文献速递前列腺癌

基于机器学习的有临床意义前列腺癌新型预测模型及在线风险计算器

A Novel Machine Learning-based Predictive Model of Clinically Significant Prostate Cancer and Online Risk Calculator.
PubMed 文献 · Urology · 2024-11-12

研究整合PI-RADS评分、PSA密度及临床变量,在新西兰、澳大利亚和瑞士接受前列腺活检的1272例患者中构建机器学习模型预测有临床意义前列腺癌,LightGBM模型在测试集ROC为0.851,外部数据集ROC为0.818,PI-RADS为最重要变量。

要点

  • LightGBM模型测试集ROC为0.851(95%CI 0.804-0.897),外部数据集ROC为0.818(95%CI 0.798-0.831)。
  • 最重要变量为PI-RADS,其次为PSA密度、既往活检史、年龄和BMI。
  • 模型内部和外部验证均显示高ROC-AUC值,并具有良好的校准指标。

核心结论

  • 开发的预测模型在内部和外部验证中均表现出高ROC-AUC值,提示整合临床参数优于每个单独预测因子,且模型具有良好的校准指标,较现有模型更平衡。

研究设计与样本

  • 研究纳入在新西兰、澳大利亚和瑞士因疑似前列腺癌接受前列腺活检的患者队列,共分析1272例患者,数据集随机分为推导(训练)集和验证(测试)集,并从哈佛Dataverse获取独立数据集进行外部验证。

主要发现

  • 所有模型的ROC-AUC值范围为0.830至0.851,LightGBM被认为是更优模型,测试集ROC为0.851(95%CI 0.804-0.897),外部数据集ROC为0.818(95%CI 0.798-0.831)。
  • 最重要变量为PI-RADS,其次为PSA密度、既往活检史、年龄和BMI。

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 create a machine-learning predictive model combining prostate imaging-reporting and data system (PI-RADS) score, PSA density, and clinical variables to predict clinically significant prostate cancer (csPCa). METHODS: We evaluated a cohort of patients who underwent prostate biopsy for suspected prostate cancer (PCa) in New Zealand, Australia, and Switzerland. We collected data on age, body mass index (BMI), PSA level, prostate volume, PSA density (PSAD), PI-RADS scores, previous biopsy, and corresponding histology results. The dataset was divided into derivation (training) and validation (test) sets using random splits. An independent dataset was obtained from the Harvard Dataverse for external validation. A cohort of 1272 patients was analyzed. We fitted a Lasso model, XGBoost, and LightGBM to the training set and assessed their accuracy. RESULTS: All models demonstrated ROC-AUC values ranging from 0.830 to 0.851. LightGBM was considered the superior model, with an ROC of 0.851 (95%CI: 0.804-0.897) in the test set and 0.818 (95% CI: 0.798-0.831) in the external dataset. The most important variable was PI-RADS, followed by PSA density, history of previous biopsy, age, and BMI. CONCLUSION: We developed a predictive model for detecting csPCa that exhibited a high ROC-AUC value for internal and external validations. This suggests that the integration of the clinical parameters outperformed each individual predictor. Additionally, the model demonstrated good calibration metrics, indicative of a more balanced model than the existing models.

来源:Urology,查看原文。版权归原作者所有。

引用

  1. Vasconcelos Ordones F, Kawano PR, Vermeulen L, et al. A Novel Machine Learning-based Predictive Model of Clinically Significant Prostate Cancer and Online Risk Calculator. Urology. 2024. PMID: 39537107. doi:10.1016/j.urology.2024.11.001

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。