Development and Validation of a Nomogram Predicting Postoperative Recurrent Lumbar Disc Herniation Based on Activity Factors.

Purpose: To develop an individualized predictive model for postoperative recurrent lumbar disc herniation (PRLDH) in patients undergoing percutaneous endoscopic transforaminal discectomy (PETD) by considering postoperative activity factors. Patients and Methods: Retrospectively collected data from 612 LDH patients who underwent PETD in our institution from January 2017 to June 2023. They were divided into a training group (429 cases) and a validation group (183 cases). Lasso regression (Model 1) and random forest (Model 2) were applied for variable selection in the training group. The two models were compared in terms of discrimination (the area under curve, AUC), calibration (calibration curve), and clinical utility (decision curve analysis, DCA). Akaike information criterion (AIC) was used for model comparison, and internal validation employed 1000 times Bootstrap + 10-fold cross-validation. Finally, a Nomogram was constructed to display the results and uploaded to the web version. Results: Among 612 treated LDH patients, 66 (10.78%) developed PRLDH. Model 1, superior in AUC, calibration, DCA, and AIC over Model 2, was chosen as the predictive model. Logistic regression in the training group identified BMI, smoking, activity level score, time to first ambulation, diabetes, Modic change, and Pfirrmann grade as independent predictors of PRLDH. Model 1 exhibited a training group AUC of 0.813 (95% CI 0.753– 0.872) and a validation group AUC of 0.868 (95% CI 0.773– 0.962). At a Youden index of 0.50, sensitivity was 0.73, specificity was 0.77. Internal validation (1000 times Bootstrap + 10-fold cross-validation) for the training group showed accuracy of 0.889, kappa consistency of 0.112, and AUC of 0.757. The Hosmer-Lemeshow goodness-of-fit tests indicated good discriminative ability for Model 1 in both the training (χ²=2.895, P=0.941) and validation groups (χ²=8.197, P=0.414). The DCA and Nomogram are accessible at https://sofarnomogram.shinyapps.io/PRLDHNom/. Conclusion: The Nomogram predictive model, developed based on postoperative activity factors in this study, demonstrates excellent predictive capability, facilitating risk assessment for the occurrence of PRLDH after PETD. [ABSTRACT FROM AUTHOR]