Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’).

Cite this article: Bone Joint J 2022;104-B(8):911–914.

Aims. Frailty greatly increases the risk of adverse outcome of trauma in older people. Frailty detection tools appear to be unsuitable for use in traumatically injured older patients. We therefore aimed to develop a method for detecting frailty in older people sustaining trauma using routinely collected clinical data. Methods. We analyzed prospectively collected registry data from 2,108 patients aged ≥ 65 years who were admitted to a single major trauma centre over five years (1 October 2015 to 31 July 2020). We divided the sample equally into two, creating derivation and validation samples. In the derivation sample, we performed univariate analyses followed by multivariate regression, starting with 27 clinical variables in the registry to predict Clinical Frailty Scale (CFS; range 1 to 9) scores. Bland-Altman analyses were performed in the validation cohort to evaluate any biases between the Nottingham Trauma Frailty Index (NTFI) and the CFS. Results. In the derivation cohort, five of the 27 variables were strongly predictive of the CFS (regression coefficient B = 6.383 (95% confidence interval 5.03 to 7.74), p < 0.001): age, Abbreviated Mental Test score, admission haemoglobin concentration (g/l), pre-admission mobility (needs assistance or not), and mechanism of injury (falls from standing height). In the validation cohort, there was strong agreement between the NTFI and the CFS (mean difference 0.02) with no apparent systematic bias. Conclusion. We have developed a clinically applicable tool using easily and routinely measured physiological and functional parameters, which clinicians and researchers can use to guide patient care and to stratify the analysis of quality improvement and research projects. Cite this article: Bone Joint J 2024;106-B(4):412–418

Aims. The aim of this study was to perform the first population-based description of the epidemiological and health economic burden of fracture-related infection (FRI). Methods. This is a retrospective cohort study of operatively managed orthopaedic trauma patients from 1 January 2007 to 31 December 2016, performed in Queensland, Australia. Record linkage was used to develop a person-centric, population-based dataset incorporating routinely collected administrative, clinical, and health economic information. The FRI group consisted of patients with International Classification of Disease 10th Revision diagnosis codes for deep infection associated with an implanted device within two years following surgery, while all others were deemed not infected. Demographic and clinical variables, as well as healthcare utilization costs, were compared. Results. There were 111,402 patients operatively managed for orthopaedic trauma, with 2,775 of these (2.5%) complicated by FRI. The development of FRI had a statistically significant association with older age, male sex, residing in rural/remote areas, Aboriginal or Torres Strait Islander background, lower socioeconomic status, road traffic accident, work-related injuries, open fractures, anatomical region (lower limb, spine, pelvis), high injury severity, requiring soft-tissue coverage, and medical comorbidities (univariate analysis). Patients with FRI had an eight-times longer median inpatient length of stay (24 days vs 3 days), and a 2.8-times higher mean estimated inpatient hospitalization cost (AU$56,565 vs AU$19,773) compared with uninfected patients. The total estimated inpatient cost of the FRI cohort to the healthcare system was AU$156.9 million over the ten-year period. Conclusion. The results of this study advocate for improvements in trauma care and infection management, address social determinants of health, and highlight the upside potential to improve prevention and treatment strategies. Cite this article: Bone Joint J 2024;106-B(1):77–85

Benefits of early stabilization of femoral shaft fractures, in mitigation of pulmonary and other complications, have been recognized over the past decades. Investigation into the appropriate level of resuscitation, and other measures of readiness for definitive fixation, versus a damage control strategy have been ongoing. These principles are now being applied to fractures of the thoracolumbar spine, pelvis, and acetabulum. Systems of trauma care are evolving to encompass attention to expeditious and safe management of not only multiply injured patients with these major fractures, but also definitive care for hip and periprosthetic fractures, which pose a similar burden of patient recumbency until stabilized. Future directions regarding refinement of patient resuscitation, assessment, and treatment are anticipated, as is the potential for data sharing and registries in enhancing trauma system functionality. Cite this article: Bone Joint J 2023;105-B(4):361–364

Aims. Periprosthetic proximal femoral fractures (PFFs) are a major complication after total hip arthroplasty (THA). Health status after PFF is not specifically investigated. The aim of this study is to evaluate the health status pattern over two years after sustaining a PFF. Methods. A cohort of patients with PFF after THA was derived from the Brabant Injury Outcomes Surveillance (BIOS) study. The BIOS study, a prospective, observational, multicentre follow-up cohort study, was conducted to obtain data by questionnaires pre-injury and at one week, and one, three, six, 12, and 24 months after trauma. Primary outcome measures were the EuroQol five-dimension three-level questionnaire (EQ-5D-3L), the Health Utility Index 2 (HUI2), and the Health Utility Index 3 (HUI3). Secondary outcome measures were general measurements such as duration of hospital stay and mortality. Results. A total of 70 patients with a PFF were included. EQ-5D utility scores were significantly lower on all timepoints except at six months’ follow-up compared to pre-injury. EuroQol visual analogue scale (EQ-VAS) scores at one month's follow-up were significantly lower compared to pre-injury. The percentage of reported problems at two years was higher for all dimensions except anxiety/depression when compared to pre-injury. The mean EQ-5D utility score was 0.26 higher in males compared to females (95% confidence interval (CI) 0.01 to 0.42; p = 0.003). The mean EQ-VAS score for males was 8.9 points higher when compared to females over all timepoints (95% CI 1.2 to 16.7; p = 0.027). Mortality was 10% after two years’ follow-up. Conclusion. PFF patients are a frail population with substantial functional impairment at baseline. Post-injury, they have a significant and clinically relevant lower health status two years after trauma when compared to pre-injury. Health status improves the most between one and three months after injury. Two years after PFF, more patients experience problems in mobility, self-care, usual activities, and pain/discomfort than pre-injury. Cite this article: Bone Joint J 2024;106-B(5):442–449

Aims. The primary objective of this study was to develop a validated classification system for assessing iatrogenic bone trauma and soft-tissue injury during total hip arthroplasty (THA). The secondary objective was to compare macroscopic bone trauma and soft-tissues injury in conventional THA (CO THA) versus robotic arm-assisted THA (RO THA) using this classification system. Methods. This study included 30 CO THAs versus 30 RO THAs performed by a single surgeon. Intraoperative photographs of the osseous acetabulum and periacetabular soft-tissues were obtained prior to implantation of the acetabular component, which were used to develop the proposed classification system. Interobserver and intraobserver variabilities of the proposed classification system were assessed. Results. The BOne trauma and Soft-Tissue Injury classification system in total Hip arthroplasty (BOSTI Hip) grades osseous acetabular trauma and periarticular muscle damage during THA. The classification system has an interclass correlation coefficient of 0.90 (95% CI 0.86 to 0.93) for interobserver agreement and 0.89 (95% CI 0.84 to 0.93) for intraobserver agreement. RO THA was associated with improved BOSTI Hip scores (p = 0.002) and more pristine osseous surfaces in the anterior superior (p = 0.001) and posterior superior (p < 0.001) acetabular quadrants compared with CO THA. There were no differences between the groups in relation to injury to the gluteus medius (p = 0.084), obturator internus (p = 0.241), piriformis (p = 0.081), superior gamellus (p = 0.116), inferior gamellus (p = 0.132), quadratus femoris (p = 0.208), and vastus lateralis (p = 0.135), but overall combined muscle injury was reduced in RO THA compared with CO THA (p = 0.023). Discussion. The proposed BOSTI Hip classification provides a reproducible grading system for stratifying iatrogenic bone trauma and soft-tissue injury during THA. RO THA was associated with improved BOSTI Hip scores, more pristine osseous acetabular surfaces, and reduced combined periarticular muscle injury compared with CO THA. Further research is required to understand if these intraoperative findings translate to differences in clinical outcomes between the treatment groups. Cite this article: Bone Joint J 2024;106-B(9):898–906

Aims. Heterotopic ossification (HO) is a common complication after elbow trauma and can cause severe upper limb disability. Although multiple prognostic factors have been reported to be associated with the development of post-traumatic HO, no model has yet been able to combine these predictors more succinctly to convey prognostic information and medical measures to patients. Therefore, this study aimed to identify prognostic factors leading to the formation of HO after surgery for elbow trauma, and to establish and validate a nomogram to predict the probability of HO formation in such particular injuries. Methods. This multicentre case-control study comprised 200 patients with post-traumatic elbow HO and 229 patients who had elbow trauma but without HO formation between July 2019 and December 2020. Features possibly associated with HO formation were obtained. The least absolute shrinkage and selection operator regression model was used to optimize feature selection. Multivariable logistic regression analysis was applied to build the new nomogram: the Shanghai post-Traumatic Elbow Heterotopic Ossification Prediction model (STEHOP). STEHOP was validated by concordance index (C-index) and calibration plot. Internal validation was conducted using bootstrapping validation. Results. Male sex, obesity, open wound, dislocations, late definitive surgical treatment, and lack of use of non-steroidal anti-inflammatory drugs were identified as adverse predictors and incorporated to construct the STEHOP model. It displayed good discrimination with a C-index of 0.80 (95% confidence interval 0.75 to 0.84). A high C-index value of 0.77 could still be reached in the internal validation. The calibration plot showed good agreement between nomogram prediction and observed outcomes. Conclusion. The newly developed STEHOP model is a valid and convenient instrument to predict HO formation after surgery for elbow trauma. It could assist clinicians in counselling patients regarding treatment expectations and therapeutic choices. Cite this article: Bone Joint J 2022;104-B(8):963–971

Aims. The purpose of this study was to determine the weightbearing practice of operatively managed fragility fractures in the setting of publically funded health services in the UK and Ireland. Methods. The Fragility Fracture Postoperative Mobilisation (FFPOM) multicentre audit included all patients aged 60 years and older undergoing surgery for a fragility fracture of the lower limb between 1 January 2019 and 30 June 2019, and 1 February 2021 and 14 March 2021. Fractures arising from high-energy transfer trauma, patients with multiple injuries, and those associated with metastatic deposits or infection were excluded. We analyzed this patient cohort to determine adherence to the British Orthopaedic Association Standard, “all surgery in the frail patient should be performed to allow full weight-bearing for activities required for daily living”. Results. A total of 19,557 patients (mean age 82 years (SD 9), 16,241 having a hip fracture) were included. Overall, 16,614 patients (85.0%) were instructed to perform weightbearing where required for daily living immediately postoperatively (15,543 (95.7%) hip fracture and 1,071 (32.3%) non-hip fracture patients). The median length of stay was 12.2 days (interquartile range (IQR) 7.9 to 20.0) (12.6 days (IQR 8.2 to 20.4) for hip fracture and 10.3 days (IQR 5.5 to 18.7) for non-hip fracture patients). Conclusion. Non-hip fracture patients experienced more postoperative weightbearing restrictions, although they had a shorter hospital stay. Patients sustaining fractures of the shaft and distal femur had a longer median length of stay than demographically similar patients who received hip fracture surgery. We have shown a significant disparity in weightbearing restrictions placed on patients with fragility fractures, despite the publication of a national guideline. Surgeons intentionally restrict postoperative weightbearing in the majority of non-hip fractures, yet are content with unrestricted weightbearing following operations for hip fractures. Cite this article: Bone Joint J 2022;104-B(8):972–979

Aims. This study reviews the past 30 years of research from the Canadian Orthopedic Trauma Society (COTS), to identify predictive factors that delay or accelerate the course of randomized controlled trials in orthopaedic trauma. Methods. We conducted a methodological review of all papers published through the Canadian Orthopaedic Trauma Society or its affiliates. Data abstracted included: year of publication; journal of publication; study type; number of study sites; sample size; and achievement of sample size goals. Information about the study timelines was also collected, including: the date of study proposal to COTS; date recruitment began; date recruitment ended; and date of publication. Results. In total, 22 studies have been published through the COTS working group, 13 of which are randomized controlled trials (RCTs). In total, 1,423 individual patients have been involved in COTS studies, a mean of 110 patients per trial (22 to 424). Each study was conducted across a mean of approximately six centres (1 to 11) and took nearly ten years (mean 119.9 months (59 to 188)) from presentation of concept to publication. The mean length of enrolment was 63 months (26 to 113) and the mean time from cessation of enrolment to publication 51 months (19 to 78). Regardless of sample size, the only factor associated with a decreased length of enrolment was a higher number of clinical sites (p = 0.041). Neither study sample size nor length of enrolment were associated with total time to publication. Conclusion. Over the last three decades, COTS has developed a multinational strategy to produce high-quality evidence in the field of orthopaedic trauma through 13 multicentre RCTs. Future efficiencies can be realized by recruitment of more clinical sites, improving connectivity between the sites, and the promotion of national streamlined ethics processes. Cite this article: Bone Joint J 2021;103-B(5):898–901

This brief annotation summarises the particular contributions made by the annual Edinburgh International Trauma Symposium in various areas of research into aspects of orthopaedic trauma and the management of acutely injured patients, during the 25 years since its establishment

This study examined spinal fractures in patients admitted to a Major Trauma Centre via two independent pathways, a major trauma (MT) pathway and a standard unscheduled non-major trauma (NMT) pathway. A total of 134 patients were admitted with a spinal fracture over a period of two years; 50% of patients were MT and the remainder NMT. MT patients were predominantly male, had a mean age of 48.8 years (13 to 95), commonly underwent surgery (62.7%), characteristically had fractures in the cervico-thoracic and thoracic regions and 50% had fractures of more than one vertebrae, which were radiologically unstable in 70%. By contrast, NMT patients showed an equal gender distribution, were older (mean 58.1 years; 12 to 94), required fewer operations (56.7%), characteristically had fractures in the lumbar region and had fewer multiple and unstable fractures. This level of complexity was reflected in the length of stay in hospital; MT patients receiving surgery were in hospital for a mean of three to four days longer than NMT patients. These results show that MT patients differ from their NMT counterparts and have an increasing complexity of spinal injury. Cite this article: Bone Joint J 2015;97-B:235–9

Aims. The aim of this study was to investigate the relationship between the Orthopaedic Trauma Society (OTS) classification of open fractures and economic costs. Methods. Resource use was measured during the six months that followed open fractures of the lower limb in 748 adults recruited as part of two large clinical trials within the UK Major Trauma Research Network. Resource inputs were valued using unit costs drawn from primary and secondary sources. Economic costs (GBP sterling, 2017 to 2018 prices), estimated from both a NHS and Personal Social Services (PSS) perspective, were related to the degree of complexity of the open fracture based on the OTS classification. Results. Adjusted mean total NHS and PSS costs were £13,785 following treatment of complex fractures and £3,550 following treatment of simple fractures, where the open fracture wound is closed at the end of the first wound debridement, generating a mean difference of £10,235 (95% confidence interval £8,074 to £12,396). Conclusion. Following previous work correlating clinical outcomes with the OTS classification of open fractures, this study suggests that the new OTS classification also correlates with economic costs estimated from alternative study perspectives. Cite this article: Bone Joint J 2022;104-B(3):408–412

Aims. To describe a new objective classification for open fractures of the lower limb and to correlate the classification with patient-centred outcomes. Methods. The proposed classification was investigated within a cohort of adults with open fractures of the lower limb who were recruited as part of two large clinical trials within the UK Major Trauma Network. The classification was correlated with patient-reported Disability Rating Index (DRI) and EuroQol five-dimension questionnaire (EQ-5D) health-related quality of life in the year after injury, and with deep infection at 30 days, according to the Centers for Disease Control and Prevention definition of a deep surgical site infection. Results. A total of 748 participants were included in the analysis. Of these, 288 (38.5%) had a simple open fracture and 460 (61.5%) had a complex fracture as defined by the new classification system. At 12 months, the mean DRI in the simple fracture group was 32.5 (SD 26.8) versus 43.9 (SD 26.1) in the complex fracture group (odds ratio (OR) 8.19; 95% confidence interval (CI) 3.69 to 12.69). At 12 months the mean health-related quality of life (EQ-5D utility) in the simple fracture group was 0.59 (SD 0.29) versus 0.56 (SD 0.32) in the complex fracture group (OR -0.03; 95% CI -0.09 to 0.02). The differences in the rate of deep infection at 30 days was not statistically significant. Conclusion. The Orthopaedic Trauma Society open fracture classification is based upon objective descriptors of the injury and correlates with patient-centred outcomes in a large cohort of open fractures of the lower limb. Cite this article: Bone Joint J 2020;102-B(11):1469–1474

There is increasing popularity in the use of artificial intelligence and machine-learning techniques to provide diagnostic and prognostic models for various aspects of Trauma & Orthopaedic surgery. However, correct interpretation of these models is difficult for those without specific knowledge of computing or health data science methodology. Lack of current reporting standards leads to the potential for significant heterogeneity in the design and quality of published studies. We provide an overview of machine-learning techniques for the lay individual, including key terminology and best practice reporting guidelines. Cite this article: Bone Joint J 2021;103-B(12):1754–1758

Aims. We aimed to determine whether there is evidence of improved patient outcomes in Major Trauma Centres following the regionalisation of trauma care in England. Patients and Methods. An observational study was undertaken using the Trauma Audit and Research Network (TARN), Hospital Episode Statistics (HES) and national death registrations. The outcome measures were indicators of the quality of trauma care, such as treatment by a senior doctor and clinical outcomes, such as mortality in hospital. Results and Conclusion. A total of 20 181 major trauma cases were reported to TARN during the study period, which was 270 days before and after each hospital became a Major Trauma Centre. Following regionalisation of trauma services, all indicators of the quality of care improved, fewer patients required secondary transfer between hospitals and a greater proportion were discharged with a Glasgow Outcome Score of “good recovery”. In this early post-implementation analysis, there were a number of apparent process improvements (e.g. time to CT) but no differences in either crude or adjusted mortality. The overall number of deaths following trauma in England did not change following the national reconfiguration of trauma services. Evidence from other countries that have regionalised trauma services suggests that further benefits may become apparent after a period of maturing of the trauma system. Cite this article: Bone Joint J 2016;98-B:1253–61

Aims. To compare the early management and mortality of older patients sustaining major orthopaedic trauma with that of a younger population with similar injuries. Patients and Methods. The Trauma Audit Research Network database was reviewed to identify eligible patients admitted between April 2012 and June 2015. Distribution and severity of injury, interventions, comorbidity, critical care episodes and mortality were recorded. The population was divided into young (64 years or younger) and older (65 years and older) patients. Results. Of 142 765 adults sustaining major trauma, 72 942 (51.09 %) had long bone or pelvic fractures and 45.81% of these were > 65 years old. Road traffic collision was the most common mechanism in the young (40.4%) and, in older people, fall from standing height (80.4%) predominated. The 30 day mortality in older patients with fractures is greater (6.8% versus 2.5%), although critical care episodes are more common in the young (18.2% versus 9.7%). Older people are less likely to be admitted to critical care beds and are often managed in isolation by surgeons. Orthopaedic surgery is the most common admitting and operating specialty and, in older people, fracture surgery accounted for 82.1% of procedures. . Conclusion. Orthopaedic trauma in older people is associated with mortality that is significantly greater than for similar fractures in the young. As with the hip fracture population, major trauma in the elderly is a growing concern which highlights the need for a review of admission pathways and shared orthogeriatric care models. . Cite this article: Bone Joint J 2017;99-B:1677–80

As residency training programmes around the globe move towards competency-based medical education (CBME), there is a need to review current teaching and assessment practices as they relate to education in orthopaedic trauma. Assessment is the cornerstone of CBME, as it not only helps to determine when a trainee is fit to practice independently, but it also provides feedback on performance and guides the development of competence. Although a standardised core knowledge base for trauma care has been developed by the leading national accreditation bodies and international agencies that teach and perform research in orthopaedic trauma, educators have not yet established optimal methods for assessing trainees’ performance in managing orthopaedic trauma patients. . This review describes the existing knowledge from the literature on assessment in orthopaedic trauma and highlights initiatives that have recently been undertaken towards CBME in the United Kingdom, Canada and the United States. . In order to support a CBME approach, programmes need to improve the frequency and quality of assessments and improve on current formative and summative feedback techniques in order to enhance resident education in orthopaedic trauma. Cite this article: Bone Joint J 2016;98-B:1320–5

Aims. The aims of this study were to report the outcomes of patients with a complex fracture of the lower limb in the five years after they took part in the Wound Healing in Surgery for Trauma (WHIST) trial. Methods. The WHIST trial compared negative pressure wound therapy (NPWT) dressings with standard dressings applied at the end of the first operation for patients undergoing internal fixation of a complex fracture of the lower limb. Complex fractures included periarticular fractures and open fractures when the wound could be closed primarily at the end of the first debridement. A total of 1,548 patients aged ≥ 16 years completed the initial follow-up, six months after injury. In this study we report the pre-planned analysis of outcome data up to five years. Patients reported their Disability Rating Index (DRI) (0 to 100, in which 100 = total disability), and health-related quality of life, chronic pain scores and neuropathic pain scores annually, using a self-reported questionnaire. Complications, including further surgery related to the fracture, were also recorded. Results. A total of 1,015 of the original patients (66%) provided at least one set of outcome data during the five years of follow-up. There was no evidence of a difference in patient-reported disability between the two groups at five years (NPWT group mean DRI 30.0 (SD 26.5), standard dressing group mean DRI 31.5 (SD 28.8), adjusted difference -0.86 (95% CI -4.14 to 2.40; p = 0.609). There was also no evidence of a difference in the complication rates at this time. Conclusion. We found no evidence of a difference in disability ratings between NPWT compared with standard wound dressings in the five years following the surgical treatment of a complex fracture of the lower limb. Patients in both groups reported high levels of persistent disability and reduced quality of life, with little evidence of improvement during this time. Cite this article: Bone Joint J 2024;106-B(8):858–864