Construction of a back propagation neural network model for predicting urosepsis after flexible ureteroscopic lithotripsy based on heparin-binding protein and C-reactive protein levels.
{"title":"Construction of a back propagation neural network model for predicting urosepsis after flexible ureteroscopic lithotripsy based on heparin-binding protein and C-reactive protein levels.","authors":"Wenwei Chen, Yanfeng He, Kaixin Lu, Changyi Liu, Tao Jiang, Hua Zhang, Rui Gao, Xueyi Xue","doi":"10.3724/zdxbyxb-2024-0128","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To analyze the association of serum heparin-binding protein (HBP) and C-reactive protein (CRP) levels with urosepsis following flexible ureteroscopic lithotripsy (FURL) and to construct a back propagation neural network prediction model.</p><p><strong>Methods: </strong>A total of 428 patients with kidney stones who underwent FURL were enrolled. Patients were divided into sepsis group (<i>n</i>=42) and control group (<i>n</i>=386) according to whether post-operative urosepsis developed. Logistic regression analysis was used to determine the risk factors and interactions of post-FURL urosepsis. A Logistic regression model and a neural network model were developed for predicting post-FURL urosepsis following FURL, and their predictive performance was evaluated using ROC curves.</p><p><strong>Results: </strong>Univariate analysis showed that stone surgery history, gender, urine culture, stone diameter, diabetes, operation time, white blood cell (WBC), platelet, CRP, and HBP levels were significantly associated with post-FURL urosepsis (<i>P</i><0.05). Multivariate analysis identified positive urine culture, CRP, and HBP levels as independent risk factors for post-FURL urosepsis (<i>P</i><0.05). Interaction analysis revealed that CRP and HBP showed both additive (<i>RERI</i>=8.453, 95%<i>CI</i>: 2.645-16.282; <i>AP</i>=0.696, 95%<i>CI</i>: 0.131-1.273; <i>S</i>=3.369, 95%<i>CI</i>: 1.176-7.632) and multiplicative (<i>OR</i>=1.754, 95%<i>CI</i>: 1.218-3.650) interactions, while CRP and urine culture demonstrated multiplicative interaction (<i>OR</i>=2.449, 95%<i>CI</i>: 1.525-3.825). The neural network model showed superior predictive performance compared to the Logistic regression model.</p><p><strong>Conclusions: </strong>CRP and HBP levels are independent risk factors for post-FURL urosepsis. The neural network model based on CRP and HBP exhibits higher predictive accuracy than the Logistic regression model, which may provide a reliable risk assessment tool for early discrimination and intervention of post-FURL urosepsis.</p>","PeriodicalId":24007,"journal":{"name":"Zhejiang da xue xue bao. Yi xue ban = Journal of Zhejiang University. Medical sciences","volume":" ","pages":"1-9"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Zhejiang da xue xue bao. Yi xue ban = Journal of Zhejiang University. Medical sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3724/zdxbyxb-2024-0128","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: To analyze the association of serum heparin-binding protein (HBP) and C-reactive protein (CRP) levels with urosepsis following flexible ureteroscopic lithotripsy (FURL) and to construct a back propagation neural network prediction model.
Methods: A total of 428 patients with kidney stones who underwent FURL were enrolled. Patients were divided into sepsis group (n=42) and control group (n=386) according to whether post-operative urosepsis developed. Logistic regression analysis was used to determine the risk factors and interactions of post-FURL urosepsis. A Logistic regression model and a neural network model were developed for predicting post-FURL urosepsis following FURL, and their predictive performance was evaluated using ROC curves.
Results: Univariate analysis showed that stone surgery history, gender, urine culture, stone diameter, diabetes, operation time, white blood cell (WBC), platelet, CRP, and HBP levels were significantly associated with post-FURL urosepsis (P<0.05). Multivariate analysis identified positive urine culture, CRP, and HBP levels as independent risk factors for post-FURL urosepsis (P<0.05). Interaction analysis revealed that CRP and HBP showed both additive (RERI=8.453, 95%CI: 2.645-16.282; AP=0.696, 95%CI: 0.131-1.273; S=3.369, 95%CI: 1.176-7.632) and multiplicative (OR=1.754, 95%CI: 1.218-3.650) interactions, while CRP and urine culture demonstrated multiplicative interaction (OR=2.449, 95%CI: 1.525-3.825). The neural network model showed superior predictive performance compared to the Logistic regression model.
Conclusions: CRP and HBP levels are independent risk factors for post-FURL urosepsis. The neural network model based on CRP and HBP exhibits higher predictive accuracy than the Logistic regression model, which may provide a reliable risk assessment tool for early discrimination and intervention of post-FURL urosepsis.