Search Results (196)

The in vivo effect of platelet-rich plasma (PRP) on supraspinatus tendon morphology and subacromial bursa cell gene expression in degenerative rotator cuff tears remains unclear. This randomized controlled trial evaluated the effect of preoperative leukocyte-poor PRP (LP-PRP) subacromial injection on supraspinatus tendon histology and subacromial bursa gene expression. Sixteen patients with full-thickness supraspinatus tears were randomized to receive an ultrasound-guided LP-PRP injection (n = 8) or no injection (n = 8) six weeks before arthroscopic repair. Tendon biopsies were assessed using the modified Movin score. Gene expression of collagen type I, II and III, metalloproteinase 3 and 13, and interleukin 1β and 6 genes from subacromial bursa cells was quantified using quantitative real-time PCR. The results of the two groups were compared to determine any statistically significant difference regarding all the examined parameters. The PRP group demonstrated a significantly lower total modified Movin score than controls (6.5 vs. 12.1, p = 0.002), with lower scores for fiber structure, fiber arrangement, nuclear rounding, inflammation and cell density (all p < 0.003), while angiogenesis did not differ (p = 0.149), indicating an architecture closer to that of normal tendon. No statistically significant differences in gene expression were observed (all p > 0.05), although collagen II and metalloproteinase 3 and 13 showed biologically relevant downregulation [fold change 0.23 (95%CI 0.05–1.09), 0.24 (95%CI 0.002–26.10), and 0.26 (95%CI 0.02–2.76), respectively]. The LP-PRP injection was associated with improved supraspinatus tendon histological characteristics and biologically relevant reductions in selected bursal genes, in the setting of supraspinatus tendon tear. Full article

Background/Objectives: Rotator cuff repair (RCR) is a common orthopedic procedure, with healing outcomes strongly influenced by patient-specific factors such as tissue quality, tear characteristics, and biological healing potential. Bioinductive collagen implants have shown great results in enhancing tendon healing and reducing retear rate. This study aimed to evaluate the clinical and imaging outcomes of RCR augmented with a xeno-derived collagen membrane over 24 months and to assess complications or implant failures. Methods: Patients underwent arthroscopic RCR using anchors (single or double-row) with additional xeno-derived matrix augmentation. The study included patients older than 40 years with full-thickness supraspinatus and/or infraspinatus tendon tears (DeOrio–Cofield grade 3–4) who were candidates for arthroscopic rotator cuff repair and provided informed consent. Clinical outcomes were assessed using the Constant–Murley Score (CMS), Disabilities of the Arm, Shoulder and Hand score (DASH), and Visual Analogue Score (VAS) at baseline, 3, 6, 12, and 24 months. MRI was performed preoperatively and at 24 months to assess tendon thickness. Results: All scores improved significantly. CMS increased from 16.3 ± 4.1 to 82.9 ± 5.8, VAS decreased from 7.8 ± 1.0 to 1.5 ± 0.8, and DASH improved from 70.3 ± 6.4 to 12.4 ± 4.5 (p < 0.05). Tendon thickness in the supraspinatus (T3) increased from 4.2 ± 0.9 mm to 6.8 ± 1.2 mm (p < 0.05). Retear rate was 7.55%, with no major complications. Conclusions: The bioinductive collagen implant showed notable results in improving tendon thickness, healing, and excellent clinical outcomes in RCR, without membrane-related complications. The study was designed as a prospective single-arm case series without a control group and that was the main limitation; The absence of adverse reactions in this cohort further supports the favorable safety profile of this implant in the present study population. Full article

Background and Objectives: It is crucial to determine physical findings and outcome measures that affect functional status of the patients, and the impact levels of these parameters on patients. Therefore, the aim of this study was to investigate the determinant and predictive effect of pain levels, shoulder range of motion (ROM) values, disability and health-related quality of life factors on functional status in individuals with partial-thickness rotator cuff tears (PRCT). Materials and Methods: Firstly, the functional status of 45 patients (mean age: 50.78 ± 5.28 years; 29 female) with PRCT, then activity and night pain levels with Numeric Pain Rating Scale, active flexion, abduction and external rotation of the shoulder ROM values with goniometer, disability level with Quick Disabilities of Arm, Shoulder & Hand Questionnaire, and health-related quality of life levels with Short Form-12 were evaluated and recorded. Results: It was detected that all determinants whose effect on functionality was evaluated with a multiple regression model explained 76% of the variance, and this effect level was statistically significant (R square = 0.760, adjusted R square = 0.707, F = 14.272, p < 0.001). Detailed evaluation showed that flexion and external rotation ROM values (respectively; β = 0.54, p < 0.001; β = 0.38, p = 0.001) and disability level (β = 0.44, p < 0.001) had statistically significant determinant effects on functional status. No statistically significant results which could be correlated with functional status were found for activity and night pain, abduction ROM value, and health-related quality of life domains (p > 0.05). Conclusions: Shoulder flexion and external rotation ROMs and disability level were found to have a predictive effect on the functional status in individuals with PRCT. It is noteworthy that more subjective and patient-reported findings and outcome measures such as pain and health-related quality of life had no predictive effect on functionality. By determining the level of these effects, results were reached that can shed light on the literature by guiding the development of reliable assessment algorithms. Full article

Background/Objectives: The optimal surgical timing for rotator cuff tears (RCTs) remains controversial, particularly regarding how tear etiology influences the final functional recovery. This study aimed to compare the clinical outcomes of early versus delayed arthroscopic repair stratified by etiology, providing evidence for etiology-specific surgical timing. Methods: A retrospective cohort study was conducted on 183 patients who underwent arthroscopic rotator cuff repair for isolated full-thickness supraspinatus tears. Patients were stratified into traumatic (n = 74) and degenerative (n = 109) groups based on etiology. They were further divided into early-repair and delayed-repair subgroups based on symptom duration (traumatic cut-off: 3 months; degenerative cut-off: 6 months). Clinical outcomes were assessed preoperatively and at the final follow-up using the Visual Analog Scale (VAS) for pain, American Shoulder and Elbow Surgeons (ASES) score, University of California at Los Angeles (UCLA) score, and range of motion. Complications, including retear rates and stiffness, were recorded. Results: In the traumatic group, early repair yielded significantly better postoperative pain relief (VAS) and higher functional scores (ASES and UCLA) compared to delayed repair. Notably, the delayed traumatic group exhibited a significantly higher retear rate compared to the early group (16.7% vs. 2.6%; p = 0.039). Conversely, in the degenerative group, comparisons between early and delayed repair revealed no significant differences in the final functional scores, pain levels, or complication rates (p > 0.05). Conclusions: Surgical timing significantly impacts outcomes in traumatic RCTs, where early repair is critical to optimize functional recovery and minimize retear risks. In contrast, delayed arthroscopic repair for degenerative tears yielded comparable outcomes to early repair, suggesting that an initial trial of conservative management is safe and does not compromise final surgical outcomes. Full article

Backgrounds/Objectives: Fatty infiltration (FI) of rotator cuff (RC) muscles is a critical prognostic factor after surgical repair. While the Goutallier–Fuchs grading system is widely used, its reproducibility is often debated. This study aimed to validate a previously reported three-dimensional (3D) magnetic resonance imaging (MRI)-based volumetric quantification method by comparing it with histologic findings in a chronic rotator cuff tear (RCT) rabbit model. Methods: Eighteen shoulders from nine rabbits were randomly assigned to three groups (n = 6 each): repair (A), chronic tear (B), and control (C). In groups A and B, a chronic RCT model was established by detaching the supraspinatus tendon, with group A receiving repair after six weeks. At 12 weeks after repair, 7.0T MRI was performed, and volumetric quantification of intra-muscular fat was performed using semi-automated 3D Slicer software. Histologic fat proportion was measured via Oil Red O staining and ImageJ analysis. Results: The muscle weight and MRI-based muscle volume were significantly lower in group B than group C (p < 0.05). The radiologically measured fat proportion was significantly higher in groups A (1.8 ± 0.8) and B (2.8 ± 0.7) compared to group C (0.5 ± 0.4, p < 0.001). Histologic analysis showed a corresponding pattern (3.0 ± 1.2%, 5.2 ± 1.0%, 1.7 ± 1.0% for groups A, B, and C, respectively; p < 0.001). A strong positive correlation was identified between the radiologic and histologic measurements of FI (r = 0.784, p < 0.001). Conclusions: Direct histologic comparison validates the reliability of 3D MRI-based volumetric quantification for evaluating FI of the RC muscle in a chronic RCT rabbit model. This objective approach may address the inherent limitations of the conventional qualitative grading system. Full article

Background: This study aimed to investigate the potential biomechanical implications of biologically motivated modulation scenarios—Resolvin E1 (RvE1), Resolvin D1 (RvD1) and carvacrol—in the context of rotator cuff tears by using a reduced finite element (FE) modeling approach. The primary objective was to compare stress distribution and deformation behavior at the tendon–bone interface under standardized loading scenarios. Materials and Methods: A three-dimensional reduced FE model of the shoulder, including the scapula and proximal humerus, was constructed based on computed tomography data. A rotator cuff tear was represented at the tendon footprint on the greater tuberosity. Standardized boundary scenarios and loading vectors were applied. Three conceptual biological modulation scenarios (RvE1, RvD1, and carvacrol) were evaluated and compared with a baseline model representing a rotator cuff tear under identical geometric, material, boundary, and loading scenarios, without any biologically motivated modulation. Von Mises stress distribution at the greater tuberosity and tendon footprint, as well as maximum displacement of the proximal humerus, were analyzed descriptively and comparatively. Results: Compared with baseline scenarios, the RvE1 and RvD1 scenarios demonstrated reduced peak von Mises stress at the tendon footprint and lower overall humeral displacement. Peak footprint stress decreased from 10.8 MPa in the baseline model to 7.9 MPa (−26.9%) in the RvE1 scenario and to 8.6 MPa (−20.4%) in the RvD1 scenario. Similarly, maximum humeral displacement was reduced from 4.6 mm at baseline to 3.4 mm (−26.1%) with RvE1 and to 3.9 mm (−15.2%) with RvD1. In contrast, the carvacrol scenario exhibited increased localized stress concentration at the tendon footprint (12.4 MPa; +14.8%) and greater maximum displacement (5.8 mm; +26.1%). Conclusions: The findings suggested that modulation scenarios associated with specialized pro-resolving mediators (SPMs) were aligned with a more favorable mechanical environment at the tendon–bone interface compared with baseline scenarios, whereas the carvacrol scenario demonstrated less favorable biomechanical behavior under the modeled assumptions. Although the biological effects were represented conceptually and the results were interpreted as relative trends, this study highlighted the potential importance of resolution-oriented pathways in influencing tendon-to-bone biomechanics and supported further experimental and translational investigations in rotator cuff repair. Full article

Background: Shoulder arthroplasty is performed for various etiologies, including osteoarthritis, proximal humerus fractures (PHFs), and rotator cuff tears. While previous studies have focused on outcomes based on implant choice, less is known about the independent effects of surgery type, comorbidities, and fracture status on postoperative outcomes. This study evaluates their influence on length of stay (LOS), in-hospital mortality, and postoperative complications. Methods: A retrospective cohort analysis of 664,545 patients undergoing anatomic total shoulder arthroplasty (ATSA), reverse total shoulder arthroplasty (RTSA), or hemiarthroplasty (HA) was conducted. Multivariable Poisson and logistic regression models assessed predictors of LOS, mortality, and complications. Results: Among 132,909 patients, 63.3% underwent RTSA, 31.3% underwent ATSA, and 5.4% underwent HA. Mean hospitalization was longest for HA (2.56 days) and RTSA (1.82 days) compared to ATSA (1.39 days; p < 0.001). Poisson regression confirmed that RTSA increased LOS by 24.1% versus ATSA (IRR = 1.24, p < 0.001), while HA had the highest LOS (IRR = 1.58, p < 0.001). Postoperative complications were observed in 8.37% of ATSA, 13.81% of RTSA, and 17.81% of HA cases (overall ~12.3%). Compared with ATSA, RTSA increased the odds of complications (OR = 1.48, p < 0.001), while HA presented the greatest complication risk (OR = 1.51, p < 0.001). Among proximal humerus fracture (PHF) patients (9.9% of the cohort), 84.7% underwent RTSA. PHF independently increased LOS (IRR = 1.61, p < 0.001), mortality (OR = 1.62, p = 0.051), and complications (OR = 2.33, p < 0.001). Conclusions: RTSA is associated with longer hospitalization and higher complication rates, while PHF worsens LOS, mortality, and complication risk. Full article

Background/Objectives: Rotator cuff tears (RCTs) are a leading cause of shoulder pain and disability. Management typically involves conservative measures, such as physical therapy and anti-inflammatory medications, or surgery for full-thickness or refractory tears. Regenerative medicine therapies, including platelet-rich plasma (PRP), platelet lysate (PL), and mesenchymal stem cells (MSCs), show promise as alternative treatment strategies, although long-term outcomes remain under investigation. Methods: This cohort included 30 patients with partial rotator cuff tears and were treated with culture-expanded MSC injections. There was no control group. Inclusion criteria included an imaging-confirmed diagnosis of partial-thickness rotator cuff tears. Outcomes were assessed at multiple time points up to 6 years. Pain and function were assessed using the Disabilities of the Arm, Shoulder, and Hand (DASH), a Numeric Rating Scale (NRS), and the modified Single Assessment Numeric Evaluation (SANE). Results: Thirty patients (37 shoulders) were included in the analysis. Significant improvements in the NRS and DASH scores were observed at 3, 6, 12, 18, and 24 months (p < 0.01). Twenty-four months post-treatment, the mean NRS and DASH decreased by 2.25 and 15.93 points, respectively, and SANE improved by 60%. At six years, among seven respondents, the mean SANE improvement was 75.54%. During this study, no significant adverse events were reported. Conclusions: This study provides the longest known follow-up of MSC therapy for partial-thickness RCTs, finding sustained pain and functional improvements. The findings support further research into MSC-based and combination regenerative therapies as a viable alternative treatment option for partial-thickness rotator cuff tears. Full article

Background/Objectives: Diagnosing Rotator Cuff Tears (RCTs) via Magnetic Resonance Imaging (MRI) is clinically challenging due to complex 3D anatomy and significant interobserver variability. Traditional slice-centric Convolutional Neural Networks (CNNs) often fail to capture the necessary volumetric context for accurate grading. This study aims to develop and validate the Patient-Aware Vision Transformer (Pa-ViT), an explainable deep-learning framework designed for the automated, patient-level classification of RCTs (Normal, Partial-Thickness, and Full-Thickness). Methods: A large-scale retrospective dataset comprising 2447 T2-weighted coronal shoulder MRI examinations was utilized. The proposed Pa-ViT framework employs a Vision Transformer (ViT-Base) backbone within a Weakly-Supervised Multiple Instance Learning (MIL) paradigm to aggregate slice-level semantic features into a unified patient diagnosis. The model was trained using a weighted cross-entropy loss to address class imbalance and was benchmarked against widely used CNN architectures and traditional machine-learning classifiers. Results: The Pa-ViT model achieved a high overall accuracy of 91% and a macro-averaged F1-score of 0.91, significantly outperforming the standard VGG-16 baseline (87%). Notably, the model demonstrated superior discriminative power for the challenging Partial-Thickness Tear class (ROC AUC: 0.903). Furthermore, Attention Rollout visualizations confirmed the model’s reliance on genuine anatomical features, such as the supraspinatus footprint, rather than artifacts. Conclusions: By effectively modeling long-range dependencies, the Pa-ViT framework provides a robust alternative to traditional CNNs. It offers a clinically viable, explainable decision support tool that enhances diagnostic sensitivity, particularly for subtle partial-thickness tears. Full article

Background/Objectives: Non-traumatic (degenerative) rotator cuff tendinopathy with partial supraspinatus tear (NT-RCTT) is a common source of shoulder pain and disability. Comparative evidence between radial extracorporeal shock wave therapy (rESWT) and multimodal physical therapy modalities (PTMs) remains scarce. Methods: In this single-center randomized controlled trial, 60 adults with MRI-confirmed NT-RCTT were assigned (1:1) to rESWT (one session weekly for six weeks; 2000 impulses per session, 2 bar air pressure, positive energy flux density 0.08 mJ/mm²; 8 impulses per second) or a multimodal PTM program (interferential current, shortwave diathermy and magnetothermal therapy; five sessions weekly for six weeks). All participants performed standardized home exercises. The primary outcome was the American Shoulder and Elbow Surgeons (ASES) total score; secondary outcomes included pain (visual analog scale, VAS), satisfaction, range of motion (ROM), supraspinatus tendon (ST) thickness and acromiohumeral distance (AHD). Assessments were conducted at baseline, and at week 6 (W6) and week 12 (W12) post-baseline. Results: Both interventions significantly improved all outcomes, but rESWT produced greater and faster effects. Mean ASES total scores increased by 31 ± 5 points with rESWT versus 26 ± 6 with PTMs (p < 0.05). VAS pain decreased from 5.2 ± 0.7 to 1.0 ± 0.7 with rESWT and from 5.2 ± 0.8 to 1.7 ± 0.8 with PTMs (p < 0.01). rESWT achieved higher satisfaction and larger gains in abduction, flexion and external rotation. Ultrasound showed reduced ST thickness and increased AHD after rESWT but not after PTMs. No serious adverse events occurred. Conclusions: rESWT yielded superior pain relief, functional recovery and tendon remodeling compared with a multimodal PTM program, with markedly lower treatment time and excellent tolerability. Full article

Background/Objective: This study aimed to compare functional and clinical outcomes in terms of shoulder muscle performance and patient-reported outcomes (PROs) between patients with rotator cuff muscle tears (RCTs) with high preoperative critical shoulder angle (CSA) or acromial index (AI) and those with low preoperative CSA or AI and to determine the outcomes associated with CSA and AI. Methods: Ninety patients with RCTs were recruited [45 with high preoperative CSA (>35°) vs. 45 with low preoperative CSA (<35°), and 42 with high preoperative AI (>0.75) vs. 48 with low preoperative AI (<0.75)]. Functional outcomes, such as muscle strength and endurance of the internal rotators, external rotators, and forward flexors, were measured for shoulder muscle performance using an isokinetic device. Clinical outcomes were evaluated using PROs, such as the University of California at Los Angeles (UCLA) and Constant scores. Results: Patients with RCTs with high preoperative CSA had decreased muscle endurance of the external rotators (p = 0.030) in the involved shoulders compared to patients with RCTs with low preoperative CSA. Patients with RCTs with high preoperative AI had decreased muscle endurance of the external rotators (p = 0.010) and UCLA scores (p = 0.010) in the involved shoulders compared with patients with RCTs with low preoperative AI. Preoperative AI was closely associated with muscle endurance for external rotators (β = −17.204) and the UCLA score (β = −3.269). Conclusions: Patients with RCTs with high preoperative CSA or AI may have lower shoulder muscle endurance than those with low preoperative CSA or AI, especially for external rotators. Furthermore, preoperative AI was independently associated with external rotator muscle endurance and the UCLA score. Therefore, assessment of preoperative CSA or AI may be important for pre- or postoperative management in patients with RCTs, as AI is associated with functional and clinical outcomes. Full article

Background/Objectives: Specialized pro-resolving lipid mediators (SPMs), such as Resolvin E1 (RvE1) and Resolvin D1 (RvD1), play a critical role in the resolution phase of inflammation. However, their relevance to tendon pathology and tissue-specific degeneration in rotator cuff tears remains unclear. This study aimed to investigate the relation between serum RvE1 and RvD1 levels and the morphological severity of tendon retraction and muscle fatty degeneration in patients with full-thickness rotator cuff tears. Methods: A total of 70 participants were included: 35 patients with full-thickness rotator cuff tears determined by magnetic resonance imaging (MRI) and 35 healthy controls. Tendon retraction and muscle fatty degeneration were graded using Patte and Goutallier classifications, respectively. Serum RvE1 and RvD1 levels were measured using enzyme-linked immunosorbent assay (ELISA). Group comparisons were performed using Welch’s t-test, and correlations were analyzed with Spearman’s coefficient. Results: RvE1 and RvD1 levels were significantly lower in patients compared to controls (p < 0.001). RvE1 showed a moderate positive correlation with Patte score (ρ = 0.37, p = 0.027), while no significant correlation was observed with Goutallier classification (ρ = 0.19, p = 0.27). RvD1 levels demonstrated no significant relationship with either morphological parameter. Conclusions: These findings suggest that decreased serum RvE1 levels are associated with the severity of tendon retraction but not with muscle fatty degeneration. Therefore, RvE1 may serve as a potential biochemical biomarker reflecting tendon damage severity and the impaired resolution of inflammation in rotator cuff tears. Full article

Objectives: The acromiohumeral distance (AHD) is widely used to evaluate subacromial pathology, particularly rotator cuff–related disorders. However, substantial heterogeneity exists across studies in imaging protocols, measurement definitions, and diagnostic thresholds. This systematic review aimed to synthesize current evidence on AHD measurement methods, assess reliability and diagnostic performance across imaging modalities, and examine the clinical relevance of AHD as both a structural and functional biomarker. Methods: A systematic search of PubMed, Web of Science, and SciELO (January 2006–May 2025) was conducted following PRISMA 2020. Eligible studies reported quantitative AHD measurements using ultrasound, MRI, or radiography in adults. Two reviewers independently conducted screening, extraction, and QUADAS-2 assessments. Due to heterogeneity, results were narratively synthesized. Results: Twenty-nine studies met the inclusion criteria. Definitions of AHD and imaging procedures varied substantially. Ultrasound showed the most consistent intra- and inter-observer reliability, whereas MRI and radiography demonstrated greater protocol-dependent variability. Reduced AHD values were frequently associated with full-thickness rotator cuff tears, while larger values typically characterized asymptomatic individuals. Several studies also reported reductions in AHD during arm elevation, supporting its interpretation as a functional parameter influenced by scapular motion and neuromuscular control. Conclusions: AHD is a reliable and clinically informative measure when acquired using standardized protocols, with Ultrasound demonstrating the highest reproducibility. Its sensitivity to positional and dynamic factors supports its role as both a structural and functional biomarker. Further research should prioritize standardized imaging procedures, dynamic assessment methods, and evaluation of emerging technologies to improve the diagnostic and prognostic value of AHD. Full article

Background/Objectives: Bioinductive bovine collagen implants (BCI) have been introduced to enhance tendon biology and promote tissue regeneration in rotator cuff (RC) repairs. This study aimed to assess the clinical and radiological outcomes of arthroscopic posterosuperior rotator cuff (psRC) repair with BCI augmentation in full-thickness tears at increased risk of retear. Methods: This case series analyzed 30 patients with psRC tears who were classified as being at high risk of failure according to a predefined set of parameters, including patient history, radiological findings and intraoperative assessments, and the presence of psRC retears. All patients subsequently underwent arthroscopic psRC repair with BCI augmentation, compromising 21 primary and 9 secondary repairs. Clinical outcomes were assessed using Subjective Shoulder Value (SSV), American Shoulder and Elbow Surgeons (ASES) shoulder score, and Constant score at 6 and 12 months postoperatively. Tendon integrity was assessed using the Sugaya classification. Results: At 12 months, magnetic resonance imaging revealed complete tendon healing in 56.7%, partial healing in 16.7%, and insufficient healing in 26.7%. Significant improvements in SSV (45.3 to 83.5), ASES (40.6 to 77.8), and Constant score (36.6 to 71.7) were observed at 12 months postoperatively, with all outcome measures exceeding their respective minimally clinically important differences. Two patients (6.7%) developed secondary shoulder stiffness, and 1 patient (3.3%) required revision surgery for bicipital groove pain. Conclusions: Augmentation with a BCI in arthroscopic repair of high-risk psRC tears demonstrate promising short-term results. Patients achieve significant improvements in pain and shoulder function, accompanied by satisfactory tendon healing on MRI. Full article

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. Full article