The Prediction of Recurrence Lumbar Disc Herniation At L5-S1 Level Through Machine Learning Models Based on Endoscopic Discectomy Via the Interlaminar Approach

NCT06833099 | Completed DMC

• 1 other identifier: JiajiaChen
• Study Type: observational
• Target: 309
• Locations: 1 country
• Sites: 1

Brief Summary

What Was the Study About? This study focused on improving the care of patients with a specific type of back problem called lumbar disc herniation at the L5-S1 level. Doctors often treat this condition with a minimally invasive surgery known as percutaneous endoscopic interlaminar discectomy (PEID). However, sometimes the herniation (the damaged disc) can come back after surgery. The goal of this study was to develop computer models that help predict which patients might experience a recurrence of their herniated disc. Who Participated? The study reviewed the medical records of 309 patients who had undergone the PEID surgery. Out of these, 33 patients experienced a recurrence of their herniation, while 276 patients did not. What Did the Researchers Do? Data Collection: They gathered information from each patient before the surgery, including clinical details (like body weight and any health conditions such as diabetes) and imaging studies (like X-rays, CT scans, or MRIs) that show the condition of the spine. Identifying Key Risk Factors: Using a statistical method called LASSO regression, the researchers identified eight important factors that could influence whether the herniation might come back. These included factors such as body mass index (BMI), a measure related to disc height (posterior disc height index), signs of spinal canal narrowing, how long the patient had symptoms before surgery, and other health conditions. Developing Prediction Models: They then used several machine learning techniques (advanced computer methods that learn from data) to build prediction models. Two of the best-performing models were based on methods called Random Forest and Extreme Gradient Boosting (XGB). What Were the Main Findings? Key Predictors: Higher BMI and changes in the disc (as measured by the posterior disc height index) were found to be the strongest predictors of a herniation coming back after surgery. Other factors, like spinal canal narrowing and longer duration of symptoms before surgery, also played significant roles. Practical Implication: These models can help doctors identify which patients are at higher risk for recurrence. With this information, they can adjust treatment plans and follow-up care to better manage and potentially reduce the risk of the herniation coming back. Why Is This Important? For patients and their families, this study offers hope for more personalized and effective treatment plans, reducing the chances of needing additional surgeries in the future. For healthcare providers, the findings provide useful tools to improve decision-making before surgery, ensuring better long-term outcomes for patients with L5-S1 lumbar disc herniation. In summary, this research uses modern computer methods to predict the risk of recurrent disc herniation after a common minimally invasive back surgery, aiming to enhance patient care and improve surgical outcomes.

Conditions

Recurrent Lumbar Disc Herniation

Keywords

Machine Learning, Ensemble Learning

Outcome Measures

Primary Outcomes (1)

• Recurrence of Lumbar Disc Herniation (rLDH) Following Percutaneous Endoscopic Interlaminar Discectomy (PEID) at the L5-S1 Level

  The primary outcome measure will assess the recurrence of lumbar disc herniation (rLDH) in patients who have undergone percutaneous endoscopic interlaminar discectomy (PEID) at the L5-S1 level. The occurrence of rLDH will be evaluated based on clinical symptoms and imaging findings, including MRI or CT scans, within a specified follow-up period post-surgery. This measure aims to develop a predictive model to estimate the likelihood of recurrence of disc herniation following PEID at the L5-S1 level.

  The recurrence will be monitored and documented during follow-up visits at least 6 months

Study Arms (2)

Recurrent rLDH

: Patients who experienced recurrent lumbar disc herniation following L5-S1 PEID.

Diagnostic Test: VAS Point and Imaging Examination

Non-Recurrent rLDH

Patients who did not experience recurrent lumbar disc herniation following L5-S1 PEID.

Diagnostic Test: VAS Point and Imaging Examination

Interventions

VAS Point and Imaging Examination DIAGNOSTIC_TEST

This intervention uses a machine learning model to predict the risk of recurrent lumbar disc herniation (rLDH) in patients who have had percutaneous endoscopic interlaminar discectomy (PEID) at the L5-S1 level. The model combines clinical data (e.g., BMI, disease duration, diabetes) and imaging metrics (e.g., posterior disc height index, spinal canal stenosis) to create a personalized risk score, unlike traditional methods that rely on clinical judgment or imaging alone. Key Features: Data-Driven Approach: Developed using data from 309 patients for real-world relevance. Advanced Variable Selection: Identifies eight key predictors using LASSO regression. Multiple Machine Learning Techniques: Uses algorithms like support vector machine, random forest, and extreme gradient boosting. Optimized for Clinical Decision-Making: Assists surgeons in personalizing treatment plans to reduce recurrence risk.

Non-Recurrent rLDH; Recurrent rLDH

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Study Population Description: The study population consisted of 309 patients who underwent percutaneous endoscopic interlaminar discectomy (PEID) for L5-S1 lumbar disc herniation between January 2020 and June 2024 at Nantong First People's Hospital. All patients had at least 6 months of follow-up post-surgery. The study focused on identifying factors that predict recurrent lumbar disc herniation (rLDH) after the procedure.

You may qualify if:

• (C) Postoperative VAS scores decreased by ≥60%, followed by an increase, confirmed by imaging.
• (D) No other abnormalities detected in imaging. (E) Minimum follow-up period of 6 months.

You may not qualify if:

• (A) Presence of other pathological conditions causing lower back pain, such as disc infections, spinal tumors, metabolic bone disease, or osteoporosis. (B) History of prior lumbar disc or other spinal surgeries. (C) Poor imaging quality or incomplete examination data. (D) Patients lost to follow-up.

Sponsors & Collaborators

• Jinyu Chen: lead
• Nantong First People's Hospital: collaborator

Study Sites (1)

Nantong First People's Hospital

Nantong, Jiangsu, 226000, China

Location

Related Publications (20)

• Shi H, Zhu L, Jiang ZL, Wu XT. Radiological risk factors for recurrent lumbar disc herniation after percutaneous transforaminal endoscopic discectomy: a retrospective matched case-control study. Eur Spine J. 2021 Apr;30(4):886-892. doi: 10.1007/s00586-020-06674-3. Epub 2021 Jan 1.

  PMID: 33386474 BACKGROUND

• Yu C, Zhan X, Liu C, Liao S, Xu J, Liang T, Zhang Z, Chen J. Risk Factors for Recurrent L5-S1 Disc Herniation After Percutaneous Endoscopic Transforaminal Discectomy: A Retrospective Study. Med Sci Monit. 2020 Mar 25;26:e919888. doi: 10.12659/MSM.919888.

  PMID: 32210223 BACKGROUND

• Choi G, Lee SH, Raiturker PP, Lee S, Chae YS. Percutaneous endoscopic interlaminar discectomy for intracanalicular disc herniations at L5-S1 using a rigid working channel endoscope. Neurosurgery. 2006 Feb;58(1 Suppl):ONS59-68; discussion ONS59-68. doi: 10.1227/01.neu.0000192713.95921.4a.

  PMID: 16479630 BACKGROUND

• Siemionow K, An H, Masuda K, Andersson G, Cs-Szabo G. The effects of age, sex, ethnicity, and spinal level on the rate of intervertebral disc degeneration: a review of 1712 intervertebral discs. Spine (Phila Pa 1976). 2011 Aug 1;36(17):1333-9. doi: 10.1097/BRS.0b013e3181f2a177.

  PMID: 21217432 BACKGROUND

• Li Y, Wang B, Li H, Chang X, Wu Y, Hu Z, Liu C, Gao X, Zhang Y, Liu H, Li Y, Li C. Adjuvant surgical decision-making system for lumbar intervertebral disc herniation after percutaneous endoscopic lumber discectomy: a retrospective nonlinear multiple logistic regression prediction model based on a large sample. Spine J. 2021 Dec;21(12):2035-2048. doi: 10.1016/j.spinee.2021.07.012. Epub 2021 Jul 20.

  PMID: 34298160 BACKGROUND

• Jia M, Sheng Y, Chen G, Zhang W, Lin J, Lu S, Li F, Ying J, Teng H. Development and validation of a nomogram predicting the risk of recurrent lumbar disk herniation within 6 months after percutaneous endoscopic lumbar discectomy. J Orthop Surg Res. 2021 Apr 21;16(1):274. doi: 10.1186/s13018-021-02425-2.

  PMID: 33882995 BACKGROUND

• Han M, Liu L, Hu M, Liu G, Li P. Medical expert and machine learning analysis of lumbar disc herniation based on magnetic resonance imaging. Comput Methods Programs Biomed. 2022 Jan;213:106498. doi: 10.1016/j.cmpb.2021.106498. Epub 2021 Oct 29.

  PMID: 34758430 BACKGROUND

• Li R, Fu D, Han H, Zhan Z, Wu Y, Meng B. Comparative analysis of percutaneous endoscopic interlaminar discectomy for highly downward-migrated disc herniation. J Orthop Surg Res. 2023 Aug 14;18(1):602. doi: 10.1186/s13018-023-04090-z.

  PMID: 37580753 BACKGROUND

• Berg B, Gorosito MA, Fjeld O, Haugerud H, Storheim K, Solberg TK, Grotle M. Machine Learning Models for Predicting Disability and Pain Following Lumbar Disc Herniation Surgery. JAMA Netw Open. 2024 Feb 5;7(2):e2355024. doi: 10.1001/jamanetworkopen.2023.55024.

  PMID: 38324310 BACKGROUND

• Harada GK, Siyaji ZK, Mallow GM, Hornung AL, Hassan F, Basques BA, Mohammed HA, Sayari AJ, Samartzis D, An HS. Artificial intelligence predicts disk re-herniation following lumbar microdiscectomy: development of the "RAD" risk profile. Eur Spine J. 2021 Aug;30(8):2167-2175. doi: 10.1007/s00586-021-06866-5. Epub 2021 Jun 7.

  PMID: 34100112 BACKGROUND

• Wang H, Zhou Y, Li C, Liu J, Xiang L. Risk factors for failure of single-level percutaneous endoscopic lumbar discectomy. J Neurosurg Spine. 2015 Sep;23(3):320-5. doi: 10.3171/2014.10.SPINE1442. Epub 2015 Jun 12.

  PMID: 26068272 BACKGROUND

• Huang W, Han Z, Liu J, Yu L, Yu X. Risk Factors for Recurrent Lumbar Disc Herniation: A Systematic Review and Meta-Analysis. Medicine (Baltimore). 2016 Jan;95(2):e2378. doi: 10.1097/MD.0000000000002378.

  PMID: 26765413 BACKGROUND

• Li H, Deng W, Wei F, Zhang L, Chen F. Factors related to the postoperative recurrence of lumbar disc herniation treated by percutaneous transforaminal endoscopy: A meta-analysis. Front Surg. 2023 Jan 19;9:1049779. doi: 10.3389/fsurg.2022.1049779. eCollection 2022.

  PMID: 36743903 BACKGROUND

• Ren G, Liu L, Zhang P, Xie Z, Wang P, Zhang W, Wang H, Shen M, Deng L, Tao Y, Li X, Wang J, Wang Y, Wu X. Machine Learning Predicts Recurrent Lumbar Disc Herniation Following Percutaneous Endoscopic Lumbar Discectomy. Global Spine J. 2024 Jan;14(1):146-152. doi: 10.1177/21925682221097650. Epub 2022 May 2.

  PMID: 35499394 BACKGROUND

• Modic MT, Ross JS. Lumbar degenerative disk disease. Radiology. 2007 Oct;245(1):43-61. doi: 10.1148/radiol.2451051706.

  PMID: 17885180 BACKGROUND

• Ju CI, Lee SM. Complications and Management of Endoscopic Spinal Surgery. Neurospine. 2023 Mar;20(1):56-77. doi: 10.14245/ns.2346226.113. Epub 2023 Mar 31.

  PMID: 37016854 BACKGROUND

• Pan M, Li Q, Li S, Mao H, Meng B, Zhou F, Yang H. Percutaneous Endoscopic Lumbar Discectomy: Indications and Complications. Pain Physician. 2020 Jan;23(1):49-56.

  PMID: 32013278 BACKGROUND

• Yin S, Du H, Yang W, Duan C, Feng C, Tao H. Prevalence of Recurrent Herniation Following Percutaneous Endoscopic Lumbar Discectomy: A Meta-Analysis. Pain Physician. 2018 Jul;21(4):337-350.

  PMID: 30045591 BACKGROUND

• Cheng J, Wang H, Zheng W, Li C, Wang J, Zhang Z, Huang B, Zhou Y. Reoperation after lumbar disc surgery in two hundred and seven patients. Int Orthop. 2013 Aug;37(8):1511-7. doi: 10.1007/s00264-013-1925-2. Epub 2013 May 22.

  PMID: 23695881 BACKGROUND

• Chen Z, Wang X, Cui X, Zhang G, Xu J, Lian X. Transforaminal Versus Interlaminar Approach of Full-Endoscopic Lumbar Discectomy Under Local Anesthesia for L5/S1 Disc Herniation: A Randomized Controlled Trial. Pain Physician. 2022 Nov;25(8):E1191-E1198.

  PMID: 36375189 BACKGROUND

Biospecimen

Retention: SAMPLES WITHOUT DNA

Biospecimen Description This study is a retrospective analysis that primarily uses clinical data and preoperative imaging records. Therefore, no biospecimens, such as blood or tissue samples, are collected, retained, or analyzed in this study. All data will be handled in strict accordance with privacy protection regulations set by the hospital's ethics committee and will be used exclusively by the research team.

MeSH Terms

Conditions

Intervertebral Disc Displacement

Condition Hierarchy (Ancestors)

Spinal Diseases; Bone Diseases; Musculoskeletal Diseases; Hernia; Pathological Conditions, Anatomical; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: resident physician

Study Record Dates

• First Submitted: February 12, 2025
• First Posted: February 18, 2025
• Study Start: January 1, 2020
• Primary Completion: May 31, 2024
• Study Completion: November 1, 2024
• Last Updated: February 18, 2025

Record last verified: 2024-10

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)