MCDOWALL M，et al.
Predicting outcome after acute and subacute stroke：
development and validation of new prognostic
models[J]. Stroke，2002，33（4）：1041-1047.
[14] NTAIOS G，FAOUZI M，FERRARI J，et al. An
integer-based score to predict functional outcome
in acute ischemic stroke：the ASTRAL score[J].
Neurology，2012，78（24）：1916-1922.
[15] KOHAVIA R，JOHN G H. Wrappers for feature
subset selection[J]. Artificial Intelligence，1997，97
（1/2）：273-324.
[16] ALAKA S A，MENON B K，BROBBEY A，et al.
Functional outcome prediction in ischemic stroke：a
comparison of machine learning algorithms and
regression models[J/OL]. Frontiers in Neurology，
2020，11：889[2021-04-01]. https：//doi.org/10.3389/
fneur.2020.00889.
[17] MONTEIRO M，FONSECA A C，FREITAS A T，et
al. Using machine learning to improve the prediction
of functional outcome in ischemic stroke patients[J].
IEEE/ACM Trans Comput Biol Bioinform，2018，15
（6）：1953-1959.