Aim. Hand-disinfection (HD) is the most effective infection-prevention-measure. HD-performance of health care professionals (HCP) is usually evaluated by compliance observations (CO). The Hawthorne effect (HE) (HCP behave differently under observation) is considered to systematically increase HD-compliance-rates during CO. However, little is known about the specifications of the HE in health care settings. We hypothesized that, due to hand-hygiene`s known impact on patient safety and infection-prevention, the HE does not affect HD performance during direct patient care in patient-rooms. Method. We conducted a prospective observational trial on an 18-bed surgical intensive care unit (ICU), a 12-bed surgical intermediate care unit (IMC) and a 36-bed surgical normal ward (NW) in a university hospital in Germany. Dispensers of hand sanitizers were equipped with an electronic monitoring system (EMS) (GWA Hygiene, Germany), which recorded the number of HDs per patient hour (HD/PH) and time and location of hand-disinfections. Locations were categorized as follows: 1. Patient rooms (PR); 2. Utility- and waste-disposal-rooms (UWR) and 3. Other rooms (hallways, kitchen, toilets etc.) (OR). Additionally trained infection-control-staff performed hand-hygiene CO according to WHO's Five Moments. The HD/PH during CO was compared to the HD/PH during the same time-periods without CO. Additionally the ratio between HD/PD-change during CO and mean-HD/PD of each ward during the study-period was determined in percentages. Descriptive and analytical statistics were calculated using R. P-values ≤ 0.05 were regarded as significant. Results. 587.128 HD were electronically recorded during the study-period (February 2022 to May 2023) and CO took place on 72 days. We recorded a significant increase of HD/PH during CO on all three wards in PRs (ICU: 21%, p<0.001; IMC: 11%, p=0.029; NW: 49%, p=0.047). Furthermore we detected a significant increase of HD/PH during CO on ICU (10%, p<0.001) and IMC (11%, p=0.033) in ORs. CO did not significantly affect HD/PH in ORs on NW and in UWR on all three wards. Conclusions. In our setting, the number of hand-disinfections per patient-hour was significantly increased during compliance-observations especially in patient-rooms, where hand-hygiene is most crucial for infection-prevention. This indicates a lower everyday compliance to WHO`s hand-hygiene indications during patient care than determined by compliance-observations. Acknowledgments. Paul-Hartmann AG financially supported this study

To examine whether Natural Language Processing (NLP) using a state-of-the-art clinically based Large Language Model (LLM) could predict patient selection for Total Hip Arthroplasty (THA), across a range of routinely available clinical text sources. Data pre-processing and analyses were conducted according to the Ai to Revolutionise the patient Care pathway in Hip and Knee arthroplasty (ARCHERY) project protocol (. https://www.researchprotocols.org/2022/5/e37092/. ). Three types of deidentified Scottish regional clinical free text data were assessed: Referral letters, radiology reports and clinic letters. NLP algorithms were based on the GatorTron model, a Bidirectional Encoder Representations from Transformers (BERT) based LLM trained on 82 billion words of de-identified clinical text. Three specific inference tasks were performed: assessment of the base GatorTron model, assessment after model-fine tuning, and external validation. There were 3911, 1621 and 1503 patient text documents included from the sources of referral letters, radiology reports and clinic letters respectively. All letter sources displayed significant class imbalance, with only 15.8%, 24.9%, and 5.9% of patients linked to the respective text source documentation having undergone surgery. Untrained model performance was poor, with F1 scores (harmonic mean of precision and recall) of 0.02, 0.38 and 0.09 respectively. This did however improve with model training, with mean scores (range) of 0.39 (0.31–0.47), 0.57 (0.48–0.63) and 0.32 (0.28–0.39) across the 5 folds of cross-validation. Performance deteriorated on external validation across all three groups but remained highest for the radiology report cohort. Even with further training on a large cohort of routinely collected free-text data a clinical LLM fails to adequately perform clinical inference in NLP tasks regarding identification of those selected to undergo THA. This likely relates to the complexity and heterogeneity of free-text information and the way that patients are determined to be surgical candidates

Current fracture-clinic models, especially in the advent of reductions in junior doctors hours, may limit outpatient trainee education and patient care. We designed a new model of fracture-clinic, involving an initial consultant led case review focused on patient management and trainee education. Outcomes for all new patients attending the redesigned fracture-clinic over a 3-week period in 2010 were compared with the traditional clinic in the same period in 2009. Health professionals completed a Likert questionnaire assessing their perceptions of education, support, standards of patient care and morale before and after the clinic redesign. 309 and 240 patients attended the clinics in 2009 and 2010 respectively. There was an increase in consultant input into patient management after the redesign (29% versus 84%, p<0.0001), while the proportion of patients requiring physical review by a consultant fell (32% versus 9%). The percentage of new patients discharged by junior medical staff increased (17% versus 25%) with a reciprocal fall in return appointments (55% versus 40%, p<0.0005). Overall, return appointment rates fell significantly (55% versus 40%, p=0.013). Staff perception of education and senior support improved from 2 to 5, morale and overall perception of patient care from 4 to 5. Our model of fracture-clinic redesign has significantly enhanced consultant input into patient care without additional funding. In addition, we have demonstrated increased service efficiency and significant improvements in staff support, morale and education. In the face of current economic and training challenges, we recommend this new model as a tool for enhancing patient and trainee experiences

Aims. Current antibiotic treatment strategies for prosthetic joint infection (PJI) are based mostly on observational retrospective studies. High-quality data from prospective cohorts using identical treatment strategies may improve current clinical practice. We developed a regional network of collaborating hospitals and established a uniform treatment protocol. Data from all patients diagnosed with a PJI are prospectively registered in a an online database. With this quality registry we aim to study the outcome of antibiotic and surgical strategies while adhering to a pre-established treatment protocol. Methods. A working group of orthopaedic surgeons, infectious disease specialists and microbiologists was established. The working group reached consensus on definition of PJI and a uniform treatment protocol, based on current guidelines and expert-based clinical experience. A website was built to communicate information to colleagues and patients (. www.protheseinfectie.nl. ). In each participating hospital weekly multidisciplinary meetings were started to discuss all PJI cases. All patients are included in an online quality registry and followed for at least two years. We aim to enroll >600 patients with a knee or hip PJI. Research will focus on the duration of antibiotic treatment, antibiotic suppressive therapy and comparison of different oral antibiotic treatment strategies in relation to successful treatment outcomes. Results. Currently, four regional hospitals are included in the partnership. Multidisciplinary meetings have lowered the threshold to discuss patients, and the adherence to the PJI treatment protocol has improved steadily. Complicated cases are discussed between colleagues from collaborating centers. The collaboration has been perceived as very successful by the participating hospitals. Since 2015, over 300 patients have been included, of whom 52% were male. In 26%, PJI occurred after revision surgery. Staphylococcus aureus was involved in 25% of cases, coagulase-negative Staphylococci in 23%, Streptococci in 13% and Gram-negative micro-organisms in 15%. Conclusions. In this project, collaboration between different medical specialties through multidisciplinary meetings was the key to the improvement of patient care The regional collaborative project led to the implementation of a uniform treatment protocol for PJI. With this prospective project we aim to improve patient care by providing evidence for optimal antibiotic and surgical strategies for PJI. Ideally, countries should have hospital networks and a uniform method of data collection to make it easy to share data for scientific research

Current fracture-clinic models, especially in the advent of reductions in junior doctors hours, may limit outpatient trainee education and patient care. We designed a new model of fracture-clinic, involving an initial consultant led case review focused on patient management and trainee education. Prospective outcomes for all new patients attending the redesigned fracture-clinic over a 3-week period in 2010 (n=240) were compared with the traditional clinic in the same period in 2009(n=296). Trainees attending the fracture clinic completed a Likert questionnaire (1 [strongly dissagree] − 5 [strongly agree]) assessing the adequacy of education, support, staff morale & standards of patient care. The percentage of cases given consultant input increased significantly from 33% in 2009 to 84% in 2010 (p< 0.0001), while the proportion of patients requiring physical review by a consultant fell by 21% (p< 0.0001). Return rates were reduced by 14.3% (p< 0.013) & utilization of the nurse lead fracture clinic improved by 10.1% (p< 0.0028). These improvements were most marked in the target group ?StR2 (24.2% & 22.3% respectively). There were significant improvements in staff perception of their education from 2 to 4.75 (p< 0.0001), provision of senior support from 2.38 to 4.5 (p=0.019), morale from 3.68 to 4.13 (p=0.0331) & their overall perception of patient care from 3.25 to 4.5 (p=0.0016). A&E staff found the new style clinic educational, practice changing & that it improved interdisciplinary relations, but did not interfere with their A&E duties. Our model of fracture-clinic redesign has significantly enhanced consultant input into patient care without additional funding. In addition, we have demonstrated increased service efficiency and significant improvements in staff support, morale and education. In the face of current economic and training challenges, we recommend this new model as a tool for enhancing patient and trainee experiences

Purpose. Introduce an Integrated Approach for Orthopedic-Sports Medicine Practice and Patient Care Management that. Is built around effective and efficient surgical techniques, and patient care management processes. Integrates Operations and Service Excellence best practices with patient care management processes. Integrates orthopedic care delivery between outpatient clinic, pre-surgery, surgery, inpatient, (acute care) and post acute care settings. Delivers exceptional clinical, patient satisfaction and financial outcomes as validated by independent national healthcare benchmarking organization. Helps position Ortho-Sports medicine services for strategic growth. Is replicable to develop Ortho-Sports Medicine Centers of Excellence. Presentation illustrates the ‘Ten Elements’ approach to implement the Ortho-Sports Medicine Centers of Excellence and demonstrate the effectiveness of the approach with an outcomes study from over 1000 total knee arthroplasty (TKA) procedures. During the presentation, the speakers would share the key clinical, patient satisfaction, and financial outcomes achieved by the implementation of the best practices defined in our ‘Ten Elements’ approach. All performance data elements are collected, validated and analyzed by an independent third party, national healthcare benchmarking company. During the presentation Dr. Bramlett would elaborate on the surgical protocol, and the key differentiating steps in procedure technique from traditional approach that significantly enhances procedure effectiveness, efficiency and lowers the patient complication rate as demonstrated by benchmarking data. Speakers would further present the key elements of Total Knee Arthoplasty procedure that focus on patient education, patient participation in pre-surgical weight loss and pre-habilitation program, anesthesia approach, avoiding tourniquet use and deep veen thrombosis (DVT) risk reduction, early post operative patient ambulation and weight bearing, and post operative patient management approach. On average the ortho-sports medicine clinical of Alabama TKA patients are disharged from the hospital in 2.6 days, and experience 65 percent less complications than expected for a similar patient population and assume early control of their independent functionality

Background. Benefits of day case foot and ankle surgery includes reduced hospital stay, associated cost savings for the hospital, high patient satisfaction and quicker recovery with no increase in complication rates. In 2007, we set up the preoperative foot and ankle group. Patients were seen three weeks before surgery by a specialist nurse, physiotherapist and a preoperative evaluation is done. The therapist explains the patient's weightbearing status and advices on how to carry this out. Our aim was to reduce inpatient hospital stay and increase our day case procedures. Methods. We evaluated length of stay and physiotherapy intervention for all our patients during the first three months of 2007 to 2011. Mean length of stay was calculated and Mann-Whitney U test was performed using median. Results. Mean length of stay for combined forefoot and midfoot group reduced by 1.92 days and median reduction was statistically significant(p< 0.01). For forefoot surgery alone, the mean length reduced by 2.14 and median reduction was significant(p< 0.001) and for midfoot surgery alone, the mean stay reduced by 1.34 days and median was significant (p< 0.001). Hind foot patient's mean length of stay reduced by 6.78 days and the median was significant (p< 0.001). But for the ankle group the mean length of stay did reduce but the median was not statistically significant (p=0.225). Day case surgery increased by 43.5% for forefoot, 23.2% for midfoot and 14% for ankle surgeries but not for hindfoot. Conclusions. The overall results show that the preoperative foot and ankle group has resulted in reduction of inpatient stay and increase in daycase surgery performed. A pre-operative group is a highly efficient method of enhancing patient care and improving length of stay at the hospital for the patient. The cost saving for the hospital is around £35,400 per annum

Introduction: Technical and patient care improvements have occurred with the posterior mini-incision total hip replacement (THR). The hypothesis of this study was that these changes would provide better results for patients in the posterior mini incision surgery (MIS) THRs performed in our institution. Methods: The clinical and radiographic results of 100 THRs performed with the posterior mini incision between January 2004 and October 2004 were compared with 100 mini incision THRs performed between December 2001 and September 2002. The second group was subjected to improved operative technique, the post-operative analgesia protocol, rehabilitation and patient advise. The acetabular cup abduction angle, anteversion angle, and stem varus/valgus alignment angle were measured in the post-operative radiographs in both groups. Pain score and Harris hip score were recorded at 6 weeks and 3 months. Statistical analysis was performed using Student 2-tailed t test, Chi-squared test and Wilcoxon-Mann-Whitney tests to compare the incision length, operative time, estimated blood loss, length of hospital stay, pain score and radiographic measurements between the two groups. Results: The results showed that the component positions were not compromised in either group. There were statistical improvements in 2004 group with less estimated blood loss, decreased hospital stay, reduction of postoperative pain and opioid analgesic use and earlier muscle recovery. In 2004 group there were no complications of infection, dislocation, or sciatic palsy. Discussion: The posterior mini-incision operation has shown improved results with experience and changes in technique and patient care treatment. We have continued our practice using this new technique

Aim. A new multidisciplinary hip fracture pathway, based on national BOA and NICE guidance, was introduced in our institution to facilitate rapid preoperative medical optimisation and early surgery for patients with hip fractures. The aim of this audit was to assess its impact on patient care and outcomes. Method. A prospective audit of 161 patients admitted with a fractured neck of femur was conducted in the six months before (92 patients) and after (69 patients) implementation of the new pathway. Data included: time to orthogeriatric assessment (TtG); time to surgery (TtS); length of hospital stay (LOS); return to original accommodation; and inpatient mortality rate. Significance was tested using Chi Squared, Fisher's exact and unpaired Student t-Tests. Results. The two groups of patients were equivalent in terms of age, male:female ratio, ASA grade and preoperative AMTS. In the six months after the introduction of the pathway, 85% of patients received a pre-operative medical assessment compared to 19% before (p=0.0001). Average TtG dropped from 91 to 19 hours (p=0.0001). LOS dropped from 24.8 days to 19.5 days (p=0.029). Furthermore, a significant reduction in mortality of 10% (14% before, 4% after, p=0.0336) was found, with an increase in the proportion of patients returning to their original place of accommodation (57% before, 80% after, p=0.0069). Whilst limited by theatre scheduling, there was an observed reduction in TtS of 6 hours (37 vs 31, p=0.0663). Conclusions. Rapid medical optimisation and prompt surgery can significantly reduce length of stay and inpatient mortality of patients with hip fractures. This is especially important in light of their often fragile physiological state and complex co-morbidities. Successful implementation of a multidisciplinary hip fracture pathway can increase the return of patients to their preoperative accommodation, thus maintaining their level of pre-morbid independence and potentially leading to significant future cost savings

Introduction: The treatment of hip fracture patients differs widely throughout Europe. In the SAHFE project (Standardised Audit of Hip Fractures in Europe) it was found that both waiting time to operation and mean hospitalisation time for operated patients was considerably higher in certain Mediterranean countries compared to the Northern parts of Europe. Local tradition influences both the choice of operation method and the routines for rehabilitation. Background factors were rather similar with mean age around 80 years and a predominance of female patients, 75% were women. Experiences from good examples of treatment throughout Europe are important to optimise the overall hip fracture treatment of benefits both for the individual patient and for the society in form of resources needed. The costs for hip fracture treatment are already considerable and with an ageing population the resources for treatment of these patients need to be optimised throughout the world. With more elderly in the populations, the total number of hip fracture patients is prognosticated to increase 5 times in the next 50 years. This symposium deals with means to improve the treatment results by focusing on the patient to make possible the best rehabilitation results after different operative procedures. Examples will be given from centres who have worked on the whole treatment chain for these elderly resource consuming patients.

Alignment and soft tissue balance are two of the most important factors that influence early and long term outcome of total knee arthroplasty.

Current clinical practice involves the use of plain radiographs for preoperative planning and conventional instrumentation for intra operative alignment.

The aim of this study is to assess the Signature^TM Personalised system using patient specific guides developed from MRI. The Signature^TM system is used with the Vanguard^RComplete Knee System. This system is compared with conventional instrumentation and computer assisted navigation with the Vanguard system.

Patients were randomised into 3 groups of 50 to either Conventional Instumented Knee, Computer Navigation Assisted Knee Arthroplasty or Signature Personalised Knee Arthoplasty. All patients had the Vanguard Total knee Arthroplasty Implanted.

All patients underwent Long leg X-rays and CT Scans to measure Alignment at pre-op and 6 months post-op. All patients had clinical review and the Knee Society Score (KSS) at 1 year post surgery was used to measure the outcome.

A complete dataset was obtained for 124 patients. There were significant differences in alignment on Long leg films ot of CT scan with perth protocol. Notably the Signature group had the smallest spread of outliers.

In conclusion the Signature knee system compares well in comparison with traditional instrumentation and CAS Total Knee Arthroplasty.

This study aims to assess the impact of re-configuration on provision of trauma care at Hospital A, in particular management of hip fractures.

Originally, Hospitals A and B both provided trauma and elective orthopaedic services. These services are undergoing re-configuration such that Hospital A will provide an elective orthopaedic service while Hospital B will provide an orthopaedic trauma service.

Two time periods, one prior to reconfiguration (time period 1) and one after reconfiguration (time period 2) were identified. All trauma patients presenting to Hospital A requiring surgery during the defined time periods were included.

During time period 1, 197 patients requiring surgery presented to Hospital A, 70 with hip fractures. During time period 2, 149 patients requiring surgery presented to Hospital A, 55 with hip fractures.

As part of the reconfiguration process, there was a reduction in dedicated trauma operating capacity at Hospital A with no equivalent increase in operating capacity at Hospital B.

During time period 1, 70% of patients with hip fractures were operated on within 36 hours, compared to 44% during time period 2.

During the re-configuration process, there was a statistically significant decrease in the percentage of patients with hip fractures meeting the recommended standards of care.

ARI is a busy trauma unit (catchment: 500 000 people). In September 2010 a day-case Hand Trauma Service (HTS) started. Previously cases were often postponed due to prioritisation of orthopaedic emergencies; therefore increasing inpatient stay and associated costs. We aim to characterise presenting cases, evaluate improvements in service provision and financial costs.

Data was collected from the first HTS year (Sept 10–11), and the preceding year (Sept 09–10). Data was collected on patient characteristics, operation, operative time, anaesthetic type and number of inpatient days. The cost of inpatient stay was calculated from the NHS Scotland resource allocation committee data.

Pre HTS there were 410 cases (500 operative hours). 141 wound explorations, 22 nail-bed repairs, 34 metacarpal ORIF, 68 phalangeal ORIF, 5 scaphoid fixations, 69 tendon repairs, 30 terminalisations, 5 MUA, 19 nerve repairs, 17 unclassified. Accounting for 510 inpatient nights (mean: 1.25, range: 0–8), costing £204,387.60 (mean: £500.95). 123 cases required image intensification (II). Most patients had GA. During the first HTS year there were 282 operations. Most operations were day-case. 77 cases were performed under LA, 81 regional blocks and 34 under GA. During this year cases requiring II continued to be performed in the main theatre.

The HTS has increased time available in main theatres. It has reduced inpatient stay costs, potentially saving £141,267.90. Performing more operations under LA/regional block decreases the risks associated with anaesthesia. Provision of II for the HTS would permit more cases to be performed, improving the service provision and further reducing costs.

Objectives

Evidence -based medicine (EBM) is designed to inform clinical decision-making within all medical specialties, including orthopaedic surgery. We recently published a pilot survey of the Canadian Orthopaedic Association (COA) membership and demonstrated that the adoption of EBM principles is variable among Canadian orthopaedic surgeons. The objective of this study was to conduct a broader international survey of orthopaedic surgeons to identify characteristics of research studies perceived as being most influential in informing clinical decision-making.

Introduction

Superficial wound complications can occur in up to 10% of total knee arthroplasty (TKA) patients and have been associated with deep infection. The ideal material for TKA closure should fulfill the following requirements: 1) fast intraoperative application, 2) minimal wound complications and discomfort, and 3) can be removed by patients without a home care visit. We present our experience with a novel, non-invasive, removable skin closure system compared to conventional staple closure.

Telehealth has the potential to change the way we approach patient care. From virtual consenting to reducing carbon emissions, costs, and waiting times, it is a powerful tool in our clinical armamentarium. There is mounting evidence that remote diagnostic evaluation and decision-making have reached an acceptable level of accuracy and can safely be adopted in orthopaedic surgery. Furthermore, patients’ and surgeons’ satisfaction with virtual appointments are comparable to in-person consultations. Challenges to the widespread use of telehealth should, however, be acknowledged and include the cost of installation, training, maintenance, and accessibility. It is also vital that clinicians are conscious of the medicolegal and ethical considerations surrounding the medium and adhere strictly to the relevant data protection legislation and storage framework. It remains to be seen how organizations harness the full spectrum of the technology to facilitate effective patient care. Cite this article: Bone Joint J 2023;105-B(8):843–849

Introduction. The knee is the most commonly injured joint in sporting accidents, leading to substantial disability, time off work and morbidity (1). Treatment and assessment vary around the UK (2), whilst there remains a limited number of high-quality randomised controlled trials assessing first time, acute soft tissue knee injuries (3,4). As the clinical and financial burden rises (5), vital answers are required to improve prevention, diagnosis, treatment, rehabilitation, and delivery of care. In association with the James Lind Alliance, this BASK, BOSTAA and BOA supported prioritising exercise was undertaken over a year. Methods. The James Lind Alliance methodology was followed; a modified nominal group technique was used in the final workshop. An initial survey invited patients and healthcare professionals to submit their uncertainties regarding soft tissue knee injury prevention, diagnosis, treatment, rehabilitation, and delivery of care. Seventy-four questions were formulated to encompass common concerns. These were checked against best available evidence. Following the interim survey, 27 questions were taken forward to the final workshop in January 2023, where they were discussed, ranked, and scored in multiple rounds of prioritisation by groups of healthcare professionals, patients, and carers. Results. Over 1000 questions were submitted initially. Twenty-seven were taken forward to the final workshop following the surveys. Nearly half of the responses were from patients/carers. The Top 10 (Figure 1) includes prevention, diagnosis, treatment, and rehabilitation questions, reflecting the concerns of patients, carers, and a wider multidisciplinary team. Conclusion. This validated process has generated an important, wide- ranging Top 10 priorities for future soft tissue knee injury research. These have been submitted to the National Institute for Health and Care Research and are now available for researchers to investigate. The final 27 questions which were taken to the final workshop have also been published on the James Lind Alliance website. Research into these questions will lead to future high-quality research, thus improving patient care & outcomes. For any figures or tables, please contact authors directly

This project hoped to evaluate a new role, encompassing an in-hours registrar physician being based on the orthopaedic wards for advice, patient reviews, and patient journey optimisation. This service aimed to provide input for all patients who required them outwith the already established ortho-geriatric service. The success of this role was assessed through feedback questionnaires, as well as through the auditing of functional indicators such as the burden on the on-call orthopaedic registrar and other departments for advice from junior doctors, plus the number of medical emergencies. The survey received a total of 42 responses from various staff roles. All respondents thought the role had improved patient care or the functioning of the department. Respondents thought the role primarily enhanced patient care and safety and led to increased support for junior doctors and nursing staff. Data showed a 44% reduction in medical emergency calls since the role began. Total calls outwith the department for medical support reduced by 100% in hours and 50% out of hours when analysed over 22 days. Over a 14 day period, calls to the on-call orthopaedic registrar also reduced by 100% in hours, with no significant difference out of hours. This role has improved patient care and safety and allowed faster medical support with reduced impact on orthopaedic and general medical services. Feedback has been very positive from all staff. The major limitation is lack of 24 hour support. Next steps will include expanding the role, as well as introduction of framework for professional development

Aims. Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials. Methods. A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures. Results. Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations. Conclusion. Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic practice. Cite this article: Bone Joint J 2024;106-B(11):1216–1222

Aims. To identify unanswered questions about the prevention, diagnosis, treatment, and rehabilitation and delivery of care of first-time soft-tissue knee injuries (ligament injuries, patella dislocations, meniscal injuries, and articular cartilage) in children (aged 12 years and older) and adults. Methods. The James Lind Alliance (JLA) methodology for Priority Setting Partnerships was followed. An initial survey invited patients and healthcare professionals from the UK to submit any uncertainties regarding soft-tissue knee injury prevention, diagnosis, treatment, and rehabilitation and delivery of care. Over 1,000 questions were received. From these, 74 questions (identifying common concerns) were formulated and checked against the best available evidence. An interim survey was then conducted and 27 questions were taken forward to the final workshop, held in January 2023, where they were discussed, ranked, and scored in multiple rounds of prioritization. This was conducted by healthcare professionals, patients, and carers. Results. The top ten included questions regarding prevention, diagnosis, treatment, and rehabilitation. The number one question was, ‘How urgently do soft-tissue knee injuries need to be treated for the best outcome?’. This reflects the concerns of patients, carers, and the wider multidisciplinary team. Conclusion. This validated process has generated ten important priorities for future soft-tissue knee injury research. These have been submitted to the National Institute for Health and Care Research. All 27 questions in the final workshop have been published on the JLA website. Cite this article: Bone Joint J 2024;106-B(3):232–239