The Prediction of Recurrence of Lumbar Disc Herniation at L5-S1 through Machine Learning Based on Endoscopic Discectomy via the Interlaminar Approach

Jul 6, 2026

Upload by Eden

This study developed machine learning models to predict recurrent lumbar disc herniation (rLDH) at the L5-S1 level after percutaneous endoscopic interlaminar discectomy (PEID), a minimally invasive treatment for L5-S1 disc herniation. Data from 309 patients treated from January 2020 to June 2024 with at least 6 months follow-up were analyzed using clinical records, preoperative imaging, and VAS scores. LASSO identified key predictors and six models were trained (SVM, DT, ADA, LGBM, RF, XGB). RF and XGB performed best; 10.7% developed rLDH, defined by ≥60% VAS reduction followed by symptom recurrence with imaging confirmation. Key risk factors included BMI, PDHI, spinal canal stenosis, disease duration, numbness or weakness, Modic changes, herniation type, and diabetes.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages19

Reading Time48 min

Abstract

Study Aim and Design

Dataset and Outcome Definition

Feature Selection and Model Development

Key Predictors and Model Performance

Clinical Implications

Medicine DATE PUBLISHED July 11, 2025 DOI 10.3791/68550 [URL](URL jove.com/t/68550)[ ](URL jove.com/t/68550)[jove.com/t/68550](URL jove.com/t/68550) The Prediction of Recurrence of Lumbar Disc Herniation at L5-S1 through Machine Learning Based on Endoscopic Discectomy via the Interlaminar Approach Jinyu Chen1,2, Yanyan Fan3, Peng Liu1,4, Zhiming Cui1,4, Jiajia Chen1,4 1Department of Spine Surgery, Affiliated Hospital 2 of Nantong University2Nantong Clinical Medical College of Kangda College of Nanjing Medical University3Nantong Hospital to Nanjing University of Chinese Medicine4Research Institute for Spine and Spinal Cord Disease of Nantong University Corresponding Authors : Zhiming Cui <[czmspine@ntu.edu.cn](czmspine@ntu.edu.cn)>, Jiajia Chen <[ntspine@ntu.edu.cn](ntspine@ntu.edu.cn)> Citation Chen, J., Fan, Y., Liu, P., Cui, Z., Chen, J. The Prediction of Recurrence of Lumbar Disc Herniation at L5-S1 through Machine Learning Based on Endoscopic Discectomy via the Interlaminar Approach. J. Vis. Exp. (221), e68550, doi:10 .3791/68550 . (2025) . Abstract This study aimed to develop machine learning (ML) models to predict the L5-S1 level recurrent lumbar disc herniation (rLDH) after percutaneous endoscopic interlaminar discectomy (PEID), a minimally invasive treatment for L5-S1 lumbar disc herniation. Data from 309 patients who underwent single-level L5-S1 PEID between January 2020 and June 2024, with at least 6 months of follow-up, were analyzed. Clinical records, preoperative imaging, and visual analog scale (VAS) scores were used. LASSO regression identified key predictors, and six ML models were built: support vector machine (SVM), decision tree (DT), adaptive boosting (ADA), light gradient boosting machine (LGBM), random forest (RF), and extreme gradient boosting (XGB) . Among the patients, 10.7% experienced rLDH, defined as ≥60% VAS reduction followed by symptom recurrence and imaging confirmation. Key predictors included Body Mass Index (BMI), posterior disc height index (PDHI), spinal canal stenosis, disease duration, numbness or weakness, Modic changes, herniation type, and diabetes. The RF and XGB models performed best. Higher BMI, Higher PDHI, spinal canal stenosis, disease duration over six months, Modic changes, non-contained herniation, and diabetes increased rLDH risk. Variable importance was ranked for both models. Predicting rLDH preoperatively can enhance decision-making and reduce recurrence risk after PEID, with ML models improving accuracy and identifying critical risk factors. Introduction Percutaneous endoscopic lumbar discectomy (PELD) encompasses various techniques, such as percutaneous endoscopic transforaminal discectomy (PETD) and percutaneous endoscopic interlaminar discectomy (PEID), with the choice of surgical approach depending on the lesion location and individual anatomical characteristics of the patient1. Recurrent lumbar disc herniation (rLDH) is one of the most common reasons for reoperation following PELD, with an incidence ranging from 0% to 12. 5%2,3 . As a minimally invasive technique, PEID has been widely applied in the treatment of lumbar conditions such as L5-S1 level disc herniation. Its advantages, including minimal trauma, short hospital stays, and rapid postoperative recovery, have made it highly favored by both clinicians and patients4. However, despite the significant benefits of endoscopic techniques in reducing surgical trauma and promoting quick recovery, some patients still face the issue of recurrent disc herniation post-surgery5. This PDF is WCAG 2.2 compliant Copyright © 2025, Journal of Visualized Experiments [jove.com](jove.com) July 2025 • 221e68550 • Page 1 of 19 Journal of Visualized Experiments Chen et al. DOI 10.3791/68550 The recurrence of lumbar disc herniation is closely associated with multiple factors, including the degree of disc degeneration, posterior disc height, Modic changes (endplate inflammation), and areas in close co

FAQs

What surgical procedure and spinal level does the study focus on?

The study focuses on percutaneous endoscopic interlaminar discectomy (PEID) performed for lumbar disc herniation at the L5-S1 level.

How is recurrent lumbar disc herniation (rLDH) defined in the study?

rLDH is defined as achieving at least a 60% reduction in VAS followed by symptom recurrence, with imaging confirmation.

Which machine learning models performed best for predicting rLDH?

The random forest (RF) and extreme gradient boosting (XGB) models performed best among the six models evaluated.

What preoperative factors increased the risk of rLDH?

Higher BMI, higher posterior disc height index (PDHI), spinal canal stenosis, disease duration over six months, Modic changes, non-contained herniation, numbness or weakness, and diabetes were associated with increased rLDH risk.

Jul 6, 2026

Upload by Eden