BACKGROUND Recurrence of lumbar disc herniation (LDH) is an adverse event after percutaneous endoscopic transforaminal discectomy (PETD). Accurate prediction of the risk of recurrent LDH (rLDH) after surgery remains a major challenge for spine surgeons. OBJECTIVES To develop and validate a prognostic model based on risk factors for rLDH after PETD. STUDY DESIGN Retrospective study. SETTING Inpatient surgery center. METHODS Clinical data were retrospectively collected from 645 patients with LDH who underwent PETD at the Affiliated Hospital of Xuzhou Medical University from January 1, 2017 to January 1, 2021. Predictors significantly associated with rLBH were screened according to least absolute shrinkage and selection operator (LASSO) regression, and a prognostic model was established, followed by internal model validation using the enhanced bootstrap method. The performance of the model was assessed using receiver operating characteristic (ROC) curves and calibration curves. Finally, the clinical usefulness of the model was analyzed using decision curve analysis (DCA) and clinical impact curves (CICs). RESULTS Among the 645 patients included in this study, 56 experienced recurrence of LDH after PETD (8.7%). Seven factors significantly associated with rLDH were selected by LASSO regression, including age, type of herniation, level of herniation, Modic changes, Pfirrmann classification, smoking, and history of high-intensity physical work. The bias-corrected curve of the model fit well with the apparent curve, and the area under the ROC curve was 0.822 (95% confidence interval, 0.76-0.88). The DCA and CIC confirmed that the prognostic model had good clinical utility. LIMITATIONS This is a single-center study, and we used internal validation only. CONCLUSIONS The prognostic model developed in this study had excellent comprehensive performance and could well predict the risk of rLDH after PETD. This model could be used to identify patients at high risk for rLDH at an early stage to individualize the patient's treatment modality and postoperative rehabilitation plan.

中文翻译：

---

开发和验证经皮内窥镜经椎间孔切除术后复发性腰椎间盘突出风险的预后模型。

背景技术腰椎间盘突出症 (LDH) 的复发是经皮内窥镜经椎间孔椎间孔切除术 (PETD) 后的一种不良事件。准确预测手术后复发性 LDH (rLDH) 的风险仍然是脊柱外科医生面临的主要挑战。目的 开发和验证基于 PETD 后 rLDH 危险因素的预后模型。研究设计回顾性研究。设置住院手术中心。方法 回顾性收集徐州医科大学附属医院2017年1月1日至2021年1月1日接受PETD检查的645例LDH患者的临床资料，根据最小绝对收缩和选择算子（LASSO）筛选与rLBH显着相关的预测因子。 )回归，并建立了预后模型，随后使用增强的引导程序方法进行内部模型验证。使用受试者工作特征 (ROC) 曲线和校准曲线评估模型的性能。最后，使用决策曲线分析 (DCA) 和临床影响曲线 (CIC) 分析了该模型的临床实用性。结果 在本研究纳入的 645 名患者中，56 名患者在 PETD 后出现 LDH 复发 (8.7%)。通过 LASSO 回归筛选出与 rLDH 显着相关的 7 个因素，包括年龄、突出类型、突出程度、Modic 变化、Pfirrmann 分类、吸烟和高强度体力劳动史。模型的偏差校正曲线与表观曲线吻合良好，ROC曲线下面积为0.822（95%置信区间，0.76-0.88）。DCA 和 CIC 确认预后模型具有良好的临床实用性。局限性 这是一项单中心研究，我们仅使用内部验证。结论 本研究建立的预后模型具有良好的综合性能，能够很好地预测PETD术后rLDH的发生风险。该模型可用于早期识别 rLDH 高风险患者，以个性化患者的治疗方式和术后康复计划。