This study presented an optimal prediction model for QOL among middle-aged South Korean adults (N = 4,048; aged 30-55 years) using a machine-learning technique. Community-based South Korean population data were sampled through multistage stratified cluster sampling. Twenty-one variables related to individual factors and various lifestyle patterns were surveyed. QOL was assessed using the Short Form Health Survey (SF-12) and categorized into total QOL, physical component score (PCS), and mental component score (MCS). Seven machine-learning algorithms were used to predict QOL: decision tree, Gaussian Naïve Bayes, k-nearest neighbor, logistic regression, extreme gradient boosting, random forest, and support vector machine. Data imbalance was resolved with the synthetic minority oversampling technique (SMOTE). Random forest was used to compare feature importance and visualize the importance of each variable.
For predicting QOL deterioration, the random forest method showed the highest performance. The random forest algorithm using SMOTE showed the highest area under the receiver operating characteristic (AUC) for total QOL (0.822), PCS (0.770), and MCS (0.786). Applying the data, SMOTE enhanced model performance by up to 0.111 AUC. Although feature importance differed across the three QOL indices, stress and sleep quality were identified as the most potent predictors of QOL. Random forest generated the most accurate prediction of QOL among middle-aged adults; the model showed that stress and sleep quality management were essential for improving QOL.
The results highlighted the need to develop a health management program for middle-aged adults that enables multidisciplinary management of QOL.
方法:本研究使用机器学习技术为韩国中年成年人(N=4,048;年龄30-55岁)的QOL提供了最佳预测模型。通过多阶段分层整群抽样对基于社区的韩国人口数据进行抽样。调查了21个与个体因素和各种生活方式相关的变量。QOL使用简短形式健康调查(SF-12)进行评估,并分类为总QOL,物理元件得分(PCS),和心理成分评分(MCS)。七种机器学习算法用于预测QOL:决策树,高斯朴素贝叶斯,k-最近邻,逻辑回归,极端梯度增强,随机森林,和支持向量机。使用合成少数过采样技术(SMOTE)解决了数据不平衡。随机森林用于比较特征重要性并可视化每个变量的重要性。
结果:为了预测生活质量恶化,随机森林方法表现出最高的性能。使用SMOTE的随机森林算法显示了总QOL(0.822)的接收器操作特性(AUC)下的最高区域,PCS(0.770),和MCS(0.786)。应用数据,SMOTE将模型性能提高了0.111AUC。尽管特征重要性在三个QOL指数中有所不同,压力和睡眠质量被确定为最有效的QOL预测因子。随机森林在中年成年人中产生了最准确的QOL预测;该模型表明,压力和睡眠质量管理对于改善QOL至关重要。
结论:结果强调需要为中年人制定一项健康管理计划,以实现QOL的多学科管理。