女性迟发性痤疮的危险因素分析及列线图预测模型的建立  

Analysis of Risk Factors of Female Delayed Acne Vulgaris and Establishment of A Nomogram Prediction Model

作　　者：曹洋 李婧 CAO Yang;LI Jing(Acupuncture-moxibustion and Tuina Ward(Third Rehabilitation Department),Tangshan 063000,Hebei,China;Department of Dermatology,Tangshan Traditional Chinese Medicine Hospital,Tangshan 063000,Hebei,China)

机构地区：[1]唐山市中医医院针灸推拿病区(康复三科),河北唐山063000 [2]唐山市中医医院皮肤科,河北唐山063000

出　　处：《中国美容医学》2024年第7期1-6,共6页Chinese Journal of Aesthetic Medicine

基　　金：河北省中医药管理局科研计划项目(编号:2020382)。

摘　　要：目的:分析女性迟发性痤疮(Female delayed acne vulgaris,FDAV)的危险因素,构建FDAV的列线图预测模型。方法:选取2020年5月-2022年5月就诊于唐山市中医医院皮肤科门诊的FDAV患者200例与200例健康志愿者,参考文献自制问卷调查表实施问卷调查,并用Logistic回归分析筛选影响FDAV发生的危险因素;采用R软件构建预测FDAV风险的列线图模型,采用Bootstrap法进行内部验证,采用验证集进行外部验证,采用ROC曲线、校准曲线评价列线图模型的预测效能。结果:Logistic回归分析结果显示,睡眠时间<8 h[95%CI(2.701~8.034),P<0.001]、使用电脑时间≥3 h/d[95%CI(2.836~8.733),P<0.001]、饮酒[95%CI(1.354~5.602),P=0.005]、有家族史[95%CI(1.534~5.443),P=0.001]是FDAV的独立危险因素。ROC曲线下面积0.785,95%CI(0.702~0.868)。校准曲线斜率接近1,且H-L拟合优度检验χ^(2)=6.141,P=0.189。外部验证结果显示:校准曲线斜率接近1,ROC曲线下面积为0.872,95%CI(0.817~0.927)。结论:FDAV与睡眠时间<8 h、使用电脑时间≥3 h/d、饮酒、有家族史有关,基于以上4项独立危险因素构建的列线图模型在预测FDAV发生方面预测效能尚可。Objective To analyze the risk factors of female delayed acne vulgaris(FDAV),and to construct a nomogram prediction model of FDAV.Methods From May 2020 to May 2022,200 FDAV patients and 200 healthy volunteers who visited the dermatology clinic of Tangshan Traditional Chinese Medicine Hospital were selected,surveys were implemented through self-made questionnaires according to the reference literature,Logistic regression analysis was applied to screen the risk factors affecting the occurrence of FDAV;R software was used to build a nomogram model for predicting the risk of FDAV,and Bootstrap method was used for internal verification,verification set was used for external verification,ROC curve and calibration curve were carried out to evaluate the prediction efficiency of nomogram model.Results Logistic regression analysis showed that sleep time of<8 h[95%CI(2.701-8.034),P<0.001],computer time of≥3 h/d[95%CI(2.836-8.733),P<0.001],alcohol consumption[95%CI(1.354-5.602),P=0.005]and family history[95%CI(1.534-5.443),P=0.001]were independent risk factors for FDAV.The area under the ROC curve was 0.785[95%CI(0.702-0.868)].The slope of the calibration curve was close to 1,and the H-L goodness of fit test showedχ^(2)=6.141,P=0.189.The external verification results showed that the slope of the calibration curve was close to 1,and the area under the ROC curve was 0.872[95%CI(0.817-0.927)].Conclusion FDAV is related to sleep time of<8 h,computer use time of≥3 h/d,alcohol consumption,and family history.The nomogram prediction model constructed based on the above four independent risk factors has good predictive performance in predicting the occurrence of FDAV.

关 键 词：女性迟发性痤疮 危险因素 列线图预测模型 

分 类 号：R751[医药卫生—皮肤病学与性病学]