文献速递前列腺癌

基于炎症与营养指标的前列腺癌骨转移机器学习模型开发与验证

Development and Validation of a Machine Learning Model for Bone Metastasis in Prostate Cancer: Based on Inflammatory and Nutritional Indicators.
PubMed 文献 · Urology · 2024-05-31

回顾性分析甘肃省人民医院泌尿外科2017年6月至2022年6月初诊前列腺癌患者404例,用逻辑回归(LR)和LASSO联合筛选特征并构建LR、随机森林(RF)、极端梯度提升(XGBoost)、朴素贝叶斯(NB)、k近邻(KNN)、决策树(DT)模型预测骨转移。训练集5折交叉验证平均AUC以LR最高(0.9054);测试集KNN的AUC最高(0.9390,95%CI 0.8760-1)。综合评价显示LR在可解释性和临床应用方面表现良好,炎症与营养指标与骨转移相关性较弱。

要点

  • 以Gleason评分、T分期、N分期、PSA和ALP为特征构建前列腺癌骨转移机器学习模型。
  • 训练集5折交叉验证平均AUC:LR 0.9054、RF 0.9032、NB 0.8961、KNN 0.8704、DT 0.8526、XGBoost 0.8066。
  • 测试集AUC:KNN 0.9390(95%CI 0.8760-1)、RF 0.9290(95%CI 0.8718-0.9861)、NB 0.9268(95%CI 0.8615-0.9920)、LR 0.9212(95%CI 0.8506-0.9917)、XGBoost 0.8292(95%CI 0.7442-0.9141)、DT 0.8057(95%CI 0.7100-0.9014)。

核心结论

  • 建立了前列腺癌骨转移模型,并观察到炎症和营养等指标与骨转移相关性较弱。

研究设计与样本

  • 回顾性分析甘肃省人民医院泌尿外科2017年6月至2022年6月初诊前列腺癌患者临床数据,最终筛选404例。
  • 采用逻辑回归(LR)和最小绝对收缩和选择算子(LASSO)联合筛选模型特征。
  • 将筛选特征纳入LR、随机森林(RF)、极端梯度提升(XGBoost)、朴素贝叶斯(NB)、k近邻(KNN)和决策树(DT)算法构建前列腺癌骨转移模型。

主要发现

  • Gleason评分、T分期、N分期、PSA和ALP被用作建模特征。
  • 训练集5折交叉验证平均AUC:LR为0.9054,RF为0.9032,NB为0.8961,KNN为0.8704,DT为0.8526,XGBoost为0.8066。
  • 测试集AUC:KNN为0.9390(95%CI 0.8760-1),RF为0.9290(95%CI 0.8718-0.9861),NB为0.9268(95%CI 0.8615-0.9920),LR为0.9212(95%CI 0.8506-0.9917),XGBoost为0.8292(95%CI 0.7442-0.9141),DT为0.8057(95%CI 0.7100-0.9014)。
  • 综合评价显示LR在可解释性和临床应用方面表现良好。
  • 观察到炎症和营养等指标与骨转移相关性较弱。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To establish a predictive model for prostate cancer bone metastasis utilizing multiple machine learning algorithms. METHODS: Retrospective analysis of the clinical data of prostate cancer initially diagnosed in the Department of Urology of Gansu Provincial People's Hospital from June 2017 to June 2022. Logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) are used to jointly screen the model features. The filtered features are incorporated into algorithms including LR, random forest (RF), extreme gradient boosting (XGBoost), naive Bayes (NB), k-nearest neighbor (KNN), and decision tree (DT), to develop prostate cancer bone metastasis models. RESULTS: A total of 404 patients were finally screened. Gleason score, T stage, N stage, PSA, and ALP were used as features for modeling. The average AUC of the 5-fold cross-validation for each machine learning model in the training set is as follows: LR (AUC=0.9054), RF (AUC=0.9032), NB (AUC=0.8961), KNN (AUC=0.8704), DT (AUC=0.8526), XGBoost (AUC=0.8066). The AUC of each machine learning model in the test set is KNN (AUC=0.9390, 95%CI: 0.8760-1), RF (AUC=0.9290, 95%CI: 0.8718-0.9861), NB (AUC=0.9268, 95%CI: 0.8615-0.9920), LR (AUC=0.9212, 95%CI: 0.8506-0.9917), XGBoost (AUC=0.8292, 95%CI: 0.7442-0.9141), DT (AUC=0.8057, 95%CI: 0.7100-0.9014). A comprehensive evaluation showed that LR performed well in interpretability and clinical applications. CONCLUSION: A bone metastasis model of prostate cancer was established, and it was observed that indicators such as inflammation and nutrition had a weak correlation with bone metastasis.

来源:Urology,查看原文。版权归原作者所有。

引用

  1. Jin T, An J, Wu W, et al. Development and Validation of a Machine Learning Model for Bone Metastasis in Prostate Cancer: Based on Inflammatory and Nutritional Indicators. Urology. 2024. PMID: 38825085. doi:10.1016/j.urology.2024.05.027

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。