Objective To determine the factors influencing insomnia and construct early insomnia warning tools for rescuers to informbest practices for early screening and intervention.Methods Cluster sampling was used to conduct...Objective To determine the factors influencing insomnia and construct early insomnia warning tools for rescuers to informbest practices for early screening and intervention.Methods Cluster sampling was used to conduct a cross-sectional survey of 1,133 rescuers from one unit in Beijing,China.Logistic regression modeling and R software were used to analyze insomniarelated factors and construct a PRISM model,respectively.Results The positive rate of insomnia among rescuers was 2.74%.Accounting for participants’age,education,systolic pressure,smoking,per capita family monthly income,psychological resilience,and cognitive emotion regulation,logistic regression analysis revealed that,compared with families with an average monthly income less than 3,000 yuan,the odds ratio(OR)values and the[95%confidence interval(CI)]for participants of the following categories were as follows:average monthly family income greater than 5,000 yuan:2.998(1.307–6.879),smoking:4.124(1.954–8.706),and psychological resilience:0.960(0.933–0.988).The ROC curve area of the PRISM model(AUC)=0.7650,specificity=0.7169,and sensitivity=0.7419.Conclusion Insomnia was related to the participants’per capita family monthly income,smoking habits,and psychological resilience on rescue workers.The PRISM model’s good diagnostic value advises its use to screen rescuer early sleep quality.Further,advisable interventions to optimize sleep quality and battle effectiveness include psychological resilience training and smoking cessation.展开更多
目的通过机器学习算法对失眠患者的多导睡眠监测(polysomnography,PSG)数据进行挖掘,建立失眠患者抑郁症的诊断模型,为失眠患者的抑郁症诊断提供科学依据。方法选择2023年1~12月在内蒙古自治区精神卫生中心进行PSG的失眠住院与门诊患者...目的通过机器学习算法对失眠患者的多导睡眠监测(polysomnography,PSG)数据进行挖掘,建立失眠患者抑郁症的诊断模型,为失眠患者的抑郁症诊断提供科学依据。方法选择2023年1~12月在内蒙古自治区精神卫生中心进行PSG的失眠住院与门诊患者共2162例,抑郁症根据《国际疾病与相关健康问题统计分类第10版》(International Statistical Classification of Diseases and Related Health Problems,10th version,ICD-10)进行诊断。收集患者的一般情况与PSG资料,分别基于logistic回归、支持向量机、随机森林、自适应提升、极限提升树、朴素贝叶斯等6种算法构建失眠患者抑郁症的诊断模型。结果纳入的失眠患者中,40.1%(868例)的患者合并抑郁症。6种模型中,logistic回归和随机森林模型的受试者操作特征曲线(receiver operating characteristic curve,ROC curve)的曲线下面积(area under the curve,AUC)值最高,分别为0.825和0.823,综合分类性能更优。结论Logistic回归和随机森林模型对失眠患者中的抑郁症人群有良好的诊断效能。展开更多
介绍目前失眠认知研究中的5种主要模型,包括Spielm an失眠3-P模型、M orin失眠微观分析模型、Lundh和B rom an的睡眠干扰过程和睡眠解释过程相互作用的整合模型、Harvey的失眠维持认知模型及Espie等的注意-意向-努力路径。这些模型从不...介绍目前失眠认知研究中的5种主要模型,包括Spielm an失眠3-P模型、M orin失眠微观分析模型、Lundh和B rom an的睡眠干扰过程和睡眠解释过程相互作用的整合模型、Harvey的失眠维持认知模型及Espie等的注意-意向-努力路径。这些模型从不同角度审视失眠,并针对性地提出了失眠的临床治疗建议。未来需要有一个更加综合的模型整合失眠的形成、发展和持续过程,这也要求进行更多的纵向研究。展开更多
基金Beijing Science and Technology"Capital Characteristics"Project[Z181100001718007]Translational Medicine Project of PLA General Hospital[2017TM-023]+1 种基金Expansion of Military Medical and Health Achievements[17WKS25]National Science and Technology Support Program[No.2013BAI08B01]。
文摘Objective To determine the factors influencing insomnia and construct early insomnia warning tools for rescuers to informbest practices for early screening and intervention.Methods Cluster sampling was used to conduct a cross-sectional survey of 1,133 rescuers from one unit in Beijing,China.Logistic regression modeling and R software were used to analyze insomniarelated factors and construct a PRISM model,respectively.Results The positive rate of insomnia among rescuers was 2.74%.Accounting for participants’age,education,systolic pressure,smoking,per capita family monthly income,psychological resilience,and cognitive emotion regulation,logistic regression analysis revealed that,compared with families with an average monthly income less than 3,000 yuan,the odds ratio(OR)values and the[95%confidence interval(CI)]for participants of the following categories were as follows:average monthly family income greater than 5,000 yuan:2.998(1.307–6.879),smoking:4.124(1.954–8.706),and psychological resilience:0.960(0.933–0.988).The ROC curve area of the PRISM model(AUC)=0.7650,specificity=0.7169,and sensitivity=0.7419.Conclusion Insomnia was related to the participants’per capita family monthly income,smoking habits,and psychological resilience on rescue workers.The PRISM model’s good diagnostic value advises its use to screen rescuer early sleep quality.Further,advisable interventions to optimize sleep quality and battle effectiveness include psychological resilience training and smoking cessation.
文摘目的通过机器学习算法对失眠患者的多导睡眠监测(polysomnography,PSG)数据进行挖掘,建立失眠患者抑郁症的诊断模型,为失眠患者的抑郁症诊断提供科学依据。方法选择2023年1~12月在内蒙古自治区精神卫生中心进行PSG的失眠住院与门诊患者共2162例,抑郁症根据《国际疾病与相关健康问题统计分类第10版》(International Statistical Classification of Diseases and Related Health Problems,10th version,ICD-10)进行诊断。收集患者的一般情况与PSG资料,分别基于logistic回归、支持向量机、随机森林、自适应提升、极限提升树、朴素贝叶斯等6种算法构建失眠患者抑郁症的诊断模型。结果纳入的失眠患者中,40.1%(868例)的患者合并抑郁症。6种模型中,logistic回归和随机森林模型的受试者操作特征曲线(receiver operating characteristic curve,ROC curve)的曲线下面积(area under the curve,AUC)值最高,分别为0.825和0.823,综合分类性能更优。结论Logistic回归和随机森林模型对失眠患者中的抑郁症人群有良好的诊断效能。
文摘介绍目前失眠认知研究中的5种主要模型,包括Spielm an失眠3-P模型、M orin失眠微观分析模型、Lundh和B rom an的睡眠干扰过程和睡眠解释过程相互作用的整合模型、Harvey的失眠维持认知模型及Espie等的注意-意向-努力路径。这些模型从不同角度审视失眠,并针对性地提出了失眠的临床治疗建议。未来需要有一个更加综合的模型整合失眠的形成、发展和持续过程,这也要求进行更多的纵向研究。