Background: Socially Assistive Robots (SARs) represent an innovative approach in rehabilitation technology, significantly enhancing the support and motivation for individuals across diverse rehabilitation settings. Despite their growing utilization, especially in stroke recovery and pediatric rehabilitation, their potential in musculoskeletal and orthopedic rehabilitation remains largely underexplored. Although there is methodological and outcome variability across the included studies, this review aims to critically evaluate and summarize the research on SARs in rehabilitation, providing a thorough overview of the current evidence and practical applications. Methods: A comprehensive search was conducted across multiple databases, resulting in the selection of 20 studies for analysis. The reviewed papers were categorized into three main classes based on the roles of the robots in rehabilitation: Motivation, Imitation, and Feedback Providers. Results: The analysis highlights that SARs significantly improve adherence to rehabilitation programs, enhance motor function, and increase motivation across clinical and home settings. Robots such as NAO, Pepper, and ZORA demonstrated high efficacy, particularly in stroke recovery and pediatric rehabilitation. Conclusions: SARs offer transformative benefits in rehabilitation, providing scalable, personalized solutions through motivational support, guided exercises, and real-time feedback. Their integration into orthopedic rehabilitation could address critical clinical needs, enhancing precision in exercises, adherence to long-term programs, and overall patient outcomes. Future research should prioritize the development and validation of SAR-based interventions for musculoskeletal disorders to unlock their full potential in this domain.

Objective: This descriptive systematic review aimed to assess in the available literature on the current application and overall performance of Artificial Intelligence (AI) models in the diagnosis and classification of Rotator Cuff Tears (RCTs) using MRIs. Methods: The systematic review was performed by two of the authors from 2020 to November 2024. Only diagnostic studies involving AI application to MRI images of the rotator cuff were considered, including supraspinatus and biceps tears. Studies evaluating AI applications to Ultrasound or X-ray, or including only healthy rotator cuffs, were not analyzed in this paper. Results: The coronal plane in the T2 sequence emerged as the predominant imaging protocol, with the VGG network being the most widely utilized AI model. The studies included in this research exhibited a solid performance of the AI models with accuracy, ranging from 71.0% to 100%. The statistical analysis revealed no significant differences (p > 0.05) in accuracy, sensitivity, specificity, or precision between AI and human experts across studies that included such comparisons. Conclusions: While AI can significantly improve diagnostic efficiency and workflow optimization, future studies must focus on external validation, regulatory approval, and AI-human collaboration models to ensure safe and effective integration into orthopedic imaging.

Gait analysis offers a powerful tool for clinical and orthopaedic decision‐making. By quantifying spatiotemporal, kinematic and kinetic parameters during walking, it provides a dynamic window into joint function that static imaging cannot capture. Despite its potential, gait analysis remains largely confined to specialised centres, with limited integration in clinical pathways, mainly due to its perceived complexity and lack of standardisation. This narrative review aims to bridge that gap through a step‐by‐step approach to guide orthopaedic surgeons, sports medicine physicians and musculoskeletal clinicians in understanding and interpreting key biomechanical markers relevant to common knee pathologies, such as osteoarthritis and anterior cruciate ligament injury. Particular attention is given to how deviations in parameters like joint angles and moments, dynamic alignment and centre of pressure trajectories can offer actionable insights into disease progression, treatment response and surgical planning. The urgent need for standardised protocols, encompassing marker placement, biomechanical modelling and data processing, is also underscored, as they are essential to ensure reproducibility and facilitate clinical translation. By clarifying the clinical meaning of gait metrics, this review empowers healthcare professionals to integrate dynamic functional data into everyday decision‐making and move towards more personalised, biomechanically informed care.Level of Evidence: Level IV.

Static radiographic alignment fails to capture the dynamic nature of joint behaviour during functional tasks. To address this, our study evaluated the relationship between Hip-Knee-Ankle angle (HKAA) and dynamic biomechanical variables (dynamic HKAA (dHKAA), via projection of hip, knee, and ankle joint centers onto the frontal plane, knee adduction moment (KAM), and knee abduction angle (KAA)), during gait and sit-to-stand tasks with and without arm assistance. A further objective was to examine the mediolateral center of pressure (COP ML) as a complementary parameter for assessing joint loading and frontal plane alignment. Twenty-two patients (mean age 67 ± 9 years, BMI 28.7 ± 3.4 kg/m²) with end-stage knee osteoarthritis scheduled for total knee arthroplasty were recruited. HKAA was extracted from full-length standing radiographs, while dynamic variables from 3D motion capture and force plates data. Associations between static and dynamic parameters were evaluated using correlation and linear regression analyses. dHKAA consistently exhibited stronger correlations with KAM and KAA than radiographic HKAA, particularly during gait loading response (ρ = 0.93; R² = 0.84, p < 0.01). Similar trends were observed in the other tasks, where HKAA showed limited associations. COP ML showed moderate correlations with KAM but none with dHKAA. These findings suggest that HKAA alone may not reliably capture functional joint loading, and that dHKAA provides a more comprehensive assessment of frontal plane knee behaviour. COP ML showed limited associations and should be cautiously interpreted in this context. These findings may enhance clinical assessments, surgical planning, and advancing-personalized, biomechanically driven intervention research.

Background: Rotator cuff tears (RCTs) are a significant cause of shoulder pain and disability. In clinical practice, assessing a patient’s rotator cuff health status generally includes multiple questionnaire-based clinical scales. Optoelectronic motion capture systems, currently considered the gold standard, can be used to assess shoulder 3-dimensional (3D) kinematics quantitatively. Identifying new, hitherto unexplored relationships between kinematic parameters and clinical scores may help provide new insights into the management of patients with RCTs. Purpose: To investigate the correlations between the most common clinical scores for evaluating patients with RCT and objective kinematic measures retrieved by optoelectronic motion capture systems. Study Design: Cross-sectional study; Level of evidence, 3. Methods: A total of 102 patients with RCT were enrolled to evaluate correlations between clinical scores (eg, Shoulder Pain and Disability Index [SPADI] score and Oxford Shoulder Score [OSS]) and kinematic measurements (range of motion [ROM] and peaks) obtained using a 3D optoelectronic analysis system while performing 4 tasks. The relationship between these variables was evaluated using the Spearman correlation analysis. Results: The results revealed moderate to weak correlations between some kinematic variables and clinical scales, varying by the kinematic variable type, the task performed, and the specific clinical scale. A moderate correlation was found between the SPADI score and peaks during flexion (ρ = −0.485; P < .001) and abduction (ρ = −0.493; P < .001). Another moderate correlation was found between the OSS and ROM in flexion (ρ = −0.428; P < .001) and abduction (ρ = −0.415; P < .001); additionally, a moderate correlation was found between the OSS and peaks in flexion (ρ = −0.403; P < .001) and abduction (ρ = −0.407; P < .001). Other significant correlations were identified between kinematic measures and clinical outcomes, albeit of fair intensity, between visual analog scale score and ROM and peaks in flexion, abduction, and external rotation. Conclusion: This study emphasizes the necessity of a multidimensional approach to managing RCT, showing that only moderate correlations exist between some kinematic measurements and outcome scores, such as the SPADI score and OSS. Furthermore, measures like the American Shoulder and Elbow Surgeons and visual analog scale scores display even weaker, fair correlations. This discrepancy suggests the need for complementary tools to comprehensively evaluate a patient’s rotator cuff health status.

Background/Objectives: Rotator cuff tears are a prevalent cause of shoulder pain and functional impairment. Full-thickness tears often require surgical intervention, but managing such injuries can be challenging, particularly when complete anatomical repair is unattainable. Bioinductive implants have emerged as an innovative adjunct to enhance tendon healing and regeneration. Methods: This case report details the partial repair of a full-thickness rotator cuff tear in a 66-year-old woman, augmented with a bioinductive implant. Postoperative recovery was monitored through clinical examinations, MRI, and kinematic analysis at 3 and 6 months. Results: The findings suggest that bioinductive implants may offer a promising strategy for managing complex rotator cuff tears, particularly when complete repair is not feasible. The patient reported improvement in function and pain reduction. Conclusions: The use of bioinductive implants showed promising results, promoting tendon regeneration and improving functional outcomes. Future research should explore patient selection criteria and the long-term effectiveness of this strategy.