RESUMO
INTRODUCTION: Technological advancements in implant design and surgical technique have focused on diminishing complications and optimizing performance of reverse shoulder arthroplasty (RSA). Despite this, there remains a paucity of literature correlating prosthetic features and clinical outcomes. This investigation utilized a machine learning approach to evaluate the effect of select implant design features and patient-related factors on surgical complications after RSA. METHODS: Over a 16-year period (2004 - 2020), all primary RSA performed at a single institution for elective and traumatic indications with a minimum follow-up of 2 years were identified. Parameters related to implant design evaluated in this study included inlay vs onlay humeral bearing design, glenoid lateralization (medialized or lateralized), humeral lateralization (medialized, minimally lateralized, or lateralized), global lateralization (medialized, minimally lateralized, lateralized, highly lateralized, or very highly lateralized), stem to metallic bearing neck shaft angle (NSA), and polyethylene NSA. Machine learning models predicting surgical complications were constructed for each patient and Shapley additive explanation (SHAP) values were calculated to quantify feature importance. RESULTS: A total of 3,837 RSAs were identified, of which 472 (12.3%) experienced a surgical complication. Those experiencing a surgical complication were more likely to be current smokers (Odds ratio [OR] = 1.71; P = .003), have prior surgery (OR = 1.60; P < .001), have an underlying diagnosis of sequalae of instability (OR = 4.59; P < .001) or non-union (OR = 3.09; P < .001), and required longer OR times (98 vs. 86 minutes; P < .001). Notable implant design features at an increased odds for complications included an inlay humeral component (OR = 1.67; P < .001), medialized glenoid (OR = 1.43; P = .001), medialized humerus (OR = 1.48; P = .004), a minimally lateralized global construct (OR = 1.51; P < .001), and glenohumeral constructs consisting of a medialized glenoid and minimally lateralized humerus (OR = 1.59; P < .001), and a lateralized glenoid and medialized humerus (OR = 2.68; P < .001). Based on patient- and implant-specific features, the machine learning model predicted complications after RSA with an area under the receiver operating characteristic curve (AUC ROC) of 0.61. CONCLUSIONS: This study demonstrated that patient-specific risk factors had a more substantial effect than implant design configurations on the predictive ability of a machine learning model on surgical complications after RSA. However, certain implant features appeared to be associated with a higher odd of surgical complications.
RESUMO
BACKGROUND: In primary shoulder arthroplasty (SA), intravenous (IV) cefazolin has demonstrated lower rates of infectious complications when compared to IV vancomycin. However, previous analyses included SA cohorts with both complete and incomplete vancomycin administration. Therefore, it is currently unclear whether cefazolin still maintains a prophylactic advantage to vancomycin when it is appropriately indicated and sufficiently administered at the time of surgical incision. This study evaluated the comparative efficacy of cefazolin and complete vancomycin administration for surgical prophylaxis in primary shoulder arthroplasty with respect to infectious complications. METHODS: A retrospective cohort study was conducted utilizing a single institution total joint registry database, where all primary SA types (hemiarthroplasty, anatomic total shoulder arthroplasty, and reverse shoulder arthroplasty) performed between 2000 to 2019 for elective and trauma indications using IV cefazolin or complete vancomycin administration as the primary antibiotic prophylaxis were identified. Vancomycin was primarily indicated for patients with a severe self-reported penicillin or cephalosporin allergy and/or MRSA colonization. Complete administration was defined as at least 30 minutes of antibiotic infusion prior to incision. All included SA had at least 2 years of clinical follow-up. Multivariable Cox proportional hazard regression was used to evaluate all-cause infectious complications including survival free of prosthetic joint infection (PJI). RESULTS: The final cohort included 7177 primary SA, 6879 (95.8%) received IV cefazolin and 298 (4.2%) received complete vancomycin administration. Infectious complications occurred in 120 (1.7%) SA leading to 81 (1.1%) infectious reoperations. Of the infectious complications, 41 (0.6%) were superficial infections and 79 were (1.1%) PJIs. When categorized by administered antibiotics, there were no differences in rates of all infectious complications (1.6% vs. 2.3%; P = .352), superficial complications (0.5% vs. 1.3%; P = .071), PJI (1.1% vs. 1.0%; P = .874), or infectious reoperations (1.1% vs. 1.0%; P = .839). On multivariable analyses, complete vancomycin infusion demonstrated no difference in rates of infectious complications compared to cefazolin administration (hazard ratio [HR], 1.50 [95% confidence interval (CI), 0.70 to 3.25]; P = .297), even when other independent predictors of PJI (male sex, prior surgery, and Methicillin-resistant Staphylococcus aureus colonization) were considered. CONCLUSIONS: In comparison to cefazolin, complete administration of vancomycin (infusion to incision time greater than 30 minutes) as the primary prophylactic agent does not adversely increase the rates of infectious complications and PJI. Prophylaxis protocols should promote appropriate indications for the use of cefazolin or vancomycin, and when necessary, ensure complete administration of vancomycin to mitigate additional infectious risks after primary SA.