基于决策树模型分析注意缺陷多动障碍患儿焦虑现状的影响因素

Analysis of the influencing factors of anxiety status in children with attention deficit hyperactivity disorder based on decision tree model

目的基于决策树模型分析注意缺陷多动障碍(ADHD)患儿焦虑现状的影响因素。方法回顾性分析2022年5月至2024年5月湖北省妇幼保健院接诊的137例ADHD患儿的临床资料,并根据儿童焦虑性情绪障碍筛查表评分结果,将患儿分为焦虑组(36例)及无焦虑组(101例),比较两组一般资料,并采用logistic回归分析ADHD患儿焦虑的影响因素并构建决策树模型;采用受试者工作特征曲线验证模型的预测价值。结果两组性别、主要照顾者文化程度、父母焦虑情况比较,差异有统计学意义(P<0.05);焦虑组中文版注意缺陷多动障碍SNAP-Ⅳ评定量表-父母版(SNAP-Ⅳ)、儿童对婚姻冲突的感知量表(CPIC)、儿童期创伤问卷简化版(CTQ-SF)评分高于无焦虑组(P<0.05);女性、主要照顾者文化初中及以下、父母重度焦虑及SNAP-Ⅳ、CPIC、CTQ-SF评分是ADHD患儿焦虑的独立危险因素(P<0.05);将上述影响因素纳入生成决策树模型,筛选出SNAP-Ⅳ评分、主要照顾者文化程度、CPIC-SF、CTQ评分4个解释变量;该模型的曲线下面积为0.900[95%CI(0.841~0.959),P<0.001]。结论女性、主要照顾者初中及以下文化、父母重度焦虑及SNAP-Ⅳ、CPIC、CTQ-SF评分是ADHD患儿焦虑的危险因素,基于上述影响因素构建的决策树模型有良好预测价值。

Objective To analyze the influencing factors of anxiety status in children with attention deficit hyperactivity disorder(ADHD)based on decision tree model.Methods The clinical data of 137 children with ADHD admitted to the Maternal and Child Health Hospital of Hubei Province from May 2022 to May 2024 were retrospectively analyzed.According to the score of the screen for child anxiety related emotional disorders,the children were divided into anxiety group(36 cases)and non-anxiety group(101 cases).The general data of the two groups were compared,and logistic regression was used to analyze the influencing factors of anxiety in children with ADHD and to construct a decision tree model.Receiver operating characteristic curve was used to verify the predictive value of the model.Results There were statistically significant differences in gender,education level of main caregivers,and anxiety of parents between the two groups(P<0.05).The scores of the Chinese version Swanson,Nolan and Pelham scaleversionⅣ(SNAP-Ⅳ),the children’s perception of interparental conflict scale(CPIC),and the childhood trauma questionnaire-short form(CTQ-SF)in the anxiety group were higher than those in the non-anxiety group(P<0.05).Female,primary caregivers with junior high school education or below,parents’severe anxiety,and SNAP-Ⅳ,CPIC,and CTQ-SF scores were independent risk factors for anxiety in children with ADHD(P<0.05).The above influencing factors were included in the generative decision tree model,and four explanatory variables including SNAP-Ⅳscore,education level of main caregivers,CPIC-SF,and CTQ score were screened out.The area under the curve of the model was 0.900(95%CI[0.841-0.959],P<0.001).Conclusion Female,primary caregivers with junior high school education or below,parents’severe anxiety,and SNAP-Ⅳ,CPIC,and CTQ-SF scores are risk factors for anxiety in ADHD children.The decision tree model based on the above influ encing factors has a good predictive value.