前列腺癌侵犯周围神经的预测因子研究  

Establishment and validation of a predictive nomogram for the risk of prostate cancer perineural invasion

作　　者：任建[1] 黄涛[1] 矫宾宾 陈雪龙 潘逸缙 苏彩霞 闫杨轩宇 王芝晶[1] 张冠[1] REN Jian;HUANG Tao;JIAO Bin-bin(Department of Urology Surgery,China-Japan Friendship Hospital,Beijing 100029,China)

机构地区：[1]中日友好医院泌尿外科,北京100029 [2]北京大学医学部,北京100191

出　　处：《中日友好医院学报》2022年第6期331-336,共6页Journal of China-Japan Friendship Hospital

摘　　要：目的:建立和评价前列腺癌神经周围侵犯的预测模型,为筛选出前列腺癌神经侵犯的高危人群提供预测工具。方法:采用回顾观察性研究,随机分裂样本法将数据划分为训练数据集和验证数据集(分裂比=0.7:0.3)。应用Lasso回归选择预测因子并建立预测模型。采用受试者工作特征(ROC)曲线评价模型的判别能力,校正曲线评价预测的准确性。决策曲线分析评价列线图。结果:纳入患者238例,以前列腺周围神经是否侵犯定义为阴性(n=123)和阳性(n=115)。以PSA,PSA比值、NLR为预测因素,将其组合成预测模型。在训练数据集0.725(95%CI:0.578~0.798)和验证数据集0.678(95%CI:0.419~0.900)中,模型显示出较好的判别能力,并在2个数据集中进行了良好的校正(均P>0.05)。临床决策曲线分析表明此模型有较好的收益作用,临床应用价值较大。结论:本研究以PSA,PSA比值、NLR为预测因素,为前列腺癌神经周围侵犯个体化预测提供了一种有效的预测模型。在预测前列腺癌神经周围侵犯,制定适当的手术方式和术后预防具有一定的临床指导意义。Objective:To develop and evaluate predictive nomogram for the risk of perineural invasion in prostate cancer patients.Methods:A retrospective,observational study was performed and designed.A credible random split-sample method was used to divide data into training and validation dataset(split ratio=0.7:0.3).Least absolute shrinkage and selection operator(Lasso)logistic regression was applied to select predictors and develop the nomogram.The discrimination of the nomogram was assessed using the receiver operating characteristic(ROC)curve,and the calibration curve was used for evaluating the accuracy of prediction.The clinical value of nomogram was also evaluated with decision curve analysis.Results:Prostate specific antigen(PSA),f/t PSA,NLR were identified as predictors and assembled into the nomogram.The nomogram showed good discrimination with the area under the roc curve(AUC)in training dataset(0.725,95%CI:0.578-0.798)and validation dataset(0.678,95%CI:0.419-0.900)and was well calibrated in both datasets(all P>0.05).Decision curve analysis demonstrated that the nomogram was clinically useful.Conclusion:This study proposed an effective nomogram for the individualized prediction of perineural invasion of prostate cancer. It has certain clinical guiding significance in predicting the perineural invasion of prostate cancer,formulating appropriate surgical methods and postoperative prevention.

关 键 词：前列腺肿瘤 前列腺癌 神经侵犯 数据模型 列线图 

分 类 号：R737.25[医药卫生—肿瘤]