Aims

The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?

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

Describe a statistical and economic analysis plan for the Distal Radius Acute Fracture Fixation Trial 2 (DRAFFT2) randomized controlled trial.

The April 2024 Wrist & Hand Roundup. 360. looks at: Lunocapitate versus four-corner fusion in scapholunate or scaphoid nonunion advanced collapse: a randomized controlled trial; Postoperative scaphoid alignment, smoking, and avascular necrosis determine outcomes; Grip strength signals broader health concerns in females with distal radius fractures; Clearing the smoke: how smoking status influences recovery from open carpal tunnel release surgery; Age matters: assessing the likelihood of corrective surgery after distal radius fractures; Is pronator quadratus muscle repair required after anterior plate fixation for distal radius fractures?; Efficacy of total wrist arthroplasty: a comparative analysis of inflammatory and non-inflammatory arthritis outcomes; A comprehensive review of the one-bone forearm as a salvage technique

The December 2022 Wrist & Hand Roundup. 360. looks at: Anti-tumour necrosis factor therapy for early-stage Dupuytren’s disease; Patient experiences of scaphoid waist fractures and their treatment; Postoperative complications following open a1 pulley release for a trigger finger or thumb; How certain are findings in distal radius fractures: a systematic review of randomized controlled trials; Partial wrist denervation in wrist osteoarthritis: patient-reported outcomes and objective function; Dorsal bridge plating versus bridging external fixation for management of complex distal radius fractures; How is reduction lost in distal radius fractures in females aged 50 years and older; The HAND-Q: psychometrics of a new patient-reported outcome measure for clinical and research applications

Aims. The primary aim of this study was to report the radiological outcomes of patients with a dorsally displaced distal radius fracture who were randomized to a moulded cast or surgical fixation with wires following manipulation and closed reduction of their fracture. The secondary aim was to correlate radiological outcomes with patient-reported outcome measures (PROMs) in the year following injury. Methods. Participants were recruited as part of DRAFFT2, a UK multicentre clinical trial. Participants were aged 16 years or over with a dorsally displaced distal radius fracture, and were eligible for the trial if they needed a manipulation of their fracture, as recommended by their treating surgeon. Participants were randomly allocated on a 1:1 ratio to moulded cast or Kirschner wires after manipulation of the fracture in the operating theatre. Standard posteroanterior and lateral radiographs were performed in the radiology department of participating centres at the time of the patient’s initial assessment in the emergency department and six weeks postoperatively. Intraoperative fluoroscopic images taken at the time of fracture reduction were also assessed. Results. Patients treated with surgical fixation with wires had less dorsal angulation of the radius versus those treated in a moulded cast at six weeks after manipulation of the fracture; the mean difference of -4.13° was statistically significant (95% confidence interval 5.82 to -2.45). There was no evidence of a difference in radial shortening. However, there was no correlation between these radiological measurements and PROMs at any timepoint in the 12 months post-injury. Conclusion. For patients with a dorsally displaced distal radius fracture treated with a closed manipulation, surgical fixation with wires leads to less dorsal angulation on radiographs at six weeks compared with patients treated in a moulded plaster cast alone. However, the difference in dorsal angulation was small and did not correlate with patient-reported pain and function. Cite this article: Bone Jt Open 2024;5(2):132–138

The August 2024 Wrist & Hand Roundup. 360. looks at: Methotrexate shows potential in reducing pain for hand osteoarthritis with synovitis; Circumferential casting versus plaster splinting in adult distal radius fractures: the CAST study findings; Surgery shows superior long-term success for Dupuytren contracture compared to needle fasciotomy and collagenase injection; Evolving trends in surgical management of wrist arthritis: a decade-long national analysis; Mid-term outcomes of three commonly used surgical reconstructions for scapholunate instability; SLAC and SNAC: what is the evidence for treatment?; Steroids for trapeziometacarpal osteoarthritis?; When is it safe to return to driving after distal radius fracture fixation? A prospective study

The December 2023 Wrist & Hand Roundup. 360. looks at: Volar locking plate for distal radius fractures with patient-reported outcomes in older adults; Total joint replacement or trapeziectomy?; Replantation better than revision amputation in traumatic amputation?; What factors are associated with revision cubital tunnel release within three years?; Use of nerve conduction studies in carpal tunnel syndrome; Surgical site infection following surgery for hand trauma: a systematic review and meta-analysis; Association between radiological and clinical outcomes following distal radial fractures; Reducing the carbon footprint in carpal tunnel surgery inside the operating room with a lean and green model: a comparative study

The October 2024 Wrist & Hand Roundup360 looks at: Circumferential casting versus plaster splinting in preventing redisplacement of distal radial fractures; Comparable outcomes for operative versus nonoperative treatment of scapholunate ligament injuries in distal radius fractures; Perceived pain during the reduction of Colles fracture without anaesthesia; Diagnostic delays and physician training are key to reducing scaphoid fracture nonunion; Necrotizing fasciitis originating in the hand: a systematic review and meta-analysis; Study design influences outcomes in distal radial fracture research; Long-term results of index finger pollicization for congenital thumb anomalies: a systematic review; Enhancing nerve injury diagnosis: the evolving role of imaging and electrodiagnostic tools

The October 2023 Wrist & Hand Roundup. 360. looks at: Distal radius fracture management: surgeon factors markedly influence decision-making; Fracture-dislocation of the radiocarpal joint: bony and capsuloligamentar management, outcomes, and long-term complications; Exploring the role of artificial intelligence chatbot in the management of scaphoid fractures; Role of ultrasonography for evaluation of nerve recovery in repaired median nerve lacerations; Four weeks versus six weeks of immobilization in a cast following closed reduction for displaced distal radial fractures in adult patients: a multicentre randomized controlled trial; Rehabilitation following flexor tendon injury in Zone 2: a randomized controlled study; On the road again: return to driving following minor hand surgery; Open versus single- or dual-portal endoscopic carpal tunnel release: a meta-analysis of randomized controlled trials

Aims. The aim of this systematic review and meta-analysis was to gather epidemiological information on selected musculoskeletal injuries and to provide pooled injury-specific incidence rates. Methods. PubMed (National Library of Medicine) and Scopus (Elsevier) databases were searched. Articles were eligible for inclusion if they reported incidence rate (or count with population at risk), contained data on adult population, and were written in English language. The number of cases and population at risk were collected, and the pooled incidence rates (per 100,000 person-years) with 95% confidence intervals (CIs) were calculated by using either a fixed or random effects model. Results. The screening of titles yielded 206 articles eligible for inclusion in the study. Of these, 173 (84%) articles provided sufficient information to be included in the pooled incidence rates. Incidences of fractures were investigated in 154 studies, and the most common fractures in the whole adult population based on the pooled incidence rates were distal radius fractures (212.0, 95% CI 178.1 to 252.4 per 100,000 person-years), finger fractures (117.1, 95% CI 105.3 to 130.2 per 100,000 person-years), and hip fractures (112.9, 95% CI 82.2 to 154.9 per 100,000 person-years). The most common sprains and dislocations were ankle sprains (429.4, 95% CI 243.0 to 759.0 per 100,000 person-years) and first-time patellar dislocations (32.8, 95% CI 21.6 to 49.7 per 100,000 person-years). The most common injuries were anterior cruciate ligament (17.5, 95% CI 6.0 to 50.2 per 100,000 person-years) and Achilles (13.7, 95% CI 9.6 to 19.5 per 100,000 person-years) ruptures. Conclusion. The presented pooled incidence estimates serve as important references in assessing the global economic and social burden of musculoskeletal injuries. Cite this article: Bone Joint Res 2022;11(11):814–825

Aims. The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. Methods. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared. Results. At the time of the study, the CNN model showed an area under the receiver operating curve of 0.97. AI assistance improved the physician’s sensitivity (correct fracture detection) from 80% to 87%, and the specificity (correct fracture exclusion) from 91% to 95%. The overall error rate (combined false positive and false negative) was reduced from 14% without AI to 9% with AI. Conclusion. The use of a CNN model as a second opinion can improve the diagnostic accuracy of DRF detection in the study setting. Cite this article: Bone Joint Res 2024;13(10):588–595

Aims. Following the introduction of national standards in 2009, most major paediatric trauma is now triaged to specialist units offering combined orthopaedic and plastic surgical expertise. We investigated the management of open tibia fractures at a paediatric trauma centre, primarily reporting the risk of infection and rate of union. Patients and Methods. A retrospective review was performed on 61 children who between 2007 and 2015 presented with an open tibia fracture. Their mean age was nine years (2 to 16) and the median follow-up was ten months (interquartile range 5 to 18). Management involved IV antibiotics, early debridement and combined treatment of the skeletal and soft-tissue injuries in line with standards proposed by the British Orthopaedic Association. Results. There were 36 diaphyseal fractures and 25 distal tibial fractures. Of the distal fractures, eight involved the physis. Motor vehicle collisions accounted for two thirds of the injuries and 38 patients (62%) arrived outside of normal working hours. The initial method of stabilisation comprised: casting in nine cases (15%); elastic nailing in 19 (31%); Kirschner (K)-wiring in 13 (21%); intramedullary nailing in one (2%); open reduction and plate fixation in four (7%); and external fixation in 15 (25%). Wound management comprised: primary wound closure in 24 (39%), delayed primary closure in 11 (18%), split skin graft (SSG) in eight (13%), local flap with SSG in 17 (28%) and a free flap in one. A total of 43 fractures (70%) were Gustilo-Anderson grade III. There were four superficial (6.6%) and three (4.9%) deep infections. Two deep infections occurred following open reduction and plate fixation and the third after K-wire fixation of a distal fracture. No patient who underwent primary wound closure developed an infection. All the fractures united, although nine patients required revision of a mono-lateral to circular frame for delayed union (two) or for altered alignment or length (seven). The mean time to union was two weeks longer in diaphyseal fractures than in distal fractures (13 weeks versus 10.8 weeks, p = 0.016). Children aged > 12 years had a significantly longer time to union than those aged < 12 years (16.3 weeks versus 11.4 weeks, p = 0.045). The length of stay in hospital for patients with a Gustilo-Anderson grade IIIB fracture was twice as long as for less severe injuries. . Conclusion. Fractures in children heal better than those in adults. Based on our experience of deep infection we discourage the use of internal fixation with a plate for open tibial fractures in children. We advocate aggressive initial wound debridement in theatre with early definitive combined orthopaedic and plastic surgery in order to obtain skeletal stabilisation and soft-tissue cover. Cite this article: Bone Joint J 2017;99-B:544–53

The February 2015 Wrist & Hand Roundup360 looks at: Toes, feet, hands and transfers… FCR Tendonitis after Trapeziectomy and suspension, Motion sparing surgery for SLAC/SNAC wrists under the spotlight, Instability following distal radius fractures, Bilateral wrist arthrodesis a good idea?, Sodium Hyaluronate improves hand recovery following flexor tendon repair, Ultrasound treatments for de Quervain’s, Strategies for treating metacarpal neck fractures

Aims

The primary aim of this study is to quantify and compare outcomes following a dorsally displaced fracture of the distal radius in elderly patients (aged ≥ 65 years) who are managed conservatively versus with surgical fixation (open reduction and internal fixation). Secondary aims are to assess and compare upper limb-specific function, health-related quality of life, wrist pain, complications, grip strength, range of motion, radiological parameters, healthcare resource use, and cost-effectiveness between the groups.