Development and validation of a LASSO-logistic regression-based prediction model for testicular atrophy after laparoscopic orchiopexy
YANG Bin
LIU Cai-xia
WANG Hui-se
ZHAO Zi-jian
WANG Yi
ZHANG Huan-yun
ZHU Hong-bian
GAO Hao-yang
Abstract：Objective To identify factors associated with postoperative testicular atrophy and to develop and vali-date a prediction model for testicular atrophy after laparoscopic orchiopexy using LASSO-logistic regression.Methods A total of 457 pediatric patients who underwent laparoscopic orchiopexy between June 2020 and June 2024 were retrospec-tively enrolled.Patients were randomly divided into a training cohort(n=320)and a validation cohort(n=137).In the training cohort,patients were further classified into an atrophy group(n=49)and a non-atrophy group(n=271)ac-cording to postoperative outcomes.Clinical variables were collected.Least absolute shrinkage and selection operator(LASSO)regression was applied for variable selection and dimensionality reduction,followed by multivariate logistic re-gression to identify independent risk factors.A nomogram prediction model was constructed and evaluated using receiver operating characteristic(ROC)curves,calibration curves,Hosmer-Lemeshow goodness-of-fit tests,and decision curve analysis(DCA).Results LASSO-logistic regression identified age,testicular position,preoperative testicular volume ratio,associated anomalies,gestational age,and testicular blood supply as independent predictors of postoperative testicular atrophy.The area under the ROC curve(AUC)was 0.920(95％CI:0.882-0.959)in the training cohort and 0.941(95％CI:0.895-0.986)in the validation cohort.Calibration analysis demonstrated good agreement between pre-dicted and observed outcomes,with C-index values of 0.920(95％CI:0.881-0.959)and 0.909(95％CI:0.851-0.966)in the training and validation cohorts,respectively.The Hosmer-Lemeshow test showed good model fit in both cohorts(training:x2=8.436,P=0.392;validation:x2=2.995,P=0.935).Decision curve analysis indicated that the model provided a favorable net clinical benefit across a wide range of threshold probabilities.Conclusion Age,tes-ticular position,preoperative testicular volume ratio,associated anomalies,gestational age,and testicular blood supply are independent risk factors for testicular atrophy after laparoscopic orchiopexy.The LASSO-logistic regression-based no-mogram demonstrates good predictive performance and clinical utility,and may assist clinicians in perioperative risk strati-fication and decision-making.
Keywords：LASSO-logistic regressionlaparoscopetesticular descent fixation surgerytesticular atrophyprediction model
Publication Date：2026-01-15
Online Publishing Date：2026-03-04(First online date of this platform, not the publication date of the document)
Pages：7( 122-128 )