Machine Learning Predicts Recurrent Lumbar Disc Herniation Following Percutaneous Endoscopic Lumbar Discectomy

Abstract

Study Design Retrospective study. Objectives To develop machine learning (ML) models to predict recurrent lumbar disc herniation (rLDH) following percutaneous endoscopic lumbar discectomy (PELD). Methods We retrospectively analyzed 1159 patients who had undergone single-level PELD for lumbar disc herniation (LDH) between July 2014 to December 2019 at our institution. Various preoperative imaging variables and demographic metrics were brought in analysis. Student’s t test and Chi-squared test were applied for univariate analysis, which were feature selection for ML models. We established ML models to predict rLDH: Artificial neural networks (ANN), Extreme Gradient Boost classifier (XGBoost), KNeighborsClassifier (KNN), Decision tree classifier (Decision Tree), Random forest classifier (Random Forest), and support vector classifier (SVC). Results A total 130 patients (11.22%) were diagnosed as rLDH in 1159 patients. Recurrence occurred within 10.25 ± 11.05 months. Body mass index (BMI) ( P = .027), facet orientation (FO) ( P < .001), herniation type ( P = .012), Modic changes ( P = .004), and disc calcification ( P = .013) are significant factors in univariate analysis ( P < .05). Extreme Gradient Boost classifier, Random Forest, ANN showed fine area under the curve, .9315, .9220, and .8814 respectively. Conclusion We developed a deep learning and 2 ensemble models with fine performance in prediction of rLDH following PELD. Predicting re-herniation before surgery has the potential to optimize decision-making and meaningfully decrease the rates of rLDH following PELD. Our ML model identified higher BMI, lower FO, Modic changes, disc calcification in a non-protrusive region, and herniation type (noncontained herniation) as significant features for predicting rLDH.

Does Immediate Postoperative Early Ambulation Affect Clinical Results of Full‐Endoscopic Lumbar Discectomy? A Historical Control Study of Daytime Operation with a 8‐Hour Hospital Stay versus Inpatient Operation

“…There was no statistically significant difference between two groups. According to the previous studies, higher BMI, Modic changes and history of lumbar surgery were associated with a higher risk of recurrent herniation 21,22 . In our study, a total of 13 patients underwent reoperation.…”

“…According to the previous studies, higher BMI, Modic changes and history of lumbar surgery were associated with a higher risk of recurrent herniation. 21,22 In our study, a total of 13 patients underwent reoperation. of which four patients (30.8%) were obese (30.8%), six patients (46.2%) had Modic changes in their MRI scans.…”

Associations of recurrent lumbar disc herniation after percutaneous endoscopic lumbar discectomy with age, body mass index, modic change, disc degeneration and sacral slope: A quantitative review

“…A total of 3 studies ( 23 , 26 , 27 ) reported the association between sacral slope angle and rLDH, and there was heterogeneity among these three studies ( I 2 =86%). Meta-analysis showed that a larger sacral slope angle was a risk factor for rLDH after PELD (WMD=3.48, 95% CI: 0.53 to 6.42), with a statistically significant difference (P=0.02).…”

Massage ameliorates lumbar disc herniation-related radicular pain in rats by suppressing TLR4/NLRP3 inflammasome signaling transduction

“…Percutaneous endoscopic lumbar discectomy is a commonly used minimally invasive therapeutic strategy for LDH due to its advantages in several aspects such as less soft tissue injury, shorter operation time, and faster recovery. 5 Nonetheless, the incidence of surgery-related complications is 15–30%, and the risk of recurrent LDH after surgery is reported to be 2–25%. 6 Clinically, conservative approaches are frequently employed as the first choice for LDH treatment and have achieved certain favorable outcomes.…”