摘要
探究影响脑梗死患者溶栓预后是否良好的影响因素并结合数据建立预测模型,为今后临床治疗的发展提供理论依据和支持.收集哈尔滨医科大学附属第一医院脑梗死患者病例并筛选数据指标建立单因素分析模型,对计量数据和计数数据分别进行检验,得到初步影响因素并将P<0.05的指标纳入机器学习预测模型建立中.结果为预后不良组与预后良好组在年龄(t=-3.050,P=0.003)、溶栓后血糖值(z=3.490,P<<0.01)、既往高血压(χ^(2)=6.853,P=0.009)等因素中存在显著性差异.根据Logistic回归、决策树、随机森林以及朴素贝叶斯算法构建的四种机器学习预测模型的准确率分别为79%、79%、75%、73%;曲线下面积分别为0.85、0.81、0.78、0.81.所构建的四种预测模型均具备较好的脑梗死患者预后是否良好的预测能力,具有用于临床研究的潜在价值.
This paper investigates the influencing factors affecting the prognosis of thrombolytic therapy in patients with cerebral infarction and combine the data to establish a prediction model to provide theoretical basis and support the development of future clinical treatment.Collecting cases of cerebral infarction patients from the First Hospital of Harbin Medical University and screening data indicators to establish a univariate analysis model,and the measurement data and count data were tested separately to obtain preliminary infuencing factors and to include the indicators with in the establishment of the machine learning prediction model.The results showed significant differences between the poor prognosis group and the good prognosis group in age(t=-3.050,P=0.003),post-thrombolytic glucose value(z=3.490,P≤0.01),and previous hypertension(χ^(2)=6.853,P=0.009).The accuracy of the four machine learning prediction models constructed based on logistic regression,decision tree,random forest,and plain Bayesian algorithms were 79%,79%,75%,and 73%,respectively;the area under the curve was 0.85,0.81,0.78,and 0.81,respectively.The four constructed prediction models all had good prediction ability of whether the prognosis of patients with cerebral infarction was good or not,and had potential value for clinical research.
作者
魏宏博
马帅男
常宏业
周影
WEI Hong-bo;MA Shuai-nan;CHANG Hong-ye;ZHOU Ying(School of Mathematical Sciences,Heilongjiang University,Harbin 150080,China;The First Hospital of Harbin Medical University,Harbin 150000,China;Xi'an Central Hospital,Xi'an Jiaotong University,Xi'an 710000,China)
出处
《数学的实践与认识》
北大核心
2024年第2期136-142,共7页
Mathematics in Practice and Theory
基金
国家自然科学基金(12071114)
黑龙江大学研究生创新科研项目(YJSCX2022-251HLJU)
哈医大一院科研创新基金-留学归国基金项目(2021L04)。
关键词
机器学习预测
脑梗死疾病
影响因素
临床研究
machine learning prediction
cerebral infarction disease
infuencing factors
clinical research
