Search

Anatomic total shoulder arthroplasty (aTSA) is a successful and reproducible treatment for patients with painful glenohumeral arthritis. However, long-term outcomes using traditional onlay glenoid components have been tempered by glenoid loosening. Inset components have been proposed to minimize glenoid loosening by reducing edge-loading and opposite-edge lift-off forces with humeral translation. Successful short and long-term outcomes have been reported while using inset glenoid implants. The current study is the largest study presenting a minimum of two-year follow-up data following aTSA with an all-polyethylene inset glenoid component (Shoulder Innovations, Holland, MI).A dual center, retrospective review of patients undergoing aTSA using an Inset glenoid component by two fellowship-trained shoulder surgeons at two separate institutions from August, 2016 to August, 2019 was performed. Minimum follow up was two years. Range of motion (ROM), Visual Analog Pain Scores (VAS), Single Assessment Numeric Evaluation (SANE), and American Shoulder and Elbow Surgeons (ASES) scores were obtained. Radiographic outcomes, including central peg lucency and glenoid loosening, were assessed by three independent reviewers on the postoperative Grashey and axillary radiographs obtained at the final follow-up.Seventy-five shoulders were included for final analysis. The mean age of the entire cohort was 64 (±11.4) years. Twenty-one (28%) glenoids were type A1, 10 (13.3%) were type A2, 13 (17.3%) were type B1, 22 (29.3%) were type B2, six (8%) were type B3 and three (4%) were type D. At a minimum follow-up of 24 months (mean 28.7 months), a significant improvement in ROM in all planes was observed. Significant improvements in VAS (5.1 to 0.9, p0.001), SANE (39.5 to 91.2, p0.001) and ASES (43.7 to 86.6, p0.001) scores were observed. There were four (5.3%) cases of central peg lucency about the inset glenoid component and one (1.3%) cases of glenoid loosening. No revisions were performed for glenoid loosening.At a minimum of two years postoperatively, there were significant improvements in ROM and VAS, SANE, and ASES scores with very low rates of central peg lucency and glenoid loosening in patients undergoing aTSA with an inset glenoid component. Further work is needed to determine the long-term benefit of this novel implant.

Hypothesis/Purpose The objective is to develop and validate an artificial intelligence model, specifically an artificial neural network (ANN), to predict length of stay (LOS), discharge disposition, and inpatient charges for primary anatomic total (aTSA), reverse total (rTSA), and hemi- (HSA) shoulder arthroplasty to establish internal validity in predicting patient-specific value metrics. Methods Using data from the National Inpatient Sample between 2003 and 2014, 4 different ANN models to predict LOS, discharge disposition, and inpatient costs using 39 preoperative variables were developed based on diagnosis and arthroplasty type: primary chronic/degenerative aTSA, primary chronic/degenerative rTSA, primary traumatic/acute rTSA, and primary acute/traumatic HSA. Models were also combined into diagnosis type only. Outcome metrics included accuracy and area under the curve (AUC) for a receiver operating characteristic curve. Results A total of 111,147 patients undergoing primary shoulder replacement were included. The machine learning algorithm predicting the overall chronic/degenerative conditions model (aTSA, rTSA) achieved accuracies of 76.5%, 91.8%, and 73.1% for total cost, LOS, and disposition, respectively; AUCs were 0.75, 0.89, and 0.77 for total cost, LOS, and disposition, respectively. The overall acute/traumatic conditions model (rTSA, HSA) had accuracies of 70.3%, 79.1%, and 72.0% and AUCs of 0.72, 0.78, and 0.79 for total cost, LOS, and discharge disposition, respectively. Conclusion Our ANN demonstrated fair to good accuracy and reliability for predicting inpatient cost, LOS, and discharge disposition in shoulder arthroplasty for both chronic/degenerative and acute/traumatic conditions. Machine learning has the potential to preoperatively predict costs, LOS, and disposition using patient-specific data for expectation management between health care providers, patients, and payers.