Department of Nuclear Medicine, Tianjin Medical University General Hospital, Tianjin, P.R. China.
School of Medical Imaging, Tianjin Medical University, Tianjin, P.R. China.
Biosci Rep. 2021 Apr 30;41(4). doi: 10.1042/BSR20203859.
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.
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.
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).
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.
本研究旨在建立基于随机森林（RF）的高尿酸血症（HUA）预测模型，并与传统的逻辑回归（LR）模型进行比较。
本横断面研究纳入了 91690 名参与者（14032 名患有 HUA，77658 名无 HUA）。我们在训练集中构建了一个基于 RF 的预测模型，并在验证集中进行了评估。通过接收者操作特征（ROC）曲线分析比较了 RF 模型和 LR 模型的性能。
在男性中，RF 模型的灵敏度和特异性分别为 0.702 和 0.650，在女性中分别为 0.767 和 0.721。阳性预测值（PPV）和阴性预测值（NPV）分别为 0.372 和 0.881。在男性中，AUC 为 0.739（0.728-0.750），在女性中为 0.818（0.799-0.837）。LR 模型在男性中的 AUC 为 0.730（0.718-0.741），在女性中为 0.815（0.795-0.835）。RF 的预测能力略高于 LR，但在女性中没有统计学意义（Delong 检验，男性为 P=0.0015，女性为 P=0.5415）。
与 LR 相比，RF 在 HUA 状态预测方面表现良好，并且对特征关联或相互作用的容忍度较高，在进一步应用中具有很大的潜力。需要前瞻性队列研究来预测 HUA 的发生。应鼓励高风险因素的人群积极控制，以降低发生 HUA 的概率。
