腹腔镜前列腺根治性切除术后切缘阳性预测模型的建立和验证

Establishment and validation of a predictive nomogram for the risk of positive surgical margin in laparoscopic radical prostatectomy

目的:建立和评估腹腔镜前列腺根治性切除术后切缘阳性的预测模型。方法:采用回顾性观察性研究,使用随机分裂样本方法将数据划分为训练和验证数据集(分裂比=0.6∶0.4)。应用Lasso回归筛选预测因子并建立预测模型。用受试者工作特征(ROC)曲线评价模型的区分性,用校正曲线评价预测的准确性。应用决策曲线分析评价模型的临床应用价值。结果:年龄、PSA、术后Gleason评分、前列腺双侧侵犯、PSA密度(PSAD)被确定为预测因素,并组合成预测模型。模型在训练数据集AUC:0.738和验证数据集AUC:0.691。有较好的区分性,且在2个数据集中均有较好的校正效果(均P>0.05)。决策曲线分析表明,该模型具有较好的临床应用价值。结论:本研究提出了一种有效的腹腔镜前列腺根治术后切缘阳性的预测模型,该预测模型在腹腔镜前列腺根治性切除术后切缘阳性的个体化预测具有潜在的应用价值。

Objective:To establish and evaluate a predictive nomogram for the risk of positive surgical margin in patients undergo laparoscopic radical prostatectomy.Methods:A retrospectively observational study was performed and designed.A credible random split-sample method was used to divide data into training and validation dataset(split ratio=0.6:0.4).Least absolute shrinkage and selection operator(Lasso)logistic regression was applied to select predictors and establish 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 usefulness of nomogram was also evaluated with decision curve analysis.Results:Age,prostate specific antigen(PSA)postoperative Gleason score,bilateral invasion of prostate and PSAD were identified as predictors,and they all assembled into the nomogram.The nomogram showed good discrimination with the area under the roc curve(AUC)in training dataset 0.738 and validation dataset 0.691,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 positive surgical margin in laparoscopic radical prostatectomy.It has certain clinical guiding significance in predicting the positive surgical margin,formulating appropriate surgical methods and postoperative prevention.