SignificanceHistorically, computer-assisted detection (CAD) in radiology has failed to achieve improvements in diagnostic accuracy, decreasing clinician sensitivity and leading to unnecessary further diagnostic tests. With the advent of deep learning approaches to CAD, there is great excitement about its application to medicine, yet there is little evidence demonstrating improved diagnostic accuracy in clinically-relevant applications. We trained a deep learning model to detect fractures on radiographs with a diagnostic accuracy similar to that of senior subspecialized orthopedic surgeons. We demonstrate that when emergency medicine clinicians are provided with the assistance of the trained model, their ability to accurately detect fractures significantly improves.

No abstract

A total of 179 adult patients with displaced intra-articular fractures of the distal radius was randomised to receive indirect percutaneous reduction and external fixation (n = 88) or open reduction and internal fixation (n = 91). Patients were followed up for two years. During the first year the upper limb musculoskeletal function assessment score, the SF-36 bodily pain sub-scale score, the overall Jebsen score, pinch strength and grip strength improved significantly in all patients. There was no statistically significant difference in the radiological restoration of anatomical features or the range of movement between the groups. During the period of two years, patients who underwent indirect reduction and percutaneous fixation had a more rapid return of function and a better functional outcome than those who underwent open reduction and internal fixation, provided that the intra-articular step and gap deformity were minimised.

W e sought to quantify agreement by different assessors of the AO classification for distal fractures of the radius. Thirty radiographs of acute distal radial fractures were evaluated by 36 assessors of varying clinical experience. Our findings suggest that AO 'type' and the presence or absence of articular displacement are measured with high consistency when classification of distal radial fractures is undertaken by experienced observers. Assessors at all experience levels had difficulty agreeing on AO 'group' and especially AO 'subgroup'. To categorise distal radial fractures according to joint displacement and AO type is simple and reproducible. Our study examined only whether distal radial fractures could be consistently classified according to the AO system. Validation of the classification as a predictor of outcome will require a prospective clinical study.

In this study, no osteotomy nonunions were encountered in 67 patients, more than half of which were open injuries. Regardless of which type of fixation is used to secure the osteotomy, secure stabilization must be obtained. Isolated symptomatic olecranon fixation requiring removal occurred in approximately 8% of patients. Although not necessary for all fractures of the distal humerus, the olecranon osteotomy can be useful in the visualization of the complex articular injuries, allowing accurate articular reduction.

Active motion therapy provides greater active finger motion than passive motion therapy after zone-II flexor tendon repair without increasing the risk of tendon rupture. Concomitant nerve injuries, multiple digit injuries, and a history of smoking negatively impact the final outcome of tendon repairs.

The use of a distraction plate combined with reduction of the articular surface and bone-grafting when needed can be an effective technique for treatment of fractures of the distal end of the radius with extensive metaphyseal and diaphyseal comminution. A functional range of motion with minimal disability can be achieved despite a prolonged period of fixation with a distraction plate across the wrist joint.

No abstract