临床护士围绝经期综合征风险预测模型的构建及验证

Construction and validation of a risk prediction model for perimenopausal syndrome among clinical nurses

目的:分析临床护士发生围绝经期综合征的影响因素,构建风险预测模型,为早期预测临床护士围绝经期综合征的发生风险提供工具。方法:采用分层随机抽样方法,于2020年8月—12月抽取重庆市一级医院、二级医院、三级医院共933名临床护士,作为研究对象,通过Logistic回归模型筛选围绝经期综合征的影响因素,运用R软件建立列线图模型并验证。结果:临床护士围绝经期综合征发生率为70.95%。Logistic回归模型显示,年龄、是否患有慢性病、每周运动情况、绝经、家庭功能、基本保障情况、充足的人力是围绝经期综合征的独立影响因素。十折交叉验证显示,训练集和验证集的预测准确率分别为69.04%和68.65%,模型较稳定;列线图模型预测围绝经期综合征的C⁃index为0.712,区分度较好。结论:临床护士围绝经期综合征风险预测模型能较好地预测临床护士围绝经期综合征的发生风险,为早期预防提供较为准确的决策依据。

Objective:To analyze the influencing factors of the perimenopausal syndrome in clinical nurses,construct a risk prediction model,and provide a tool for early prediction of the risk of the perimenopausal syndrome in clinical nurses.Methods:A total of 933 clinical nurses from primary,secondary,and tertiary hospitals in Chongqing were selected from August to December 2020 as the research subjects by using the stratified random sampling method.The Logistic regression model was used to screen out the independent influencing factors of the perimenopausal syndrome;R software was used to establish a histographic model and validate it.Results:The incidence of perimenopausal syndrome among clinical nurses was 70.95%.The Logistic regression model showed that age,chronic disease,weekly exercise,menopause,family function,basic security,and sufficient manpower were independent influencing factors of the perimenopausal syndrome.According to the 10⁃fold cross⁃validation,the prediction accuracy of the training set and validation set were 69.04%and 68.65%,respectively,and the model was relatively stable.The C⁃index of nomogram model in predicting perimenopausal syndrome was 0.712,which had good discrimination.Conclusions:The clinical nurses'perimenopausal syndrome risk prediction model could better predict the risk of clinical nurses'perimenopausal syndrome and provide a more accurate decision⁃making basis for early prevention.