Prediction Model of Recurrence in Patients with Lumbar Disc Herniation after Unilateral Biportal Endoscopic Spinal Surgery

Jul 6, 2026

Upload by Rowan

Study focuses on postoperative recurrence in patients with single-segment lumbar disc herniation after unilateral biportal endoscopic (UBE) spinal surgery, where recurrence risk factors remain incompletely understood. A retrospective cohort of 271 patients underwent data-driven risk modeling. LASSO regression screened features and an XGBoost model predicted recurrence, evaluated using ROC, calibration, decision-curve analysis, and classification metrics. SHAP interpretation ranked key variables including protrusion width base, bone removal range, and Modic change. Larger WPB and extensive BRR with preoperative Modic changes correspond to higher recurrence risk, while hyperlipidemia shows a negative correlation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

Abstract

Background and Aims

Study Design and Methods

Results and Key Findings

Conclusions and Clinical Relevance

European Spine Journal (2025) 34:3876–3887 [https://doi.org/10.1007/s00586-025-09032-3](https://doi.org/10.1007/s00586-025-09032-3) RESEARCH Prediction model of recurrence in patients with lumbar disc herniation after unilateral biportal endoscopy spinal surgery-XGBoost machine learning model can be interpreted based on SHAP Yi Rong1 · Hao Yu1 · Zhen Hua1 · Jian-feng Chen1 · Jian-wei Wang1 Received: 11 October 2024 / Revised: 6 January 2025 / Accepted: 2 June 2025 / Published online: 7 July 2025 © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025 Abstract Background Patients with single-segment lumbar disc herniation(LDH) who have undergone unilateral biportal endoscopic (UBE) spinal surgery face the risk of postoperative recurrence. The potential factors for recurrence of lumbar disc herniation(rLDH) are not fully understood. Aims This study aimed to investigate the risk factors for rLDH after UBE spinal surgery and establish a risk factor prediction model using machine learning to predict the recurrence rate. Study design This study used LASSO regression for feature screening, XGBoost for machine learning model construction, ROC curve analysis, calibration curve analysis, clinical decision curve analysis, specificity, sensitivity, accuracy, and F1 score to evaluate the model’s performance. Results The clinical data of 271 patients with LDH were retrospectively analyzed. All patients have undergone UBE spinal surgery. 47 patients relapsed, with a recurrence rate of 17.3%. The XGBoost model predicted a higherAUC for rLDH (training: 0.927, 95%CI: 0.882–0.958; Test: 0.866, 95%CI: 0.760–0.937) . The importance of SHAP variables in the model in descending order is:“Width of Protrusion Base(WPB),“” Bone Removal Range(BRR),“"Modic Change,” " Type of LDH,”“Middle Vertebral space Height(MVH),”“Hyperlipidemia.” Conclusion The large WPB、high WPB、 extensive BRR, and preoperative Modic Changes are more likely to develop rLDH. Hyperlipidemia and prolapsed disc herniation are negatively correlated with rLDH. Relevance to clinical practice Improve the ability to predict the rLDH after UBE spinal surgery. This will enable clinicians to intervene early and improve postoperative outcomes. Keywords Lumbar disc herniation · Unilateral biportal endoscopic spinal surgery · Recurrence · Machine learning · SHAP | Yi Rong and Hao Yu contributed equally to this work. | | --- | | Hao Yu is a co-first author of this paper. | 􀀍 Hao Yu[yuhao495422190@qq.com](yuhao495422190@qq.com) 􀀍 Jian-wei Wang [wxzy006@njucm.edu.cn](wxzy006@njucm.edu.cn) Yi Rong [260714388@qq.com](260714388@qq.com) Zhen Hua [wxzy044@njucm.edu.cn](wxzy044@njucm.edu.cn) [Jian-feng Chen](Jian-feng Chen) [weileweilei@126.com](weileweilei@126.com) 1 Wuxi Affiliated Hospital of Nanjing University of Chinese Medicine, Wuxi, China Background Lumbar disc herniation (LDH) is a common clinical disease that can cause pain and numbness in the lower back and legs, seriously affecting patients’ daily lives [1] . Unilateral biportal endoscopic (UBE) spinal surgery has been widely used in clinical practice because of its advantages such as little trauma, clear operating field, less bleeding, low risk of nerve injury, low infection rate and quick recovery [2] . However, some patients are still at risk of recurrence of lumbar disc herniation (rLDH) . 5% ~ 18% of the patients with LDH may relapse after initial surgery [3] . Recurrence may worsen lower back pain and lower limb pain, and some patients with severe symptoms may need a second surgery [4] . Worse still, due to fibrosis and scarring in the operative area caused by the primary surgery, it is often challenging to perform a second revision surgery in a minimally invasive manner. In addition, this will also increase the physical and mental pressure and economic burden of patients, resulting in a particular waste of medical resources. Therefore, prev

FAQs

What patient group and clinical problem does the study address?

The study targets patients with single-segment lumbar disc herniation who underwent unilateral biportal endoscopic spinal surgery, aiming to predict postoperative recurrence risk.

How was the prediction model constructed and evaluated?

Features were screened with LASSO regression and an XGBoost model was built, with performance assessed via ROC analysis, calibration curves, clinical decision curve analysis, and metrics such as sensitivity, specificity, accuracy, and F1 score.

Which factors were most important for recurrence according to SHAP?

SHAP variable importance ranked width of protrusion base (WPB) first, followed by bone removal range (BRR), Modic change, type of LDH, middle vertebral space height (MVH), and hyperlipidemia.

What conclusions link preoperative variables to recurrence risk?

Large WPB, high WPB, extensive BRR, and preoperative Modic changes are associated with a greater likelihood of recurrent lumbar disc herniation, while hyperlipidemia shows a negative correlation.

Jul 6, 2026

Upload by Rowan