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. The timing of when to remove a circular frame is crucial; early removal results in refracture or deformity, while late removal increases the patient morbidity and delay in return to work. This study was designed to assess the effectiveness of a staged reloading protocol. We report the incidence of mechanical failure following both single-stage and two stage reloading protocols and analyze the associated risk factors. Methods. We identified consecutive patients from our departmental database. Both trauma and elective cases were included, of all ages, frame types, and pathologies who underwent circular frame treatment. Our protocol is either a single-stage or two-stage process implemented by defunctioning the frame, in order to progressively increase the weightbearing load through the bone, and promote full loading prior to frame removal. Before progression, through the process we monitor patients for any increase in pain and assess radiographs for deformity or refracture. Results. There were 244 frames (230 patients) included in the analyses, of which 90 were Ilizarov type frames and 154 were hexapods. There were 149 frames which underwent single-stage reloading and 95 frames which underwent a two-stage reloading protocol. Mechanical failure occurred after frame removal in 13 frames (5%), which suffered refracture. There were no cases of change in alignment. There was no difference between refracture patients who underwent single-stage or two-stage reloading protocols (p = 0.772). In all, 14 patients had failure prevented through identification with the reloading protocol. Conclusion. Our reloading protocol is a simple and effective way to confirm the timing of frame removal and minimize the rate of mechanical failure. Similar failure rates occurred between patients undergoing single-stage and two-stage reloading protocols. If the surgeon is confident with clinical and radiological assessment, it may be possible to progress directly to stage two and decrease frame time and patient morbidity. Cite this article: Bone Jt Open 2022;3(5):359–366

The December 2012 Trauma Roundup. 360. looks at: whether tranexamic acid stops bleeding in trauma across the board; antibiotic beads and VAC; whether anaesthetic determines the outcome in surgery for distal radial fractures; high complications in surgery on bisphosphonate-hardened bone; better outcomes but more dislocations in femoral neck fractures; the mythical hip fracture; plate augmentation in nonunion surgery; and SIGN intramedullary nailing and infections

Aims. Healthcare systems have been rapidly restructured to meet COVID-19 demand. Clinicians are working to novel clinical guidelines, treating new patient cohorts and working in unfamiliar environments. Trauma and orthopaedics (T&O) has experienced cancellation of routine clinics and operating, with redistribution of the workload and human resources. To date, no studies have evaluated the mental health impact of these changes on the T&O workforce. We report the results of a novel survey on the impact of the pandemic on the mental health of our orthopaedic workforce and the contributory factors. Methods. A 20-question survey-based cross-sectional study of orthopaedic team members was conducted during the COVID-19 pandemic. The primary objective was to identify the impact of the pandemic on mental health in the form of major depressive disorder (MDD) and general anxiety disorder (GAD). The survey incorporated the patient health questionnaire (PHQ-2), which is validated for screening of MDD, and the generalized anxiety disorder questionnaire (GAD-2), which is validated for screening of GAD. Results. There were 62 respondents (18 females and 44 males). As compared to the general population, we noted a greater estimated prevalence of GAD (17.7% vs 5.9%, p = 0.0009297) and MDD (19.4% vs 3.3%, p = 0.0000007731). The prevalence of MDD symptoms was greatest among senior house officers (SHOs) (p = 0.02216). Female respondents scored higher for symptoms of MDD (p = 0.03583) and GAD (p = 0.0001086). Those identifying as ‘Black, African, Caribbean or Black British’ displayed a higher prevalence of GAD symptoms (p = 0.001575) and felt least supported at work (p = 0.001341). Conclusion. Our study, in the first of its kind, shows a significant prevalence of GAD and MDD in the workforce. We found that SHOs, females and those of Black, African, Caribbean, or Black British origin were disproportionately affected. Action should be taken to help prevent adverse mental health outcomes for our colleagues during the pandemic. Cite this article: Bone Joint Open 2020;1-6:316–325

The April 2012 Trauma Roundup. 360 . looks at fibula-pro-tibia plating, galeazzi fractures, distal radial fractures in the over 65s, transverse sacral fractures, acute dislocation of the knee, posterior malleolar fractures, immobilising the broken scaphoid, the terrible triad, lower limb amputation after trauma, and whiplash injuries

Aims. The aim of this study was to assess whether it is possible to predict the mortality, and the extent and time of neurological recovery from the time of the onset of symptoms and MRI grade, in patients with the cerebral fat embolism syndrome (CFES). This has not previously been investigated. Methods. The study included 34 patients who were diagnosed with CFES following trauma between 2012 and 2018. The clinical diagnosis was confirmed and the severity graded by MRI. We investigated the rate of mortality, the time and extent of neurological recovery, the time between the injury and the onset of symptoms, the clinical severity of the condition, and the MRI grade. All patients were male with a mean age of 29.7 years (18 to 70). The mean follow-up was 4.15 years (2 to 8), with neurological recovery being assessed by the Glasgow Outcome Scale and the Mini-Mental State Examination. Results. In all, seven who had early-onset CFES (< 24 hours), and a severe Takahashi grade on MRI, died. There was a significant association between the time of onset of neurological signs and mortality (p = 0.035). Mortality was also significantly associated with a severe Takahashi grade (p < 0.001). Among the 27 surviving patients, 26 (96.3%) recovered completely. One (3.7%) had a cognitive deficit. The mean time to recovery was 4.7 weeks (2 to 13), with late recovery aftereight eight weeks being recorded in three patients. Conclusion. There was a significantly increased rate of mortality in patients with CFES who had an early onset of symptoms and a severe grade on MRI. Complete neurological recovery can be expected in most patients with CFES who survive. Cite this article: Bone Joint J 2022;104-B(1):142–149

Aims. Deep surgical site infection (SSI) is common after lower limb fracture. We compared the diagnosis of deep SSI using alternative methods of data collection and examined the agreement of clinical photography and in-person clinical assessment by the Centers for Disease Control and Prevention (CDC) criteria after lower limb fracture surgery. Methods. Data from two large, UK-based multicentre randomized controlled major trauma trials investigating SSI and wound healing after surgical repair of open lower limb fractures that could not be primarily closed (UK WOLLF), and surgical incisions for fractures that were primarily closed (UK WHiST), were examined. Trial interventions were standard wound care management and negative pressure wound therapy after initial surgical debridement. Wound outcomes were collected from 30 days to six weeks. We compared the level of agreement between wound photography and clinical assessment of CDC-defined SSI. We are also assessed the level of agreement between blinded independent assessors of the photographs. Results. Rates of CDC-defined deep SSI were 7.6% (35/460) after open fracture and 6.3% (95/1519) after closed incisional repair. Photographs were obtained for 77% and 73% of WOLLF and WHiST cohorts respectively (all participants n = 1,478). Agreement between photographic-SSI and CDC-SSI was fair for open fracture wounds (83%; k = 0.27 (95% confidence interval (CI) 0.14 to 0.42)) and for closed incisional wounds (88%; k = 0.29 (95% CI 0.20 to 0.37)) although the rate of photographically detected deep SSIs was twice as high as CDC-SSI (12% vs 6%). Agreement between different assessors for photographic-SSI (WOLLF 88%, k = 0.63 (95% CI 0.52 to 0.72); WHiST 89%; k = 0.61 (95% CI 0.54 to 0.69)); and wound healing was good (WOLLF 90%; k = 0.80 (95% CI 0.73 to 0.86); WHiST 87%; k = 0.57 (95% CI 0.50 to 0.64)). Conclusion. Although wound photography was feasible within the research context and inter-rater assessor agreement substantial, digital photographs used in isolation overestimated deep SSI rates, when compared to CDC criteria. Wound photography should not replace clinical assessment in pragmatic trials but may be useful for screening purposes where surgical infection outcomes are paramount. Cite this article: Bone Joint J 2021;103-B(12):1802–1808

Aims. The aim of this study was to investigate whether on-demand removal (ODR) is noninferior to routine removal (RR) of syndesmotic screws regarding functional outcome. Methods. Adult patients (aged above 17 years) with traumatic syndesmotic injury, surgically treated within 14 days of trauma using one or two syndesmotic screws, were eligible (n = 490) for inclusion in this randomized controlled noninferiority trial. A total of 197 patients were randomized for either ODR (retaining the syndesmotic screw unless there were complaints warranting removal) or RR (screw removed at eight to 12 weeks after syndesmotic fixation), of whom 152 completed the study. The primary outcome was functional outcome at 12 months after screw placement, measured by the Olerud-Molander Ankle Score (OMAS). Results. There were 152 patients included in final analysis (RR = 73; ODR = 79). Of these, 59.2% were male (n = 90), and the mean age was 46.9 years (SD 14.6). Median OMAS at 12 months after syndesmotic fixation was 85 (interquartile range (IQR) 60 to 95) for RR and 80 (IQR 65 to 100) for ODR. The noninferiority test indicated that the observed effect size was significantly within the equivalent bounds of -10 and 10 scale points (p < 0.001) for both the intention-to-treat and per-protocol, meaning that ODR was not inferior to RR. There were significantly more complications in the RR group (12/73) than in the ODR group (1/79) (p = 0.007). Conclusion. ODR of the syndesmotic screw is not inferior to routine removal when it comes to functional outcome. Combined with the high complication rate of screw removal, this offers a strong argument to adopt on demand removal as standard practice of care after syndesmotic screw fixation. Cite this article: Bone Joint J 2021;103-B(11):1709–1716

Aims. To compare the cost-utility of standard dressing with incisional negative-pressure wound therapy (iNPWT) in adults with closed surgical wounds associated with major trauma to the lower limbs. Methods. A within-trial economic evaluation was conducted from the UK NHS and personal social services (PSS) perspective based on data collected from the Wound Healing in Surgery for Trauma (WHiST) multicentre randomized clinical trial. Health resource utilization was collected over a six-month post-randomization period using trial case report forms and participant-completed questionnaires. Cost-utility was reported in terms of incremental cost per quality-adjusted life year (QALY) gained. Sensitivity analysis was conducted to test the robustness of cost-effectiveness estimates while uncertainty was handled using confidence ellipses and cost-effectiveness acceptability curves. Results. The incremental cost of standard dressing versus iNPWT over six months was £2,037 (95% confidence interval (CI) £349 to £3,724). There was an insignificant increment in QALYs gained in the iNPWT group (0.005, 95% CI -0.018 to 0.028). The probability of iNPWT being cost-effective at £20,000 per QALY was 1.9%. The results remained robust in the sensitivity analysis. Conclusion. The within-trial economic evaluation suggests that iNPWT is unlikely to be a cost-effective alternative to standard dressing in adults with closed surgical wounds to their lower limbs. Cite this article: Bone Joint J 2020;102-B(8):1072–1081

The February 2015 Trauma Roundup. 360 . looks at: Evaluating the syndesmosis in ankle fractures; Calcaneal fracture management an ongoing problem; Angular stable locking in low tibial fractures did not improve results; Open fractures: do the seconds really count?; Long-term outcomes of tibial fractures; Targeted performance improvements in pelvic fractures

The April 2015 Trauma Roundup. 360 . looks at: Negative presure wound therapy in open tibial fractures; Priority-driven approach to pelvic injuries; Early surgery essential in hip fracture management; Sheer fractures to the posteromedial plateau; Fasciotomy closure under the spotlight; Why do patients die from hip fracture?; Acetabular fractures down the line; Biomechanics of femoral neck fractures reviewed

The December 2014 Trauma Roundup. 360 . looks at: infection and temporising external fixation; Vitamin C in distal radial fractures; DRAFFT: Cheap and cheerful Kirschner wires win out; femoral neck fractures not as stable as they might be; displaced sacral fractures give high morbidity and mortality; sanders and calcaneal fractures: a 20-year experience; bleeding and pelvic fractures; optimising timing for acetabular fractures; and tibial plateau fractures

The August 2015 Trauma Roundup. 360 . looks at: Thromboprophylaxis not required in lower limb fractures; Subclinical thyroid dysfunction and fracture risk: moving the boundaries in fracture; Posterior wall fractures refined; Neurological injury and acetabular fracture surgery; Posterior tibial plateau fixation; Tibial plateau fractures in the longer term; Comprehensive orthogeriatric care and hip fracture; Compartment syndrome: in the eye of the beholder?

The August 2014 Trauma Roundup. 360 . looks at: On-table CT for calcaneal fractures; timing of femoral fracture surgery and outcomes; salvage arthroplasty for failed internal fixation of the femoral neck; screw insertion in osteoporotic bone; fibular intramedullary nailing on the ascendant; posterior wall acetabular fractures not all that innocent; bugs, plating and resistance and improving outcomes in olecranon tension band wiring

The February 2013 Trauma Roundup. 360 . looks at: the risk of ankle fractures; absorbable implants; minimally invasive heel fracture fixation; pertrochanteric fractures; arthroplasty and intracapsular hip fractures; and extensor mechanism disruption