基于决策树模型分析肺癌化疗患者睡眠障碍发生的危险因素及护理对策  

Analysis of risk factors and nursing strategies for sleep disorders in lung cancer chemotherapy patients based on decision tree model

作　　者：胡菲 阳华[1] 阳婷 李璐[1] HU Fei;YANG Hua;YANG Ting;LI Lu(Cancer Medical Center of the First Affiliated Hospital of Nanchang University,Nanchang,Jiangxi 330001,China)

机构地区：[1]南昌大学第一附属医院肿瘤医学中心,江西南昌330001

出　　处：《中华全科医学》2024年第12期2158-2161,共4页Chinese Journal of General Practice

基　　金：江西省教育厅科学研究计划项目(GJJ2200122)。

摘　　要：目的分析肺癌化疗患者睡眠障碍的影响因素,制定护理对策以降低肺癌化疗患者睡眠障碍发生风险。方法选取2023年1—12月南昌大学第一附属医院收治的110例肺癌患者作为研究对象。根据阿森斯失眠量表(AIS)评分将患者分为睡眠障碍组(44例)及非睡眠障碍组(66例)。比较2组基线资料、实验室指标;采用二元logistic回归分析肺癌化疗患者睡眠障碍的影响因素,构建决策树模型,绘制受试者工作特征曲线(ROC)验证决策树模型预测效能。结果肺癌化疗患者睡眠障碍发生率[40.00%(44/110)];睡眠障碍组化疗周期、视觉模拟评分法(VAS)评分、白细胞介素-6(IL-6)、肿瘤坏死因子-α(TNF-α)、C反应蛋白(CRP)高于非睡眠障碍组,Ⅲ~Ⅳ分期、使用紫杉醇+铂类化疗方案占比高于非睡眠障碍组(P<0.05);二元logistic回归分析结果显示,Ⅲ~Ⅳ分期、紫杉醇+铂类化疗方案、化疗周期、VAS评分、IL-6是肺癌化疗患者睡眠障碍的影响因素(OR>1,P<0.05);纳入以上因素生成决策树模型,共筛出VAS评分、IL-6、TNM分期3个解释变量,VAS评分为最重要根节点变量、预测因子。决策树预测模型曲线下面积为0.915,P<0.001,预测价值较高。结论TNM分期、化疗方案、化疗周期、VAS评分、IL-6构建的决策树模型对肺癌化疗患者睡眠障碍具有较高的预测价值。Objective To analyze the influencing factors of sleep disorders in lung cancer chemotherapy patients and develop nursing strategies to reduce the risk of sleep disorders in lung cancer chemotherapy patients.Methods A total of 110 lung cancer patients admitted to the First Affiliated Hospital of Nanchang University from January 2023 to December 2023 were selected as the research subjects.Patients were divided into a sleep disorder group(n=44)and a non-sleep disorder group(n=66)based on the Athens insomnia scale(AIS)score.Baseline data and laboratory indicators were compared between the two groups;Binary logistic regression was used to analyze the influencing factors of sleep disorders in lung cancer chemotherapy patients,build a decision tree model,and draw receiver operating characteristic curves(ROC)to verify the predictive efficiency of the decision tree model.Results The incidence of sleep disorders in lung cancer chemotherapy patients[40.00%(44/110)];The chemotherapy cycle,visual analog scale(VAS)score,interleukin-6(IL-6),tumor necrosis factor-α(TNF-α),and C-reactive protein(CRP)in the sleep disorder group were higher than those in the non-sleep disorder group.The proportion of stageⅢ-Ⅳand the use of paclitaxel+platinum chemotherapy regimen was higher in the sleep disorder group than in the non-sleep disorder group(P<0.05);According to binary logistic regression analysis,stagesⅢ-Ⅳ,paclitaxel+platinum chemotherapy regimen,chemotherapy cycle,VAS score,and IL-6 were the influencing factors of sleep disorders in lung cancer chemotherapy patients(OR>1,P<0.05).A decision tree model was generated by incorporating these factors,and three explanatory variables including VAS score,IL-6,and TNM staging were screened out.VAS score was the most important root node variable and predictor.The AUC of the decision tree prediction model was 0.915,P<0.001,indicating a high predictive value.Conclusion The decision tree model constructed by TNM staging,chemotherapy regimen,chemotherapy cycle,VAS score,and IL-6 has a hig

关 键 词：肺癌 睡眠障碍 化疗 影响因素 决策树 

分 类 号：R734.2[医药卫生—肿瘤] R473.73[医药卫生—临床医学]