Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values

Abstract This study aims to develop a machine learning model utilizing Computed Tomography (CT) values to predict systemic inflammatory response syndrome (SIRS) after endoscopic surgery for kidney stones. The goal is to identify high-risk patients early and provide valuable guidance for urologists i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiaxin Li, Yao Du, Gaoming Huang, Yawei Huang, Xiaoqing Xi, Zhenfeng Ye
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-88704-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1823862285783793664
author Jiaxin Li
Yao Du
Gaoming Huang
Yawei Huang
Xiaoqing Xi
Zhenfeng Ye
author_facet Jiaxin Li
Yao Du
Gaoming Huang
Yawei Huang
Xiaoqing Xi
Zhenfeng Ye
author_sort Jiaxin Li
collection DOAJ
description Abstract This study aims to develop a machine learning model utilizing Computed Tomography (CT) values to predict systemic inflammatory response syndrome (SIRS) after endoscopic surgery for kidney stones. The goal is to identify high-risk patients early and provide valuable guidance for urologists in the early diagnosis and intervention of post-operative urosepsis. This study included 833 patients who underwent retrograde intrarenal surgery (RIRS) or percutaneous nephrolithotomy (PCNL) for kidney stones. Five machine learning algorithms and ten preoperative or intraoperative variables were used to develop a predictive model for SIRS. The SHapley Additive exPlanations (SHAP) method was used to explain the distribution of feature importance in the model’s predictions. Among the 833 patients, 126 (15.1%) developed SIRS postoperatively. All five machine learning models demonstrated strong discrimination on the validation set (AUC: 0.690–0.858). The eXtreme Gradient Boosting (XGBoost) model was the best performer [AUC: 0.858; sensitivity: 0.877; specificity: 0.981; accuracy: 0.841; positive predictive value: 0.629; negative predictive value: 0.851]. The characteristic importance of the Machine Learning model (ML model) and SHAP results indicated Hounsfield Unit (HU), Urinary protein, Stone burden, and Serum uric acid as important predictors for the model. A machine learning model utilizing CT values was developed to predict postoperative SIRS in endoscopic kidney stone surgery. The model demonstrates strong predictive performance and can assist in assessing the risk of urosepsis in postoperative patients.
format Article
id doaj-art-275f4d5796f34fe8a065b9472b91b64c
institution Kabale University
issn 2045-2322
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-275f4d5796f34fe8a065b9472b91b64c2025-02-09T12:35:20ZengNature PortfolioScientific Reports2045-23222025-02-0115111310.1038/s41598-025-88704-yConstructing a machine learning model for systemic infection after kidney stone surgery based on CT valuesJiaxin Li0Yao Du1Gaoming Huang2Yawei Huang3Xiaoqing Xi4Zhenfeng Ye5Department of Urology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Cardiovascular Medicine, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Urology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Urology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Urology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityDepartment of Urology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang UniversityAbstract This study aims to develop a machine learning model utilizing Computed Tomography (CT) values to predict systemic inflammatory response syndrome (SIRS) after endoscopic surgery for kidney stones. The goal is to identify high-risk patients early and provide valuable guidance for urologists in the early diagnosis and intervention of post-operative urosepsis. This study included 833 patients who underwent retrograde intrarenal surgery (RIRS) or percutaneous nephrolithotomy (PCNL) for kidney stones. Five machine learning algorithms and ten preoperative or intraoperative variables were used to develop a predictive model for SIRS. The SHapley Additive exPlanations (SHAP) method was used to explain the distribution of feature importance in the model’s predictions. Among the 833 patients, 126 (15.1%) developed SIRS postoperatively. All five machine learning models demonstrated strong discrimination on the validation set (AUC: 0.690–0.858). The eXtreme Gradient Boosting (XGBoost) model was the best performer [AUC: 0.858; sensitivity: 0.877; specificity: 0.981; accuracy: 0.841; positive predictive value: 0.629; negative predictive value: 0.851]. The characteristic importance of the Machine Learning model (ML model) and SHAP results indicated Hounsfield Unit (HU), Urinary protein, Stone burden, and Serum uric acid as important predictors for the model. A machine learning model utilizing CT values was developed to predict postoperative SIRS in endoscopic kidney stone surgery. The model demonstrates strong predictive performance and can assist in assessing the risk of urosepsis in postoperative patients.https://doi.org/10.1038/s41598-025-88704-yMachine learningRenal endoscopic lithotripsyUrosepsisCT valuesShapley Additive exPlanations (SHAP)
spellingShingle Jiaxin Li
Yao Du
Gaoming Huang
Yawei Huang
Xiaoqing Xi
Zhenfeng Ye
Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
Scientific Reports
Machine learning
Renal endoscopic lithotripsy
Urosepsis
CT values
Shapley Additive exPlanations (SHAP)
title Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
title_full Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
title_fullStr Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
title_full_unstemmed Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
title_short Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values
title_sort constructing a machine learning model for systemic infection after kidney stone surgery based on ct values
topic Machine learning
Renal endoscopic lithotripsy
Urosepsis
CT values
Shapley Additive exPlanations (SHAP)
url https://doi.org/10.1038/s41598-025-88704-y
work_keys_str_mv AT jiaxinli constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues
AT yaodu constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues
AT gaominghuang constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues
AT yaweihuang constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues
AT xiaoqingxi constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues
AT zhenfengye constructingamachinelearningmodelforsystemicinfectionafterkidneystonesurgerybasedonctvalues