基于GCS评分的Nomogram图预测急性脑出血后卒中相关性肺炎的发生风险

Nomogram based on GCS score predicted the risk of stroke associated pneumonia after acute cerebral hemorrhage

目的 通过构建Nomogram预测模型,探讨急性脑出血后发生卒中相关性肺炎(SAP)的危险因素。方法 回顾性分析2018-01—2022-12平顶山学院第一附属医院神经外科、重症医学科及神经重症的1 050例急性脑出血患者的临床资料,先根据GCS评分进行感染率的分层分析,然后运用组间差异性比较及多因素Logistic回归分析筛选SAP的独立危险因素,应用R语言构建Nomogram预测模型,并对构建的模型进行评价。结果 急性脑出血患者中SAP发生率为35.9%,其中GCS评分3~8分患者为77.21%,GCS评分9~12分患者为30.81%,GCS评分13~15分患者为6.50%,各组间感染率差异有统计学意义(P<0.05)。多因素Logistic回归显示,年龄、GCS评分、入院时随机血糖、淋巴细胞绝对值及手术治疗均为SAP独立危险因素,以这5个危险因素构建的Nomogram预测模型可帮助临床医师预测急性脑出血后SAP发生风险,具有较高的准确性和临床适用性。结论 基于GCS评分构建的Nomogram预测模型能够在疾病早期阶段准确高效地对急性脑出血患者发生SAP的风险进行分层,识别出易发生SAP患者的高风险人群,从而采取有针对性的干预措施。

Objective To investigate the risk factors for stroke associated pneumonia(SAP)after acute cerebral hemorrhage by constructing a nomogram prediction model.Methods A retrospective analysis was conducted on the clinical data of 1050 patients with acute cerebral hemorrhage from January 2018 to December 2022 in the Department of Neurosurgery,Department of Critical Care Medicine and Department of Neurosurgical Intensive Care Unit,the First Affiliated Hospital of Pingdingshan University.Firstly,a stratified analysis of infection was conducted based on GCS scores.Then,the comparative analysis of the differences between groups and multivariate Logistic regression analysis were used to screen for independent risk factors for SAP.The Nomogram prediction model was constructed using R language,and the constructed model was evaluated. Results The incidence of SAP in patients with acute cerebral hemorrhage was 35.9%,which in patients with GCS score of 3-8 points was 77.21%,in patients with GCS score of 9-12 points was 30.81%,and in patients with GCS score of 13-15 points was 6.50%.There was a statistically significant difference in infection rates among the groups(P<0.05).Multivariate Logistic regression showed that age,GCS score,random blood glucose at admission,absolute lymphocyte count and surgical treatment were all independent risk factors for SAP.The Nomogram prediction model constructed using these five risk factors could help clinical physicians predict the risk of SAP after acute cerebral hemorrhage with high accuracy and clinical applicability.Conclusion The Nomogram prediction model based on GCS score can accurately and efficiently stratify the risk of SAP in patients with acute cerebral hemorrhage in the early stage of the disease,to identify high-risk populations prone to SAP and enable medical staff to take targeted intervention measures.