Identification of Perioperative Risk Factors for Early Sacral Nerve Stimulator Explantation: A Single-Center Retrospective Cohort Study

Abstract

Background: Sacral nerve stimulators (SNSs) can be an effective treatment for urinary incontinence. However, with a failure rate of up to 50%, an explantation rate of up to 16%, and a cost of ~USD 10,000 per implant, identification of patients at high risk for explantation is necessary to improve patient satisfaction and reduce the economic burden on the healthcare system. The objective of this retrospective cohort study was to determine predictors of SNS explantation within the first two years of device placement. Methods: The MOVER database was queried for patients with a SNS and at least two years of follow-up (n = 54). Multivariate logistic regression was performed to assess risk factors for explantation. Factor optimization was used to eliminate factors with limited predictive value. Results: The model displayed excellent performance with an AUC of 0.93 (95% CI: 0.78-1.00) and an f1-score of 0.81. Female sex (OR: 3.75; CI: 3.71-3.79), malignancy (OR: 3.14; CI: 3.10-3.18), ASA score (OR: 2.53; CI: 2.50-2.57), peripheral neuropathy (OR: 2.04: CI: 2.01-2.07), alcohol use (OR: 1.98; CI: 1.96-2.01), and length of stay (OR: 1.47; CI: 1.45-1.49) displayed statistically significant increased risk of explantation. Atrial fibrillation (OR: 0.36; CI: 0.35-0.36) and chronic kidney disease (OR: 0.54; CI: 0.53-0.54) were included in the model but conferred decreased risk of explantation. Conclusions: Patient ASA score and a medical history of malignancy, peripheral neuropathy, and alcohol use are possible novel risk factors for SNS explantation.

Keywords: chronic pain management; explantation surgery; sacral nerve stimulator; surgical indication; urinary incontinence.

Figure 1

Flowchart demonstrating the sampling process. The MOVER database contained 58,799 unique patient records, from which we identified 126 unique patients with a neuraxial procedure and at least 2 years of follow-up. Of these 126 patients, 54 had a sacral nerve stimulator. SCS: spinal cord stimulator; PNS: peripheral nerve stimulator.

Figure 2

Recursive feature elimination. The logistic regression algorithm was instructed to loop through, removing the least predictive feature with each iteration, until the optimal number of features was identified based upon the area under the receiver operating characteristic curve (AUC-ROC). The blue line represents the AUC-ROC value at each respective number of variables. Eight features resulted in the optimal AUC-ROC of 0.93. The red-dotted line represents the Bonferroni threshold for statistical significance.

Figure 3

Calibration curve providing a visual assessment of the logistic regression model performance. The grey dotted line represents a perfectly calibrated model. The blue solid line represents the model’s performance. The model displayed robust performance with an AUC: 0.93.

Figure 4

Bar graph providing a visual representation of the bootstrap validation. The model was repeated 100 times, with the bars representing the frequency of each AUC-ROC value. The red-dotted line represents the mean AUC-ROC and the light blue line represents the line of best fit. The model displayed an average AUC-ROC of 0.93, with a 95% confidence interval of 0.78 to 1.00.

Figure 5

Forest plot demonstrating female sex, malignancy, higher ASA score, peripheral neuropathy, alcohol use, and length of stay following implant as predictive of increased risk of SNS explantation. Atrial fibrillation and chronic kidney disease were predictive of decreased risk. The dot represents the odds ratio, with the brackets indicating the 95% confidence interval. The red dotted line represents an odds ratio of 1.0.