Application of machine learning models in predicting renal function decline following robot-assisted partial nephrectomy
10.13406/j.cnki.cyxb.003799
- VernacularTitle:机器学习模型预测机器人辅助肾部分切除术后肾功能减退
- Author:
Jing LI
1
;
Linfeng WANG
;
Gaojie ZHANG
;
Yong HUANG
;
Yingying GAO
;
Rui SUN
;
Yang CAO
;
Qiuchen LI
;
Hao HE
;
Ziling WEI
;
Jiayu LIU
Author Information
1. 重庆医科大学第一临床学院,重庆 401331
- Keywords:
robot-assisted partial nephrectomy;
renal function decline;
machine learning model;
Shapley additive explanation;
predic-tive model;
postoperative management
- From:
Journal of Chongqing Medical University
2025;50(4):457-462
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To compare the efficacy of various machine learning models in predicting renal function decline after robot-assisted partial nephrectomy(RAPN),and to provide evidence for clinical risk stratification.Methods:This study retrospectively in-cluded the clinical data of 733 patients with renal cell carcinoma undergoing RAPN at the Urology Department of The First Affiliated Hospital of Chongqing Medical University from January 2019 to December 2023.Demographic characteristics,laboratory indicators,and perioperative parameters were integrated to construct seven machine learning models.Key predictors were interpreted using Shap-ley additive explanations(SHAP).Model performance was evaluated using the area under the receiver operating characteristic curve(AUC).Results:The random forest model demonstrated the best predictive performance(AUC=0.84).SHAP analysis identified neutrophil-to-lymphocyte ratio,tumor diameter,the international normalized ratio of prothrombin time,white blood cell count,and in-traoperative blood loss as significant factors influencing postoperative renal function decline.Conclusion:This study provides a poten-tial predictive tool for clinical practice,aiding in identifying high-risk patients and optimizing postoperative management strategies.
