Department of Dermatology, Xianyang Central Hospital, Xianyang 712000, China.
Department of Clinical Medical Research Center, Xianyang Central Hospital, Xianyang 712000, China.
Comput Math Methods Med. 2022 Oct 3;2022:5676570. doi: 10.1155/2022/5676570. eCollection 2022.
Since the prognosis of renal cell carcinoma (RCC) patients with bone metastasis (BM) is poor, this study is aimed at using big data to build a machine learning (ML) model to predict the risk of BM in RCC patients.
A retrospective study was conducted on 40,355 RCC patients in the SEER database from 2010 to 2017. LASSO regression and multivariate logistic regression analysis was performed to determine independent risk factors of RCC-BM. Six ML algorithm models, including LR, GBM, XGB, RF, DT, and NBC, were used to establish risk models for predicting RCC-BM. The prediction performance of ML models was weighed by 10-fold cross-validation.
The study investigated 40,355 patients diagnosed with RCC in the SEER database, where 1,811 (4.5%) were BM patients. Independent risk factors for BM were tumor grade, T stage, N stage, liver metastasis, lung metastasis, and brain metastasis. Among the RCC-BM risk prediction models established by six ML algorithms, the XGB model showed the best prediction performance (AUC = 0.891). Therefore, a network calculator based on the XGB model was established to individually assess the risk of BM in patients with RCC.
The XGB risk prediction model based on the ML algorithm performed a good prediction effect on BM in RCC patients.
由于肾细胞癌（RCC）伴骨转移（BM）患者的预后较差，本研究旨在利用大数据构建机器学习（ML）模型来预测 RCC 患者发生 BM 的风险。
对 2010 年至 2017 年 SEER 数据库中 40355 例 RCC 患者进行回顾性研究。采用 LASSO 回归和多因素逻辑回归分析确定 RCC-BM 的独立危险因素。采用 LR、GBM、XGB、RF、DT 和 NBC 等 6 种 ML 算法模型建立预测 RCC-BM 的风险模型。通过 10 折交叉验证来衡量 ML 模型的预测性能。
本研究共纳入 SEER 数据库中诊断为 RCC 的 40355 例患者，其中 1811 例（4.5%）为 BM 患者。BM 的独立危险因素包括肿瘤分级、T 分期、N 分期、肝转移、肺转移和脑转移。在 6 种 ML 算法建立的 RCC-BM 风险预测模型中，XGB 模型的预测性能最佳（AUC=0.891）。因此，建立了基于 XGB 模型的网络计算器，用于个体评估 RCC 患者发生 BM 的风险。
基于 ML 算法的 XGB 风险预测模型对 RCC 患者的 BM 具有较好的预测效果。
