Prediction model of random forest for the risk of hyperuricemia in a Chinese basic health checkup test.
Prediction model of random forest for the risk of hyperuricemia in a Chinese basic health checkup test.
复制标题
中国基础健康体检中高尿酸血症风险的随机森林预测模型
DOI：
10.1042/bsr20203859
复制
发表时间：
2021-04-30
影响因子：
4
通讯作者：
Fan Y
中科院分区：
文献类型：
--
作者：
Gao Y;Jia S;Li D;Huang C;Meng Z;Wang Y;Yu M;Xu T;Liu M;Sun J;Jia Q;Zhang Q;Gao Y;Song K;Wang X;Fan Y
摘要 目的：本研究旨在开发一种基于随机森林（RF）的高尿酸血症（HUA）预测模型，并将其性能与传统逻辑回归（LR）模型进行比较。方法：这项横断面研究招募了 91,690 名参与者（14,032 名患有 HUA，77,658 名未患有 HUA）。我们在训练集中构建了基于 RF 的预测模型，并在验证集中对其进行了评估。通过受试者工作特征（ROC）曲线分析将 RF 模型的性能与 LR 模型进行比较。结果：RF模型的敏感性和特异性在男性中分别为0.702和0.650，在女性中分别为0.767和0.721。男性阳性预测值（PPV）和阴性预测值（NPV）分别为0.372和0.881，女性分别为0.159和0.978。男性 RF 模型的 AUC 为 0.739 (0.728–0.750)，女性为 0.818 (0.799–0.837)。男性 LR 模型的 AUC 为 0.730 (0.718–0.741)，女性为 0.815 (0.795–0.835)。 RF的预测能力略高于LR，但在女性中无统计学意义（Delong检验，男性P=0.0015，女性P=0.5415）。结论：与LR相比，RF在HUA状态预测和特征关联或交互的容忍度方面具有良好的性能，显示出RF在进一步应用中的巨大潜力。前瞻性队列对于 HUA 发展预测是必要的。应鼓励高危因素人群积极控制，降低发生HUA的概率。
Abstract Objectives: The present study aimed to develop a random forest (RF) based prediction model for hyperuricemia (HUA) and compare its performance with the conventional logistic regression (LR) model. Methods: This cross-sectional study recruited 91,690 participants (14,032 with HUA, 77,658 without HUA). We constructed a RF-based prediction model in the training sets and evaluated it in the validation sets. Performance of the RF model was compared with the LR model by receiver operating characteristic (ROC) curve analysis. Results: The sensitivity and specificity of the RF models were 0.702 and 0.650 in males, 0.767 and 0.721 in females. The positive predictive value (PPV) and negative predictive value (NPV) were 0.372 and 0.881 in males, 0.159 and 0.978 in females. AUC of the RF models was 0.739 (0.728–0.750) in males and 0.818 (0.799–0.837) in females. AUC of the LR models were 0.730 (0.718–0.741) for males and 0.815 (0.795–0.835) for females. The predictive power of RF was slightly higher than that of LR, but was not statistically significant in females (Delong tests, P=0.0015 for males, P=0.5415 for females). Conclusion: Compared with LR, the good performance in HUA status prediction and the tolerance of features associations or interactions showed great potential of RF in further application. A prospective cohort is necessary for HUA developing prediction. People with high risk factors should be encouraged to actively control to reduce the probability of developing HUA.