基于 PLCO 和 SELECT 试验预测任何及更高等级前列腺癌的未来风险。
Prediction of future risk of any and higher-grade prostate cancer based on the PLCO and SELECT trials.
机构信息
Department of Population Health Sciences, Mail Code 7933, 7703 Floyd Curl Drive, San Antonio, TX, 78229-3900, USA.
Department of Biostatistics, University of North Carolina, Chapel Hill, NC, USA.
出版信息
BMC Urol. 2022 Mar 26;22(1):45. doi: 10.1186/s12894-022-00986-w.
BACKGROUND
A model was built that characterized effects of individual factors on five-year prostate cancer (PCa) risk in the Prostate, Lung, Colon, and Ovarian Cancer Screening Trial (PLCO) and the Selenium and Vitamin E Cancer Prevention Trial (SELECT). This model was validated in a third San Antonio Biomarkers of Risk (SABOR) screening cohort.
METHODS
A prediction model for 1- to 5-year risk of developing PCa and Gleason > 7 PCa (HG PCa) was built on PLCO and SELECT using the Cox proportional hazards model adjusting for patient baseline characteristics. Random forests and neural networks were compared to Cox proportional hazard survival models, using the trial datasets for model building and the SABOR cohort for model evaluation. The most accurate prediction model is included in an online calculator.
RESULTS
The respective rates of PCa were 8.9%, 7.2%, and 11.1% in PLCO (n = 31,495), SELECT (n = 35,507), and SABOR (n = 1790) over median follow-up of 11.7, 8.1 and 9.0 years. The Cox model showed higher prostate-specific antigen (PSA), BMI and age, and African American race to be associated with PCa and HGPCa. Five-year risk predictions from the combined SELECT and PLCO model effectively discriminated risk in the SABOR cohort with C-index 0.76 (95% CI [0.72, 0.79]) for PCa, and 0.74 (95% CI [0.65,0.83]) for HGPCa.
CONCLUSIONS
A 1- to 5-year PCa risk prediction model developed from PLCO and SELECT was validated with SABOR and implemented online. This model can individualize and inform shared screening decisions.
背景
建立了一个模型，该模型描述了个体因素对前列腺癌（PCa）筛查试验（PLCO）和硒和维生素 E 癌症预防试验（SELECT）中五年 PCa 风险的影响。该模型在第三个圣安东尼奥风险生物标志物（SABOR）筛查队列中进行了验证。
方法
使用 Cox 比例风险模型，根据患者基线特征调整，在 PLCO 和 SELECT 中建立了用于预测 1 至 5 年内发生 PCa 和 Gleason > 7 PCa（HG PCa）风险的预测模型。随机森林和神经网络与 Cox 比例风险生存模型进行了比较，使用试验数据集进行模型构建，使用 SABOR 队列进行模型评估。最准确的预测模型包含在在线计算器中。
结果
在 PLCO（n = 31495）、SELECT（n = 35507）和 SABOR（n = 1790）中，中位随访 11.7、8.1 和 9.0 年，PCa 的发生率分别为 8.9%、7.2%和 11.1%。Cox 模型显示较高的前列腺特异性抗原（PSA）、BMI 和年龄以及非裔美国人种族与 PCa 和 HGPCa 相关。来自 SELECT 和 PLCO 联合模型的五年风险预测有效地在 SABOR 队列中区分了风险，PCa 的 C 指数为 0.76（95%CI [0.72, 0.79]），HGPCa 为 0.74（95%CI [0.65,0.83]）。
结论
从 PLCO 和 SELECT 开发的 1 至 5 年 PCa 风险预测模型在 SABOR 中进行了验证，并在线实施。该模型可以对个体进行分类，并为共享筛查决策提供信息。
Zotero 插件