Emilio Calvo

Purpose: To develop an artificial intelligence‐based algorithm to predict success of nonoperative treatment in degenerative posterosuperior tears and to identify the most influential features. Methods: Patients with degenerative rotator cuff tears initially treated nonoperatively were enrolled prospectively from January 2022 to November 2024. Exclusion criteria included age >75 years; 2); and severe fatty degeneration (Goutallier >2). All patients followed a standardized physiotherapy protocol and could choose surgery if symptoms persisted; failure was defined as opting for surgery. Collected variables included demographics, comorbidities (diabetes, dyslipidemia, hypertension, hypothyroidism, and smoking), magnetic resonance imaging tear characteristics (size; International Society of Arthroscopy, Knee Surgery, and Orthopaedic Sports Medicine classification; associated cuff involvement; and biceps pathology), corticosteroid injection history, and functional scores (American Shoulder and Elbow Surgeons score, Subjective Shoulder Value, and the visual analog scale). First, a standard statistical analysis between groups was performed. Later, the dataset was split into a train (80%) and test (20%), and a random forest algorithm model was developed. Finally, SHapley Additive exPlanations values were computed to assess feature importance. Results: Of the 412 patients enrolled, 347 patients met the inclusion criteria. After 24 months, 66 (19%) patients opted for surgery. Mean follow‐up was 30.4 months (range, 24‐32). Compared with the successful nonoperative treatment group, patients who failed treatment were younger (58.5 vs 64.6 years, P = .001) and had higher body mass index (28.8 vs 27.2, P = .016), greater subscapularis involvement (13.5% vs 3%, P = .042), higher visual analog scale scores (7.7 vs 7.2, P = .018), lower Subjective Shoulder Value (30.9 vs 38.9, P = .003), and lower American Shoulder and Elbow Surgeons scores (40.6 vs 47.1, P = .001). The model achieved an area under the curve of 84%, predicting success rate of the nonoperative treatment with 94% sensitivity, 62% specificity, 89% positive predictive value, and 77% negative predictive value. The most influential variables for the model were age, tear size, and pretreatment functional scores. Conclusions: The artificial intelligence‐based algorithm accurately predicted nonoperative treatment outcomes in degenerative posterosuperior rotator cuff tears (area under the curve 0.84, sensitivity 94%). Age, tear size, and function were the main predictors. Level of Evidence: Level IV, prognostic retrospective case series.

Purpose: To establish evidence‐based consensus recommendations for the management of partial‐thickness posterosuperior rotator cuff tears (PT‐PS‐RCTs). This second part addresses treatment strategies, rehabilitation, return to sport and complications. Methods: This European Society for Sports Traumatology, Knee Surgery and Arthroscopy–European Shoulder Associates (ESSKA‐ESA) Formal Consensus was conducted according to the ESSKA Formal Consensus Methodology. A Steering Group (13 shoulder surgeons) developed 33 questions and statements based on a standardized literature review and assigned recommendation grades (A–D) according to the level of evidence. Statements were evaluated by an independent Rating Group (20 shoulder surgeons) through a three‐round consensus process. Results: Twenty‐one Question–Statement (Q–S) pairs achieved strong agreement, generating 30 individual recommendations (1 Grade A, 6 Grade B, 10 Grade C and 13 Grade D). Grade A evidence identified an increased risk of postoperative stiffness after trans‐tendon repair of articular‐sided PT‐PS‐RCTs compared with tear completion. Grade B evidence supported conservative treatment for at least 6 months, platelet‐rich plasma injections and management of stiffness before surgery; both trans‐tendon/in‐situ repair and tear‐completion‐and‐repair showed similar return‐to‐sport rates, although tear‐completion‐and‐repair had slightly higher retear rates. The most commonly reported patient‐reported outcome measures were the American Shoulder and Elbow Surgeons, Constant–Murley and visual analogue scale scores. Conclusion: Management should be individualized according to patient characteristics (activity level, sports participation), symptoms, tear morphology and tissue quality rather than based on a single treatment algorithm. Non‐surgical treatment is the preferred initial approach, whereas no surgical technique has demonstrated consistent superiority across all clinical scenarios. These recommendations provide clinicians with a practical framework to guide treatment decisions and standardize the management of PT‐PS‐RCTs in daily clinical practice. Level of Evidence: Level I, formal consensus.

Purpose: To establish evidence‐based consensus recommendations regarding the diagnosis and treatment of partial‐thickness posterosuperior rotator cuff tears (PT‐PS‐RCTs). This part addresses the definition, classification, natural history and diagnosis of these controversial conditions in shoulder surgery. Methods: This official European Society of Sports Medicine, Knee Surgery and Arthroscopy–European Shoulder Associates (ESSKA‐ESA) Formal Consensus was conducted according to the ESSKA Formal Consensus Methodology. A Steering Group developed 33 questions, followed by a standardized literature search and evidence review. For each question, a consensus statement was drafted and assigned recommendation grades (A–D) according to the level of evidence. An independent Rating Group evaluated all statements until strong agreement was achieved. Results: Twelve recommendations were generated with three Grade A, three Grade B, two Grade C, five Grade D and strong agreement. Grade A was found for the use of multiple classification systems in unison to characterize these injuries and for the distinction between acute and chronic tears. Scientific presumption level (Grade B) was found for the increased incidence of articular injuries in overhead and contact athletes and for the absence of a link between calcifying tendinitis and PT‐PS‐RCTs. Grade C was found to define the risk and timeframe of tear progression and the ideal imaging modality. Conclusion: This ESSKA‐ESA Formal Consensus recommends that PT‐PS‐RCTs should be classified according to tear location, depth and tendon involvement. The aetiology of these injuries is multifactorial, and their progression is unpredictable. Current imaging modalities have limitations in characterizing these lesions. The present consensus provides clinicians with a practical evidence‐based framework for the diagnosis and classification of PT‐PS‐RCTs while identifying key priorities for future clinical research. Level of Evidence: Level I formal consensus.

Purpose: To evaluate the incidence of unexpected positive cultures (UPCs) in revision versus primary arthroscopic shoulder stabilization procedures. Methods: Prospective comparative study of patients undergoing shoulder stabilization surgery. Thirty‐four patients undergoing revision stabilization surgery and 34 undergoing a primary stabilization procedure were consecutively enrolled from August 2022 until December 2024. Inclusion criteria were patients undergoing primary or revision arthroscopic shoulder stabilization by the same surgeon. Patients with signs of infection or prior clinical infection, open surgery or recent antibiotic use were excluded. Intraoperative tissue samples were collected before prophylactic antibiotics and sent for microbiological analysis. Data on types of procedures, rate of positive cultures, isolated microorganisms, and demographic information (age, sex, body mass index, smoking, malnutrition, intravenous drug use, epilepsy, and immunosuppression) were recorded. Results: The mean age of the cohort was 33.7 ± 10.2 years with 75% male and 25% female patients. There were no significant differences between groups regarding age, sex, smoking, and immunosuppressive state ( P > .05). There were no significant differences in the type of procedure performed in primary surgery (soft tissue vs bone transfer) P > .05. The leading cause for revision was instability (91.2%) followed by stiffness (5.9%) and pain (2.9%). Revision surgeries had significantly higher rate of UPCs ( P = .025) with 6 patients (17.6%) in the revision group and none in the primary group. Cutibacterium acnes was identified in 5 (83.3%) cases, while Staphylococcus aureus was identified in 1 (16.7%) case. Conclusions: The incidence of UPCs is significantly higher in revision arthroscopic shoulder stabilization procedures than in primary surgeries. Level of evidence: Level II, prospective comparative study.

While most patients with degenerative rotator cuff tears respond to conservative treatment, a minority progress to surgery. To anticipate these cases under class imbalance, we propose a sensitivity-constrained evolutionary feature selection framework prioritizing surgical-class recall, benchmarked against traditional methods. Two variants are proposed: (i) a single-objective search maximizing balanced accuracy and (ii) a multi-objective search also minimizing the number of selected features. Both enforce a minimum-sensitivity constraint on the minority class to limit false negatives. The dataset includes 347 patients (66 surgical, 19%) described by 28 clinical, imaging, symptom, and functional variables. We compare against 62 widely adopted pipelines, including oversampling, undersampling, hybrid resampling, cost-sensitive classifiers, and imbalance-aware ensembles. The main metric is balanced accuracy, with surgical-class F1-score as secondary. Pairwise Wilcoxon tests with a win–loss ranking assessed statistical significance. Evolutionary models rank among the top; the multi-objective variant with a Balanced Bagging Classifier performs best, achieving a mean balanced accuracy of 0.741. Selected subsets recurrently include age, tear location/severity, comorbidities, and pain/functional scores, matching clinical expectations. The constraint preserved minority-class recall without discarding or synthesizing data. Sensitivity-constrained evolutionary feature selection thus offers a data-preserving, interpretable solution for pre-surgical decision support, improving balanced performance and supporting safer triage decisions.

Purpose Periprosthetic joint infection (PJI) after shoulder arthroplasty remains a devastating complication, and the optimal surgical approach is still debated. This study aimed to compare the outcomes of single-stage versus two-stage revision and to identify clinical or demographic factors associated with treatment failure. Methods A retrospective observational study was conducted at a single tertiary hospital including 29 patients treated for shoulder PJI between 2010 and 2023. Patients underwent either one-stage (n = 15) or two-stage (n = 14) revision according to clinical and microbiological criteria, and the final choice of surgical strategy (one-stage vs. two-stage revision) was made at the discretion of the attending surgeon. The primary outcome was treatment success, defined as infection eradication without further surgery or suppressive antibiotics. Secondary outcomes were pain and functional results measured with the Constant-Murley Score (CMS), the Simple Shoulder Test (SST), and the Visual Analog Scale (VAS). A standard statistical analysis was performed comparing baseline data of both groups and finding factors related to the primary outcome. Results Baseline characteristics of both groups were comparable. Overall infection control was achieved in 83% of patients, nonetheless, the one-stage group showed a higher success rate compared with the two-stage group (93% vs. 71%), although this difference did not reach statistical significance (p = 0.169; OR:0.19(0.003,2.29)). Functional outcomes assessed by CMS and VAS did not differ significantly between groups, whereas SST scores were significantly better following one-stage revision (p = 0.006). Increased BMI and a higher number of previous surgeries tended to be associated with treatment failure. Conclusion Single-stage revision achieved comparable infection control and better functional outcomes than two-stage revision, supporting its role as a reliable surgical option for shoulder PJI in appropriately selected patients, although it could be influenced by bias selection.