Development and validation of a nomogram predicting the risk of recurrent lumbar disk herniation within 6 months after percutaneous endoscopic lumbar discectomy

To develop and validate a nomogram useful in predicting recurrent lumbar disk herniation (rLDH) within 6 months after percutaneous endoscopic lumbar discectomy (PELD). Information on patients’ lumbar disk herniation (LDH) between January 2018 and May 2019 in addition to 26 other features was collected from the authors’ hospital. The least absolute shrinkage and selection operator (LASSO) method was used to select the most important risk factors. Moreover, a nomogram was used to build a prediction model using the risk factors selected from LASSO regression. The concordance index (C-index), the receiver operating characteristic (ROC) curve, and calibration curve were used to assess the performance of the model. Finally, clinical usefulness of the nomogram was analyzed using the decision curve and bootstrapping used for internal validation. Totally, 352 LDH patients were included into this study. Thirty-two patients had recurrence within 6 months while 320 showed no recurrence. Four potential factors, the course of disease, Pfirrmann grade, Modic change, and migration grade, were selected according to the LASSO regression model. Additionally, the C-index of the prediction nomogram was 0.813 (95% CI, 0.726-0.900) and the area under receiver operating characteristic curve (AUC) value was 0.798 while the interval bootstrapping validation C-index was 0.743. Hence, the nomogram might be a good predictive model. Each variable, the course of disease, Pfirrmann grade, Modic change, and migration grade in the nomogram had a quantitatively corresponding risk score, which can be used in predicting the overall recurrence rate of rLDH within 6 months.