实用老年医学

实用老年医学 ›› 2024, Vol. 38 ›› Issue (12): 1246-1249.doi: 10.3969/j.issn.1003-9198.2024.12.013

• 临床研究 • 上一篇    下一篇

老年人阿尔茨海默病发生风险的列线图预测模型构建

王冰升, 曹世华, 程灵玲, 石爱丽, 史颜凯, 姚佳妮, 娄夏菁, 齐文豪, 董超群, 朱晓红, 汪彬, 何丹妮, 陈彦菲   

  1. 311121 浙江省杭州市,杭州师范大学护理学院(王冰升,曹世华,史颜凯,姚佳妮,娄夏菁,齐文豪,董超群,朱晓红,汪彬,何丹妮,陈彦菲);
    310014 浙江省杭州市,浙江省人民医院急诊科(程灵玲,石爱丽)
  • 收稿日期:2024-01-10 出版日期:2024-12-20 发布日期:2024-12-19
  • 通讯作者: 曹世华,Email:csh@hznu.edu.cn

A nomogram prediction model for risk of Alzheimer’s disease among the elderly

WANG Bingsheng, CAO Shihua, CHENG Lingling, SHI Aili, SHI Yankai, YAO Jiani, LOU Xiajing, QI Wenhao, DONG Chaoqun, ZHU Xiaohong, WANG Bing, HE Danni, CHEN Yanfei   

  1. School of Nursing, Hanghzou Normal University, Hangzhou 311121, China(WANG Bingsheng, CAO Shihua, SHI Yankai, YAO Jiani, LOU Xiajing, QI Wenhao, DONG Chaoqun, ZHU Xiaohong, WANG Bing, HE Danni, CHEN Yanfei);
    Department of Emergency, Zhejiang People’s Hospital, Hangzhou 310014, China(CHENG Lingling, SHI Aili)
  • Received:2024-01-10 Online:2024-12-20 Published:2024-12-19
  • Contact: CAO Shihua, Email: csh@hznu.edu.cn

PDF (PC)

312

摘要： 目的 探讨老年人发生AD的危险因素并构建风险列线图预测模型。方法 从美国公共数据库阿尔茨海默病协调中心(NACC)提取2968 例参试者资料,包括社会人口学信息、生活方式、心理健康、睡眠模式、疾病史和药物使用情况等。参试者以7∶3比例被随机划分为建模组和内部验证组。在建模阶段,采用多因素Logistic回归模型筛选出老年人发生AD的独立预测因素,并基于这些变量构建列线图。在模型的内部验证过程中,采用ROC曲线下面积和校准曲线来评估模型的区分度和校准度;采用临床影响曲线评估模型的临床应用价值。结果 多因素Logistic回归模型结果显示,性别、受教育年限、收缩压、抑郁症、焦虑症、快速眼动睡眠障碍、年龄、创伤性脑损伤史及服用药物数量与老年人AD密切相关 (P<0.05)。基于这些危险因素建立风险列线图预测模型,ROC曲线下面积和校准曲线显示模型的区分度和准确度良好;临床影响曲线分析显示,模型在较大的阈值内具有一定临床实用性。结论 本研究构建的老年人AD列线图模型预测效果较好,可为早期识别AD高风险人群提供参考。

关键词: 阿尔茨海默病, 列线图, 预测, 影响因素, 老年人

Abstract: Objective To investigate the risk factors of Alzheimer’s disease (AD) in the elderly and to develop a nomogram model for risk prediction. Methods The data of 2968 elderly cases were extracted from the National Alzheimer’s Coordinating Center (NACC), a public database in USA, including sociodemographic information, lifestyle, mental health, sleep patterns, disease history and medication usage. The subjects were randomly divided into a modeling group and an internal validation group at a ratio of 7∶3. Multivariable Logistic regression model was employed to identify the risk factors of AD in the elderly, and a nomogram prediction model was constructed based on these variables. The model’s discriminative ability and calibration were assessed by the area under the receiver operating characteristic (ROC) curve and calibration plots. The clinical value of the model was evaluated with clinical impact curves. Results The multivariable Logistic regression analysis showed that gender, educational level, systolic blood pressure, depression, anxiety, rapid eye movement sleep behavior disorder, age, history of traumatic brain injury and the number of medications were influencing factors of AD in the elderly (P<0.05). A risk prediction nomogram was established based on these nine factors. The area under the ROC curve and calibration plots showed good discriminative ability and accuracy of the model. The clinical impact curves demonstrated that the model had practical clinical utility within a substantial range of threshold values. Conclusions The nomogram prediction model for AD constructed in this study demonstrates good predictive performance and can provide a reference for the early identification of the elderly with high risk of AD.

Key words: Alzheimer’s disease, nomogram, prediction, influencing factor, aged

中图分类号: