Spondylodiscitis is a serious spinal infection that can cause spinal instability, neurologic deficits, and paralysis. Although endoscopic procedures are becoming increasingly common, their role in spondylodiscitis management remains undefined. In this systematic review, PubMed, Embase, and MEDLINE were searched for studies published from January 1950 to March 2024 on percutaneous endoscopic debridement and drainage (PEDD) surgery for spondylodiscitis. The inclusion criteria included clinical trials or case series of spondylodiscitis patients treated with endoscopy. Primary outcomes included culture yield, complications, reoperations, treatment success rates, and pain scores. Our review included 40 studies that assessed 667 patients. Most studies presented low-level evidence, consisting of case reports (40.0%) and case series (60.0%). Endoscopic techniques demonstrated a positive culture yield of 67.3%, with an overall complication rate of 7.8% (95% confidence interval [CI], 5.35%–10.47%) and a reoperation rate of 13.1% (95% CI, 10.08%–16.31%). There were no complications related to cerebrospinal fluid leaks or meningitis. The medical treatment success rate was higher in patients who underwent concurrent instrumentation than in those who received endoscopic debridement alone (96.4% vs. 85.9%, p=0.003). Thirteen studies presented patient-reported pain outcomes, and all cohorts showed improvements. This review suggests that PEDD shows promise as a safe and effective adjunctive treatment for spondylodiscitis, offering low complication rates and successful treatment. PEDD may play a role within a multidisciplinary treatment approach. Future clinical trials are needed to determine whether early PEDD can improve the overall success of medical therapy and reduce the need for more extensive debridement and fusion surgery.

Methods: The American College of Surgeons’ National Surgical Quality Improvement Program database was used to identify patients who underwent ACC. Prolonged LOS, non-home discharges, and major complications were assessed as the outcomes of interest. ML models were developed with the TabPFN algorithm and integrated into an open-access website to predict these outcomes. Results: The models for predicting prolonged LOS, non-home discharges, and major complications demonstrated mean areas under the receiver operating characteristic curve (AUROC) of 0.802, 0.816, and 0.702, respectively. These findings highlight the discriminatory capacities of the models: fair (AUROC >0.7) for differentiating patients with major complications from those without, and good (AUROC >0.8) for distinguishing between those with and without prolonged LOS and non-home discharges. According to the SHapley Additive Explanations analysis, single- versus multiple-level surgery, age, body mass index, preoperative hematocrit, and American Society of Anesthesiologists physical status repetitively emerged as the most important variables for each outcome. Conclusions This study has considerably enhanced the prediction of postoperative results after ACC surgery by implementing advanced ML techniques. A major contribution is the creation of an accessible web application, highlighting the practical value of the developed models. Our findings imply that ML can serve as an invaluable supplementary tool to stratify patient risk for this procedure and can predict diverse postoperative adverse outcomes.