A practical guide to the implementation of artificial intelligence in orthopaedic research-Part 2: A technical introduction.

Recent advances in artificial intelligence (AI) present a broad range of possibilities in medical research. However, orthopaedic researchers aiming to participate in research projects implementing AI-based techniques require a sound understanding of the technical fundamentals of this rapidly developing field. Initial sections of this technical primer provide an overview of the general and the more detailed taxonomy of AI methods. Researchers are presented with the technical basics of the most frequently performed machine learning (ML) tasks, such as classification, regression, clustering and dimensionality reduction. Additionally, the spectrum of supervision in ML including the domains of supervised, unsupervised, semisupervised and self-supervised learning will be explored. Recent advances in neural networks (NNs) and deep learning (DL) architectures have rendered them essential tools for the analysis of complex medical data, which warrants a rudimentary technical introduction to orthopaedic researchers. Furthermore, the capability of natural language processing (NLP) to interpret patterns in human language is discussed and may offer several potential applications in medical text classification, patient sentiment analysis and clinical decision support. The technical discussion concludes with the transformative potential of generative AI and large language models (LLMs) on AI research. Consequently, this second article of the series aims to equip orthopaedic researchers with the fundamental technical knowledge required to engage in interdisciplinary collaboration in AI-driven orthopaedic research. Level of Evidence: Level IV.

Advanced Home-Based Shoulder Rehabilitation: A Systematic Review of Remote Monitoring Devices and Their Therapeutic Efficacy.

Shoulder pain represents the most frequently reported musculoskeletal disorder, often leading to significant functional impairment and pain, impacting quality of life. Home-based rehabilitation programs offer a more accessible and convenient solution for an effective shoulder disorder treatment, addressing logistical and financial constraints associated with traditional physiotherapy. The aim of this systematic review is to report the monitoring devices currently proposed and tested for shoulder rehabilitation in home settings. The research question was formulated using the PICO approach, and the PRISMA guidelines were applied to ensure a transparent methodology for the systematic review process. A comprehensive search of PubMed and Scopus was conducted, and the results were included from 2014 up to 2023. Three different tools (i.e., the Rob 2 version of the Cochrane risk-of-bias tool, the Joanna Briggs Institute (JBI) Critical Appraisal tool, and the ROBINS-I tool) were used to assess the risk of bias. Fifteen studies were included as they fulfilled the inclusion criteria. The results showed that wearable systems represent a promising solution as remote monitoring technologies, offering quantitative and clinically meaningful insights into the progress of individuals within a rehabilitation pathway. Recent trends indicate a growing use of low-cost, non-intrusive visual tracking devices, such as camera-based monitoring systems, within the domain of tele-rehabilitation. The integration of home-based monitoring devices alongside traditional rehabilitation methods is acquiring significant attention, offering broader access to high-quality care, and potentially reducing healthcare costs associated with in-person therapy.

The Epidemiology of Shoulder Injuries in Water Polo Players: A Monocentric Descriptive Study on Clinical and Radiological Presentation.

Water polo players' shoulders are exposed to repeated overhead and throwing motions as well as direct and indirect traumas. Shoulder injuries account for over half of all injuries sustained by water polo players. This is a monocentric descriptive epidemiological study on the clinical and radiological presentation of a consecutive series of water polo players from January 2002 to September 2022. All patients underwent clinical and physical examinations and an MRI arthrogram. A total of 92 water polo players were included in this study. Fifty-three patients (57.6%) reported at least one previous shoulder instability episode; 100% of patients in this group were diagnosed with a capsulolabral complex lesion, and 88.7% of these players complained of subjective symptoms of shoulder instability (RR: 4.4). A total of 39 out of 92 patients (42.4%) did not report previous shoulder dislocation episodes; the mean age at presentation in this group was significantly higher than the mean age of the patients who experienced previous instability episodes (p < 0.01), and the throwing arm was affected in 79.5% of patients (RR = 1.41).

Effectiveness of High-Power Laser Therapy via Shear Wave Speed Analysis on Pain and Functioning in Patients with Lateral Epicondylitis: A Proof-of-Concept Study.

Background: Lateral epicondylitis (LE) causes lateral elbow pain due to the overuse of the common extensor tendon. Several therapies have been proposed for pain relief and functional recovery, including physical therapy, minimally invasive injection approaches, and physical agent modalities such as laser therapy. Methods: Our study evaluates the impact of high-power laser therapy (HPLT) on pain and functioning. The HPLT protocol consists of 10 daily sessions using a LASERIX PRO device. The healthy elbow of each participant was also considered as a control group. The outcomes assessed were the Numerical Rating Scale (NRS) for pain, QuickDASH questionnaire for functionality, and shear wave velocity (SWS) through ultrasonography. Assessments were conducted at baseline (T0), post-treatment (T1), and 2-week follow-up (T2). Results: Sixteen participants (81.2% male, mean age 40.4 ± 5.53 years) completed the study. Post-treatment, pain significantly decreased (NRS: T0 6.13 ± 0.96; T1 2.75 ± 1.69; p < 0.001), functionality improved (QuickDASH: T0 69.88 ± 10.75; T1 41.20 ± 3.78; p < 0.001), and shear wave velocity increased (SWS (m/s): T0 1.69 ± 0.35; T1 2.56 ± 0.36; p < 0.001). Conclusions: At the 2-week follow-up, pain relief was maintained, and shear wave velocity showed no further significant change. Shear wave velocity assessments might be considered a useful diagnostic tool. However, further research is needed to support the role of HPLT and shear wave velocity in the rehabilitation management of LE.

Genome-Wide Association Screens for Anterior Cruciate Ligament Tears.

BACKGROUND: The etiopathogenesis of ACL rupture is not clarified. The aim of this study is to identify genomic regions and genetic variants relevant to anterior cruciate ligament injury susceptibility that could be involved in non-contact anterior cruciate ligament ruptures. METHODS: A systematic review of the literature was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines with a PRISMA checklist and algorithm. A search of PubMed, MEDLINE, CINAHL, Cochrane, EMBASE, and Google Scholar databases was conducted using combinations of the terms "anterior cruciate ligament", "ACL", "rupture", "genetics", "single nucleotide polymorphisms", and "SNP" since the inception of the databases until 2021. RESULTS: Twenty-three studies were included. A total of 7724 patients were analyzed. In total, 3477 patients had ACL ruptures and 4247 patients were controls. Genetic variants in genes encoding for collagens, elastin, fibrillin, matrix metalloproteinases, proteoglycans, angiogenesis-associated signaling cascade proteins, growth differentiation factors, tissue inhibitors of metalloproteases, interleukins, and fibrinogen were analyzed. CONCLUSION: Findings regarding the association between genes encoding for collagen (COL3A1, COL1A1, and COL12A1), aggrecan (ACAN), decorin (DCN), matrix metalloproteinase (MMP3), interleukin 6 (IL-6), vascular endothelial growth factor A (VEGFA), biglycan (BGN), fibrinogen (FGB), and ACL injuries were found to be inconclusive. Additional evidence is required in order to establish substantial conclusions regarding the association between genetic variants and ACL rupture.

Epidemiology of Spondylolisthesis: A Nationwide Study From 2001 to 2016 in the Italian Population.

STUDY DESIGN: Epidemiological study. OBJECTIVE: This study aimed to evaluate the annual incidence of spondylolisthesis requiring surgery in Italy and the epidemiological characteristics of the patients. BACKGROUND: The health care system continues to incur considerable costs as a result of low-back pain. Segmental instability of the lumbar spine has attracted significant interest from researchers as a potential mechanism leading to mechanical low back pain. MATERIALS AND METHODS: The Italian Ministry of Health's National Hospital Discharge Reports database in the 2001-2016 period was considered. RESULTS: A total of 55,804 hospital admissions for spondylolisthesis were performed in Italy. The cumulative incidence was 6.8 interventions for every 100,000 Italian adult residents. The highest amount of procedures was recorded in the 65-69 years of age group. The overall patient's age was 56.8 ± 15.1 years. The 62.2% of patients were females. The average hospital stay length was 8.1 ± 7.3 days. On average, older patients require more days of hospital stay. Over the study period, it was observed a decreasing trend in the average number of days of hospital stay. The main primary diagnoses included were "acquired spondylolisthesis" [International Classification of Diseases (ICD) code: 738.4; 57.8%] and "spondylolisthesis" (ICD code: 756.12; 42.2%). By far, the main primary procedure performed was "lumbar and lumbosacral fusion of the anterior column, posterior technique" (ICD code: 81.08; 60.3%). CONCLUSIONS: Spondylolisthesis is a problem in Italy and a leading cause requiring spine surgery. Females were the majority of patients requiring surgery for spondylolisthesis. However, for younger age groups, males showed superior or equal need for spine surgery. The socioeconomic impact of spondylolisthesis in Italy is relevant, affecting patients still in the working population. The increasing trend of spine surgery for spondylolisthesis in Italy may be attributable to the widespread diffusion of modern diagnostic and surgical technologies. LEVEL OF EVIDENCE: Level II.

Role of the Gut Microbiota in Osteoarthritis, Rheumatoid Arthritis, and Spondylarthritis: An Update on the Gut-Joint Axis.

Dysregulation of the gut microbiota and their metabolites is involved in the pathogenic process of intestinal diseases, and several pieces of evidence within the current literature have also highlighted a possible connection between the gut microbiota and the unfolding of inflammatory pathologies of the joints. This dysregulation is defined as the "gut-joint axis" and is based on the joint-gut interaction. It is widely recognized that the microbiota of the gut produce a variety of compounds, including enzymes, short-chain fatty acids, and metabolites. As a consequence, these proinflammatory compounds that bacteria produce, such as that of lipopolysaccharide, move from the "leaky gut" to the bloodstream, thereby leading to systemic inflammation which then reaches the joints, with consequences such as osteoarthritis, rheumatoid arthritis, and spondylarthritis. In this state-of-the-art research, the authors describe the connections between gut dysbiosis and osteoarthritis, rheumatoid arthritis, and spondylarthritis. Moreover, the diagnostic tools, outcome measures, and treatment options are elucidated. There is accumulating proof suggesting that the microbiota of the gut play an important part not only in immune-mediated, metabolic, and neurological illnesses but also in inflammatory joints. According to the authors, future studies should concentrate on developing innovative microbiota-targeted treatments and their effects on joint pathology as well as on organizing screening protocols to predict the onset of inflammatory joint disease based on gut dysbiosis.

Arthroscopic microfracture and associated techniques in the treatment of osteochondral lesions of the talus: A systematic review and metanalysis.

BACKGROUND: Osteochondral lesions of the talus are common in patients suffering even minor trauma; timely diagnosis and treatment can prevent the development of early osteoarthritis. The objectives of this systematic review and meta-analysis were to evaluate the effects of additional procedures on arthroscopic ankle microperforations for osteochondral lesions. METHODS: A systematic literature search was conducted using PubMed-Medline, Cochrane Central, and Google Scholar to select clinical studies analyzing the efficacy of platelet-rich plasma (PRP), hyaluronic acid (HA), and bone marrow concentrate (BMC) procedures. Ten articles following PRISMA guidelines with a total of 464 patients were included in this review. Quality assessment using MINORS was performed, and all studies demonstrated high quality. RESULTS: The results of the systematic review showed benefits in all patients undergoing infiltrative therapy with PRP, hyaluronic acid, and BMC. The best results in terms of AOFAS score and VAS scale were found in patients undergoing PRP injection. The meta-analysis showed improvements in pain relief and return to daily activities in patients undergoing arthroscopic microperforations and PRP, although not reporting statistically significant results (p = 0.42). CONCLUSION: All treatment strategies reported better scores compared to the control groups. Among the various treatments analyzed, the addition of PRP appears to be the most valuable probably for the larger population receiving this treatment, showing excellent outcomes in pain reduction, clinical outcomes, and return to daily activities. LEVEL OF EVIDENCE: II.

Comparison of knee flexor strength recovery between semitendinosus alone versus semitendinosus with gracilis autograft for ACL reconstruction: a systematic review and meta-analysis.

BACKGROUND: Whether there is a difference in harvesting the semitendinosus tendon alone (S) or in combination with the gracilis tendon (SG) for the recovery of knee flexor strength after anterior cruciate ligament (ACL) reconstruction remains inconclusive. Therefore, this study aimed to assess the recovery of knee flexor strength based on the autograft composition, S or SG autograft at 6, 12, and ≥ 24 months after ACL reconstruction. METHODS: A systematic review and meta-analysis was conducted following the PRISMA guidelines. A comprehensive search was performed encompassing the Cochrane Library, Embase, Medline, PEDRo and AMED databases from inception to January 2023. Inclusion criteria were human clinical trials published in English, comprised of randomized controlled trials (RCTs), longitudinal cohort-, cross-sectional and case-control studies that compared knee flexor strength recovery between S and SG autografts in patients undergoing primary ACL reconstruction. Isokinetic peak torques were summarized for angular velocities of 60°/s, 180°/s, and across all angular velocities, assessed at 6, 12, and ≥ 24 months after ACL reconstruction. A random-effects model was used with standardized mean differences and 95% confidence intervals. Risk of bias was assessed with the RoBANS for non-randomized studies and the Cochrane RoB 2 tool for RCTs. Certainty of evidence was appraised using the GRADE working group methodology. RESULTS: Among the 1,227 patients from the 15 included studies, 604 patients received treatment with S autograft (49%), and 623 received SG autograft (51%). Patients treated with S autograft displayed lesser strength deficits at 6 months across all angular velocities d = -0.25, (95% CI -0.40; -0.10, p = 0.001). Beyond 6 months after ACL reconstruction, no significant difference was observed between autograft compositions. CONCLUSION: The harvest of S autograft for ACL reconstruction yields superior knee flexor strength recovery compared to SG autograft 6 months after ACL reconstruction, irrespective of angular velocity at isokinetic testing. However, the clinical significance of the observed difference in knee flexor strength between autograft compositions at 6 months is questionable, given the very low certainty of evidence and small effect size. There was no significant difference in knee flexor strength recovery between autograft compositions beyond 6 months after ACL reconstruction. TRIAL REGISTRATION: CRD42022286773.

The influence of gut microbiome on periprosthetic joint infections: State-of-the art.

Early periprosthetic joint infection constitutes one of the most frightening complications of joint replacement. Recently, some evidence has highlighted the potential link between dysregulation of the gut microbiota and degenerative diseases of joints. It has been hypothesized that microbiome dysbiosis may increase the risk of periprosthetic joint infection by facilitating bacterial translocation from these sites to the bloodstream or by impairing local or systemic immune responses. Although the processes tying the gut microbiome to infection susceptibility are still unknown, new research suggests that the presurgical gut microbiota-a previously unconsidered component-may influence the patient's ability to resist infection. Exploring the potential impact of the microbiome on periprosthetic joint infections may therefore bring new insights into the pathogenesis and therapy of these disorders. For a successful therapy, a proper surgical procedure in conjunction with an antibacterial concept is essential. As per the surgical approach, different treatment strategies include surgical irrigation, debridement, antibiotic therapy, and implant retention with or without polyethylene exchange. Other alternatives could be one-stage or two-stage revisions surgery. Interventions that either directly target gut microbes as well as interventions that modify the composition and/or function of the commensal microbes represent an innovative and potentially successful field to be explored. In recent times, innovative therapeutic methods have arisen in the realm of microbiome restoration and the management of gut-related ailments. These progressive approaches offer fresh perspectives on tackling intricate microbial imbalances in the gastrointestinal tract. These emerging therapies signify a shift towards more precise and individualized approaches to microbiome restoration and the management of gut-related disorders. Once a more advanced knowledge of the pathways linking the gut microbiota to musculoskeletal tissues is gained, relevant microbiome-based therapies can be developed. If dysbiosis is proven to be a significant contributor, developing treatments for dysbiosis may represent a new frontier in the prevention of periprosthetic joint infections.

Machine learning can predict anterior elevation after reverse total shoulder arthroplasty: A new tool for daily outpatient clinic?

The aim of the present study was to individuate and compare specific machine learning algorithms that could predict postoperative anterior elevation score after reverse shoulder arthroplasty surgery at different time points. Data from 105 patients who underwent reverse shoulder arthroplasty at the same institute have been collected with the purpose of generating algorithms which could predict the target. Twenty-eight features were extracted and applied to two different machine learning techniques: Linear regression and support vector regression (SVR). These two techniques were also compared in order to define to most faithfully predictive. Using the extracted features, the SVR algorithm resulted in a mean absolute error (MAE) of 11.6° and a classification accuracy (PCC) of 0.88 on the test-set. Linear regression, instead, resulted in a MAE of 13.0° and a PCC of 0.85 on the test-set. Our machine learning study demonstrates that machine learning could provide high predictive algorithms for anterior elevation after reverse shoulder arthroplasty. The differential analysis between the utilized techniques showed higher accuracy in prediction for the support vector regression. Level of Evidence III: Retrospective cohort comparison; Computer Modeling.

Debridement, antibiotics, and implant retention (DAIR) for the early prosthetic joint infection of total knee and hip arthroplasties: a systematic review.

PURPOSE: Early periprosthetic joint infection (PJI) represents one of the most fearsome complications of joint replacement. No international consensus has been reached regarding the best approach for early prosthetic knee and hip infections. The aim of this updated systematic review is to assess whether debridement, antibiotics, and implant retention (DAIR) is an effective choice of treatment in early postoperative and acute hematogenous PJI. METHODS: This systematic review was performed using the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines. The diagnostic criteria defining a PJI, the most present pathogen, and the days between the index procedure and the onset of the PJI were extracted from the selected articles. Additionally, the mean follow-up, antibiotic regimen, and success rate of the treatment were also reported. RESULTS: The articles included provided a cohort of 970 patients. Ten studies specified the joint of their cohort in PJIs regarding either hip prostheses or knee prostheses, resulting in 454 total knees and 460 total hips. The age of the patients ranged from 18 to 92 years old. Success rates for the DAIR treatments in the following cohort ranged from 55.5% up to a maximum of 90% (mean value of 71%). CONCLUSION: Even though the DAIR procedure is quite limited, it is still considered an effective option for patients developing an early post-operative or acute hematogenous PJI. However, there is a lack of studies, in particular randomized control trials (RCTs), comparing DAIR with one-stage and two-stage revision protocols in the setting of early PJIs, reflecting the necessity to conduct further high-quality studies to face the burden of early PJI.

Evaluating the Minimum Clinically Important Difference and Patient Acceptable Symptom State for the Womac Osteoarthritis Index after Unicompartmental Knee Arthroplasty.

Patient-Reported Outcome Measures (PROMs) are standardized questionnaires that gather information on health-related quality of life directly from patients. Since a significant statistical mean change may not correspond to a clinical improvement, there is a need to calculate a considerable change in scores. This is done by the Minimum Clinically Important Difference (MCID) and Patient Acceptable Symptom State (PASS). The objective of this article is to report the MCID and the PASS values of the WOMAC (Western Ontario and McMaster University) osteoarthritis index for patients undergoing Unicompartmental Knee Arthroplasty (UKA). A total of 37 patients (25 females and 12 males; mean age 68 ± 8.1 years and mean BMI 28.7 ± 4) who underwent UKA were enrolled. All patients were assessed using the WOMAC and the Oxford Knee Score (OKS) questionnaires before and six months following the procedure. To measure the cut-off values for MCID, distribution methods and anchor methods were applied, while the PASS was assessed only via anchor approaches. The MCID related to the WOMAC average global score was 90.7 ± 7.6, the average pain dimension score was 93.2 ± 6.6, the average stiffness dimension score was 92.6 ± 17, and the average physical function dimension score was 89.7 ± 7.6. In terms of PASS, the normalized WOMAC was 82.8, the pain dimension was 87.5, the stiffness dimension was 93.7, and the functional dimension was 83.1. A 34.5 amelioration in the WOMAC score, from initial evaluation to final follow-up, using change in OKS > 5 as anchor, indicates that the patients' health state improved to a clinically significant degree. A value at least of 82.8 in WOMAC score after treatment denotes that the symptom state is deemed acceptable by most of the patients.

Influence of Lateralization and Distalization on Joint Function after Primary Reverse Total Shoulder Arthroplasty.

The purpose of this study was to investigate how lateralization shoulder angle (LSA) and distalization shoulder angle (DSA) are related to clinical and kinematic outcomes after reverse total shoulder arthroplasty. Thirty-three patients were evaluated at least six months postoperatively. The Single Assessment Numeric Evaluation (SANE), Constant Murley Score (CMS), Simple Shoulder Test (SST), and Visual Analogue Scale (VAS) were used. Shoulder kinematics was evaluated with a stereophotogrammetric system. LSA and DSA inter-rater reliability was analysed through the interclass correlation coefficient (ICC). Stepwise forward linear regression analysis was conducted between LSA and DSA with clinical scales and kinematic measures, between which a correlation analysis was conducted. The inter-rater reliability for LSA (mean ICC = 0.93) and DSA (mean ICC = 0.97) results were good to excellent. Greater LSA values were associated with higher peaks of internal rotation (p = 0.012, R2 = 0.188) and range of motion (ROM) (p = 0.037, R2 = 0.133). SANE (p = 0.009), CMS (p = 0.031), and SST (0.026) were positively correlated to external rotation, while VAS (p = 0.020) was negatively related. Abduction peaks were positively related to CMS (p = 0.011) and SANE (p = 0.037), as well as abduction ROM (SANE, p = 0.031; CMS, p = 0.014).

Conservative Management of Partial Thickness Rotator Cuff Tears: A Systematic Review.

BACKGROUND: Conservative management has emerged as an attractive option for partial thickness rotator cuff tears (PT-RCTs). A single algorithmic treatment strategy for patients with symptomatic PT-RCT has not yet been developed. This systematic review aims to ascertain whether a conservative approach to PT-RCTs yields positive results in terms of clinical outcomes and functional recovery. METHODS: This is a systematic review of the literature on patients with PT-RCTs receiving conservative treatment with physiotherapy, platelet-rich plasma (PRP) injections, collagen injections, hyaluronic acid (HA) injections, or corticosteroids injections coupled with polydeoxyribonucleotide (PDRN). Outcomes such as the Visual Analog Scale (VAS) for pain, American Shoulder and Elbow Surgeons and Constant-Murley Score evaluations, as well as the Shoulder Pain and Disability Index and Euro Quality of Life-5D questionnaires were reported following a conservative approach. RESULTS: Eleven studies were included. Six articles explored the outcomes of patients with PT-RCT treated with PRP injections. Significant improvements in VAS for pain were observed. Two studies examined collagen injections and reported variations in VAS for pain and Constant-Murley Score. Sodium hyaluronate and HA injections were studied in two other articles, showing notable improvements in American Shoulder and Elbow Surgeons scores. Corticosteroid and PDRN injections also displayed favorable outcomes. In addition, physical therapy protocols demonstrated improvements in VAS for pain and strength, particularly with eccentric rehabilitation. CONCLUSIONS: Conservative management of PT-RCTs, involving physical therapy, PRP injections, collagen injections, corticosteroid injections, HA injections, and PDRN in jections, demonstrates favorable clinical outcomes. In addition, favorable results are observed in terms of decreased tear width and improved strength recovery, at least during a short-term follow-up. Unfortunately, long-term insight into the structural integrity of conservatively treated rotator cuff tendons following a partial injury has not been thoroughly evaluated yet. STUDY DESIGN LEVELS OF EVIDENCE: Level IV-systematic review.

Performance Evaluation of an Immersive Virtual Reality Application for Rehabilitation after Arthroscopic Rotator Cuff Repair.

Few studies have evaluated the effectiveness of shoulder rehabilitation in virtual environments. The objective of this study was to investigate the performance of a custom virtual reality application (VR app) with a stereophotogrammetric system considered the gold standard. A custom VR app was designed considering the recommended rehabilitation exercises following arthroscopic rotator cuff repair. Following the setting of the play space, the user's arm length, and height, five healthy volunteers performed four levels of rehabilitative exercises. Results for the first and second rounds of flexion and abduction displayed low total mean absolute error values and low numbers of unmet conditions. In internal and external rotation, the number of times conditions were not met was slightly higher; this was attributed to a lack of isolated shoulder movement. Data is promising, and volunteers were able to reach goal conditions more often than not. Despite positive results, more literature comparing VR applications with gold-standard clinical parameters is necessary. Nevertheless, results contribute to a body of literature that continues to encourage the application of VR to shoulder rehabilitation programs.

Immersive virtual reality for shoulder rehabilitation: evaluation of a physical therapy program executed with oculus quest 2.

BACKGROUND: Virtual Reality (VR) systems have been increasingly used across several medical fields. A crucial preliminary step for developing optimized VR-based applications for rehabilitation purposes is identifying potential interventions to meet the requirements necessary to satisfy end-users' needs. This study aims to assess the acceptability, usability, and appropriateness of a VR physical therapy program executed with Oculus Quest 2 by expert physiotherapists of shoulder musculoskeletal rehabilitation. METHODS: Eleven physiotherapists were enrolled to test a VR program for shoulder musculoskeletal rehabilitation. At the end of each session, physiotherapists completed three questionnaires about the acceptability, usability, and appropriateness of the VR system and application, investigating aspects such as wearability, safety, stability, ease of control, comfort, size, utility, playability, and use mode. RESULTS: The acceptability questionnaire revealed that all the physiotherapists found the VR system easy to wear and control, very confident, and safe. The usability questionnaire showed that most physiotherapists (73%) found the VR application entertaining, although only 45% said the system could be used independently by patients without the support of a therapist. Many physiotherapists found the use of the VR application appropriate for patients with rotator cuff tears treated conservatively (63.6%) or surgically (54.5%), for patients with shoulder osteoarthritis treated conservatively (72.7%), for patients with shoulder osteoarthritis after surgical treatment (63.6%). 91% of physiotherapists think it would be best for patients to use the VR system under the supervision of a therapist and not independently in a home setting. CONCLUSIONS: The use of VR in orthopaedic rehabilitation is encouraging, although further efforts are needed to increase the independent use of patients without the supervision of a physiotherapist. Moreover, future studies should strive to ensure the clinical effectiveness of VR rehabilitation in reaching therapeutic goal settings.

A practical guide to the implementation of AI in orthopaedic research - part 1: opportunities in clinical application and overcoming existing challenges.

Artificial intelligence (AI) has the potential to transform medical research by improving disease diagnosis, clinical decision-making, and outcome prediction. Despite the rapid adoption of AI and machine learning (ML) in other domains and industry, deployment in medical research and clinical practice poses several challenges due to the inherent characteristics and barriers of the healthcare sector. Therefore, researchers aiming to perform AI-intensive studies require a fundamental understanding of the key concepts, biases, and clinical safety concerns associated with the use of AI. Through the analysis of large, multimodal datasets, AI has the potential to revolutionize orthopaedic research, with new insights regarding the optimal diagnosis and management of patients affected musculoskeletal injury and disease. The article is the first in a series introducing fundamental concepts and best practices to guide healthcare professionals and researcher interested in performing AI-intensive orthopaedic research studies. The vast potential of AI in orthopaedics is illustrated through examples involving disease- or injury-specific outcome prediction, medical image analysis, clinical decision support systems and digital twin technology. Furthermore, it is essential to address the role of human involvement in training unbiased, generalizable AI models, their explainability in high-risk clinical settings and the implementation of expert oversight and clinical safety measures for failure. In conclusion, the opportunities and challenges of AI in medicine are presented to ensure the safe and ethical deployment of AI models for orthopaedic research and clinical application. Level of evidence IV.

Economic Evaluation of a Bioinductive Implant for the Repair of Rotator Cuff Tears Compared with Standard Surgery in Italy.

INTRODUCTION: Rotator cuff tear (RCT) is a painful, progressive condition resulting from damage to the rotator cuff tendons and is the leading cause of shoulder-related disability. Surgical repair of rotator cuff is an established standard of care (SOC); however, failure of the procedure can occur. In this context, the use of collagen-based bioinductive implant REGENETEN showed long-term improvements in clinical scores. The aim of the study was to assess the cost-effectiveness of REGENETEN combined with SOC (SOC + REGENETEN) compared to SOC alone from both National Healthcare Service (NHS) and societal perspectives in Italy. METHODS: A decision analytic model was developed to estimate the number of tears healed and costs for the two considered treatment strategies over 1 year. Clinical data were retrieved from the literature, and the clinical pathways for the management of patients with RCTs were retrieved from four key opinion leaders in Italy. RESULTS: Over a 1-year time horizon, healed lesions were 90.70% and 72.90% for surgical repair of RCTs with and without REGENETEN, respectively. Considering the NHS perspective, mean costs per patient were €7828 and €4650 for the two strategies, respectively, leading to an incremental cost-effectiveness ratio (ICER) of €17,857 per healed tear. From the societal perspective, the mean costs per patient were €12,659 for SOC and €11,784 for REGENETEN, thus showing savings of €4918 per healed tear when the bioinductive implant is used. The sensitivity analyses confirmed the robustness of the model results. CONCLUSION: In the context of paucity of cost-effectiveness studies, our findings provide additional evidence for clinicians and payers regarding the value of a new treatment option that supports a tailored approach for the management of patients with RCTs.

The rotator cuff refers to a group of four muscles, with tendons connected to the upper arm bone, which act together to allow lifting and rotating the shoulder. A tear of the rotator cuff can affect either a single tendon or multiple tendons. Typical first-line treatment includes conservative therapies, which aim to alleviate pain and reduce functional impairment, but are often ineffective. Persisting disease is usually managed through conventional surgical repair. Recently, REGENETEN, a collagen-based bioinductive implant derived from purified bovine Achilles tendon, positioned over the site of the damaged rotator cuff, achieved successful rotator cuff tendon repair with an increase in healed tears of 17.80% at 1 year compared to conventional surgery. Considering the National Healthcare Service perspective in Italy, the cost needed to achieve one additional healed tear using REGENETEN compared to conventional surgery is €17,857. From the societal perspective, which includes patients' productivity losses from hospital admission to return to work, the use of REGENETEN may be cost-saving compared to conventional surgery. The findings of our study provide evidence for clinicians and payers to support the value of a new treatment option for patients with rotator cuff lesions.

Application of Machine Learning Algorithms for Prognostic Assessment in Rotator Cuff Pathologies: A Clinical Data-Based Approach.

AIM: The overall aim of this proposal is to ameliorate the care of rotator cuff (RC) tear patients by applying an innovative machine learning approach for outcome prediction after arthroscopic repair. MATERIALS AND METHODS: We applied state-of-the-art machine learning algorithms to evaluate the best predictors of the outcome, and 100 RC patients were evaluated at baseline (T0), after 1 month (T1), 3 months (T2), 6 months (T3), and 1 year (T4) from surgical intervention. The outcome measure was the Costant-Murley Shoulder Score, whereas age, sex, BMI, the 36-Item Short-Form Survey, the Simple Shoulder Test, the Hospital Anxiety and Depression Scale, the American Shoulder and Elbow Surgeons Score, the Oxford Shoulder Score, and the Shoulder Pain and Disability Index were considered as predictive factors. Support vector machine (SVM), k-nearest neighbors (k-NN), naïve Bayes (NB), and random forest (RF) algorithms were employed. RESULTS: Across all sessions, the classifiers demonstrated suboptimal performance when using both the complete and shrunken sets of features. Specifically, the logistic regression (LR) classifier achieved a mean accuracy of 46.5% ± 6%, while the random forest (RF) classifier achieved 51.25% ± 4%. For the shrunken set of features, LR obtained a mean accuracy of 48.5% ± 6%, and RF achieved 45.5% ± 4.5%. No statistical differences were found when comparing the performance metrics of ML algorithms. CONCLUSIONS: This study underlines the importance of extending the application of AI methods to new predictors, such as neuroimaging and kinematic data, in order to better record significant shifts in RC patients' prognosis. LIMITATIONS: The data quality within the cohort could represent a limitation, since certain variables, such as smoking, diabetes, and work injury, are known to have an impact on the outcome.