文章摘要
急性脑梗死患者并发认知功能障碍的风险预测Nomogram模型构建
Construction of Nomogram model for predicting the risk of cognitive impairment in patients with acute cerebral infarction
投稿时间:2024-03-26  修订日期:2024-03-26
DOI:
中文关键词: 急性脑梗死  认知功能障碍  危险因素  列线图模型
英文关键词: Acute cerebral infarction  Cognitive dysfunction  Risk factors  Nomogram model
基金项目:2021上海市中西医结合学会社区医学与健康管理科研课题立项项目,编号2021-88
作者单位邮编
顾福一 上海交通大学医学院附属新华医院 200092
摘要点击次数: 269
全文下载次数: 0
中文摘要:
      目的:构建急性脑梗死(ACI)患者并发认知功能障碍的风险预测Nomogram模型。方法:回顾性分析2020年9月至2023年3月本院收治的279例ACI患者的临床资料,按照2:1比例将其分配为建模组(n=186)和验证组(n=93),并根据蒙特利尔认知评估量表评分将其分为认知功能障碍组和认知功能正常组。采用多因素Logistic回归分析法分析ACI患者并发认知功能障碍的危险因素,并基于此构建风险预测列线图。采用Bootstrap法对列线图模型进行验证,并绘制校准曲线评价列线图模型的校准度,绘制受试者工作特征(ROC)曲线分析列线图模型的预测效能,绘制决策曲线验证模型的临床净获益率。结果:高血压、糖尿病、大动脉粥样硬化性脑卒中、多发性脑梗死、脑白质疏松、入院时美国国立卫生研究院卒中量表(NIHSS)评分>10分、入院时高水平同型半胱氨酸(Hcy)、高水平C反应蛋白(CRP)均为ACI患者并发认知功能障碍的危险因素(P<0.05)。根据上述影响因素构建的列线图模型,运用Bootstrap法进行验证,建模组和验证组的一致性指数分别为0.833、0.821,校准曲线和理想曲线拟合度均较好;ROC曲线结果显示,建模组、验证组列线图预测ACI患者并发认知功能障碍的曲线下面积分别为0.898、0.852;决策曲线显示,建模组风险阈值概率在1%~74%时、验证组风险阈值概率在1%~80%时有较高的净获益值。结论:高血压、糖尿病、大动脉粥样硬化性脑卒中、多发性脑梗死、脑白质疏松、入院时NIHSS评分>10分、入院时高水平Hcy、CRP均为影响ACI患者并发认知功能障碍的因素,据此构建的列线图预测模型具有良好的校准度、预测效能和临床应用效果。
英文摘要:
      Objective: To construct a Nomogram model for predicting the risk of cognitive impairment in patients with acute cerebral infarction (ACI). Methods: The clinical data of 279 patients with ACI admitted to our hospital from September 2020 to March 2023 were retrospectively analyzed. They were divided into the modeling group (n=186) and the verification group (n=93) according to the 2:1 ratio, and they were divided into the cognitive dysfunction group and normal cognitive function group according to the Montreal Cognitive Assessment score. Multivariate Logistic regression analysis was used to analyze the risk factors of cognitive dysfunction in ACI patients, and a risk prediction Nomogram was constructed based on this. The Bootstrap method was used to verify the Nomogram model, and the calibration curve was drawn to evaluate the calibration of the Nomogram model. The receiver operating characteristic (ROC) curve was drawn to analyze the predictive efficacy of the Nomogram model, and the decision curve was drawn to verify the clinical net benefit rate of the model. Results: Hypertension, diabetes, large atherosclerotic stroke, multiple cerebral infarction, leukoaraiosis, National Institutes of Health Stroke Scale (NIHSS) score > 10 at admission, and high level of homocysteine (Hcy) and high level ofC-reactive protein (CRP) at admission were risk factors for cognitive dysfunction in ACI patients (P<0.05). The Nomogram model constructed based on the above influencing factors was verified by Bootstrap method, and the consistency indexes of the modeling group and the verification group were 0.833 and 0.821, respectively, and the calibration curve and ideal curve fitting were both good. The results of ROC curve showed that the area under the curve of the Nomogram of the modeling group and the validation group for predicting cognitive dysfunction in ACI patients was 0.898 and 0.852, respectively. The decision curve showed that there were a high net benefit value when the risk threshold probability of the modeling group was between 1% and 74%, and the risk threshold probability of the validation group was between 1% and 80%. Conclusion: Hypertension, diabetes, large atherosclerosis stroke, multiple cerebral infarction, leukoaraiosis, NIHSS score>10 at admission, high level of Hcy and CRP at admission are all factors that affect the cognitive dysfunction of ACI patients. The Nomogram prediction model constructed on this basis has good calibration, prediction efficiency and clinical application effect.
View Fulltext   查看/发表评论  下载PDF阅读器
关闭