Background: Glenoid component loosening remains a challenge in anatomic total shoulder arthroplasty (aTSA). The aims of this study were to evaluate complications, implant survival, and revision rates in patients with primary and secondary osteoarthritis (OA) undergoing stemless aTSA using the Arthrex Eclipse humeral implant with a cemented pegged all-polyethylene glenoid component and to identify risk factors leading to revision. Methods: Of 211 patients who underwent primary stemless aTSA (using the Eclipse humeral component with a cemented pegged all-polyethylene glenoid) with prospectively documented data in a local registry, 197 were evaluated, grouped by OA pathology (primary OA, 153 patients; secondary OA, 44 patients). Demographic and functional data (e.g., age, sex, shoulder function) and the cause of OA were documented preoperatively in both groups. Comparative analyses were conducted to assess complications and implant revisions between the study groups. In addition, various radiographic parameters (e.g., glenoid morphology, critical shoulder angle, lateral acromion index, implant sizing [humeral component overhang], radial matching of the humeral and glenoid components, glenohumeral distance, and medial glenoid cement penetration) were evaluated to explore their potential association with revision. A subset of these parameters was subsequently included in the multivariable Cox model on the basis of clinical relevance. Results: After a median postoperative period of 72 months, the overall revision rate was 51%. The reasons for revision were glenoid component loosening (85%), periprosthetic humeral fracture (9%), early rotator cuff failure (3%), and low-grade infection (3%). The median implant survival in patients with primary OA (95 months; 95% confidence interval [CI]: 84 to 108) was significantly longer than that in patients with secondary OA (71 months; 95% CI: 60 to 88; p = 0.027). Female patients had a significantly shorter time to revision than male patients (p = 0.016). There were no significant differences in complications or revision rates by OA pathology. Secondary OA, the presence of medial glenoid cement penetration, and an anterior overhang of the humeral component were associated with an increased risk of revision. Conclusions: Our findings indicate a high rate of glenoid component loosening as the primary cause of revision in patients with primary and secondary OA undergoing stemless aTSA with the Eclipse and a cemented pegged all-polyethylene glenoid component. This outcome emphasizes the need for careful consideration of implant design, patient selection criteria, and implant positioning and cementation in order to optimize implant survival. Level of Evidence: Therapeutic Level III . See Instructions for Authors for a complete description of levels of evidence.

Aims: Machine learning (ML) holds significant promise in optimizing various aspects of total shoulder arthroplasty (TSA), potentially improving patient outcomes and enhancing surgical decision-making. The aim of this systematic review was to identify ML algorithms and evaluate their effectiveness, including those for predicting clinical outcomes and those used in image analysis.Methods: We searched the PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases for studies applying ML algorithms in TSA. The analysis focused on dataset characteristics, relevant subspecialties, specific ML algorithms used, and their performance outcomes.Results: Following the final screening process, 25 articles satisfied the eligibility criteria for our review. Of these, 60% focused on tabular data while the remaining 40% analyzed image data. Among them, 16 studies were dedicated to developing new models and nine used transfer learning to leverage existing pretrained models. Additionally, three of these models underwent external validation to confirm their reliability and effectiveness.Conclusion: ML algorithms used in TSA demonstrated fair to good performance, as evidenced by the reported metrics. Integrating these models into daily clinical practice could revolutionize TSA, enhancing both surgical precision and patient outcome predictions. Despite their potential, the lack of transparency and generalizability in many current models poses a significant challenge, limiting their clinical utility. Future research should prioritize addressing these limitations to truly propel the field forward and maximize the benefits of ML in enhancing patient care.Cite this article: Bone Jt Open 2025;6(2):126–134.

Most research on shoulder arthroplasty has predominantly concentrated on optimizing treatment to enhance shoulder function with comparatively less emphasis on postsurgical pain. Yet, pain is an equally significant or even more important outcome in orthopedic surgery. The aim of this study was to develop a deep learning algorithm for predicting postsurgical pain after reverse total shoulder arthroplasty (rTSA). Clinical data of rTSA patients were extracted from a local shoulder arthroplasty registry and used to build an artificial neural network, which was set up with input from 34 preoperative features including demographics, disease-related information, clinical, and self-report assessments. The target variable was a binary classification derived from a numeric pain rating scale (0-10): if the pain scored 3 or higher, it was classified as positive; if the pain score was 2 or lower, it was classified as negative. The model was internally validated with a test dataset that was comprised of 20% of the whole dataset. Model performance was evaluated on the testset using the metrics accuracy, precision, recall, and f1-score. Our model, including data from 1707 patients (pain: n = 705, no pain: n = 1002), achieved a 63% accuracy rate in predicting postsurgical pain 2 years following rTSA. Identification of the most critical factors indicating low postsurgical pain was performed by SHapley Additive exPlanations analysis, which included a low American Society of Anesthesiologists physical status classification, a low Quick Disability of the Arm, Shoulder and Hand questionnaire score, private insurance status, primary OA, being admitted due to illness as opposed to due to an accident, low pain levels, occasional alcohol consumption, low shoulder pain and disability index and functional scores. We successfully developed an artificial neural network to predict postsurgical pain after rTSA. Additional efforts are still required to refine the models’ performance, such as including further parameters predictive of pain and considering other machine learning algorithms. In a clinical setting, the implementation of such a prediction model could optimize surgical indications and help manage patient expectations more effectively.

Background: The management of irreparable posterosuperior rotator cuff tears with an isolated loss of external rotation presents significant challenges. Latissimus dorsi tendon transfer in conjunction with medialized reverse total shoulder arthroplasty has been employed to rectify external rotation deficits; however, lateralized RTSA designs may yield similar outcomes with a reduced incidence of complications. The objective of this study was to compare the clinical outcomes of lateralized reverse total shoulder arthroplasty without latissimus dorsi tendon transfer against medialized RTSA with LDT in patients with ILER and a positive external rotation lag sign. Methods: This retrospective cohort study involved 34 patients diagnosed with CTA and severe external rotation deficiency, characterized by a positive ER lag sign and 0° active ER. The patients were treated with either lateralized reverse total shoulder arthroplasty (n = 21) or medialized RTSA with LDT (n = 13). Outcomes evaluated preoperatively and at the 24-month follow-up comprised range of motion, ER lag sign, Constant–Murley Score, SPADI, and radiographic offset parameters. Statistical analyses were adjusted for age, sex, and baseline values. Results: At follow-up, 70% of patients undergoing lateralized RTSA exhibited resolution of ER lag, compared to 23% in the LDT group (p < 0.05). Active external rotation improvement was more significant in the LDT group (34.6° compared to 18.5°, p < 0.05). However, both groups exhibited comparable final external rotation and functional scores (CMS: 63 ± 9 vs. 63 ± 16; SPADI: 73 ± 20 vs. 74 ± 22). Lateralized RTSA demonstrated superior preservation of internal rotation, as evidenced by a higher percentage of patients achieving a negative Apley scratch test (67% compared to 23%, p < 0.05). A greater glenoidal offset correlated with improved postoperative external rotation and resolution of external rotation lag. The influence of teres minor integrity was more significant in the LDT group. Conclusions: Lateralized reverse total shoulder arthroplasty without latissimus dorsi tendon transfer provides similar functional restoration of external rotation in irreparable posterosuperior rotator cuff tear patients, accompanied by reduced complications, shorter surgical durations, and improved preservation of internal rotation. LDT has the potential to provide enhanced ER gains from a low baseline; however, it is characterized by increased invasiveness and technical complexity. Prosthetic lateralization is a biomechanically effective method for restoring external rotation in patients with rotator cuff arthropathy and external rotation deficits.