Page 130 - 南京医科大学自然版

南京医科大学学报（自然科学版） 第45卷第8期
·1186 · Journal of Nanjing Medical University（Natural Sciences） 2025年8月

·临床研究·

高危前列腺癌患者穿刺病理预测模型的构建及验证研究

钱 哲 ，臧 攀 ，丁 磊 ，王宇昊 ，梁 超 ，李 杰 1*
1
1
2
1
1
南京医科大学第一附属医院泌尿外科，江苏 南京 210029；徐州医科大学附属医院泌尿外科，江苏 徐州 221000
1 2
［摘 要］ 目的：通过分析高危前列腺癌患者的临床数据，建立模型预测其前列腺病灶的病理性质，识别可免于系统穿刺而单
独进行靶向穿刺的患者，优化当前前列腺穿刺活检策略。方法：回顾性分析2022年1月—2024年6月于南京医科大学第一附
属医院行前列腺穿刺患者的临床数据，筛选出符合条件的患者分为训练集和验证集。单因素和多因素逻辑回归分析用于筛选
前列腺靶向穿刺病理的显著相关因素。基于训练集的数据构建预测模型，并在验证集中验证该模型效能。受试者工作特征
（receiver operating characteristic，ROC）曲线用于评估模型在两个数据集中的诊断性能。结果：年龄（X1）、病灶数量（X2）、病灶所
在的组织学区域（X3）、前列腺影像和数据报告系统（prostate imaging reporting and data system，PI⁃RADS）评分（X4）以及前列腺特
异性抗原密度（X5）是与患者前列腺靶向穿刺病理相关的变量。预测模型的数学表达式为：P=1/［1+e^（-15.770+0.067×X1-
0.658×X2+0.381×X3+2.271×X4+5.742×X5）］。预测模型在训练集中ROC曲线下面积（area under the curve，AUC）为0.856（95%CI：
0.812~0.900），在验证集中AUC为0.886（95%CI：0.776~0.995）。结论：本研究构建的针对高危前列腺癌患者靶向穿刺病理预测
模型能指导临床前列腺穿刺策略，在保持良好诊断性能的同时减少穿刺数，从而减少穿刺并发症，节约医疗资源。
［关键词］ 前列腺癌；前列腺穿刺活检；磁共振成像；预测模型
［中图分类号］ R737.25 ［文献标志码］ A ［文章编号］ 1007⁃4368（2025）08⁃1186⁃09
doi：10.7655/NYDXBNSN250388

Construction and validation study of a puncture pathology prediction model for high⁃risk
prostate cancer patients

1 1 1 2 1 1*
QIAN Zhe ，ZANG Pan ，DING Lei ，WANG Yuhao ，LIANG Chao ，LI Jie
1 Department of Urology，the First Affiliated Hospital of Nanjing Medical University，Nanjing 210029；Department of
2
Urology，the Affiliated Hospital of Xuzhou Medical University，Xuzhou 221000，China

［Abstract］ Objective：To optimize the current strategy of prostate puncture biopsy by analysing the clinical data of high ⁃ risk
prostate cancer patients，establishing a model to predict the pathological nature of their prostate lesions，and identifying patients who
can be exempted from systematic biopsy and undergo targeted puncture alone. Methods：Clinical data of patients who underwent
prostate puncture at the First Affiliated Hospital of Nanjing Medical University from January 2022 to June 2024 were retrospectively
analyzed，and eligible patients were screened and divided into a training set and a validation set. Univariate and multivariate logistic
regression analyses were used to screen the significant factors of the pathology of prostate targeted biopsy. A predictive model was
constructed based on the data from the training set，and the model effectiveness was verified in the validation set. Receiver operating
characteristic（ROC）curves were used to assess the diagnostic performance of the model in both data sets. Results：Age（X1），number
of lesions（X2），histological region in which the lesions are located（X3），prostate imaging reporting and data system（PI⁃RADS）score
（X4），and prostate⁃specific antigen density（X5）were the variables associated with the patient’s prostate targeted biopsy pathology. The
mathematical expression of the predictive model was：P=1/［1+e^（-15.770+0.067×X1-0.658×X2+0.381×X3+2.271×X4+5.742×X5）］.
The area under the curve（AUC）of the prediction model was 0.856（95%CI：0.812-0.900）in the training set and 0.886（95%CI：0.776-
0.995）in the validation set. Conclusion：The constructed prediction model for targeted biopsy pathology in high⁃risk prostate cancer
patients can guide the clinical strategy of prostate puncture to maintain a good diagnostic performance while reducing the number of

［基金项目］ 江苏省科教能力提升工程（ZDXK202219）
通信作者（Corresponding author），E⁃mail：drc_lijie@126.com（ORCID：0000⁃0003⁃0260⁃1611）
∗