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. 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.Aims
Methods
We studied prospectively the regional inflammatory response to a unilateral distal radial fracture in 114 patients at eight to nine weeks after injury and again at one year. Our aim was to identify patients at risk for a delayed recovery and particularly those likely to develop complex regional pain syndrome. In order to quantify clinically the inflammatory response, a regional inflammatory score was developed. In addition, blood samples were collected from the antecubital veins of both arms for comparative biochemical and blood-gas analysis. The severity of the inflammatory response was related to the type of treatment (Kruskal-Wallis test, p = 0.002). A highly significantly-positive correlation was found between the regional inflammatory score and the length of time to full recovery (r2 = 0.92, p = 0.01, linear regession). A regional inflammatory score of 5 points with a sensitivity of 100% but a specificity of only 16% also identified patients at risk of complex regional pain syndrome. None of the biochemical parameters studied correlated with regional inflammatory score or predicted the development of complex regional pain syndrome. Our study suggests that patients with a distal radial fracture and a regional inflammatory score of 5 points or more at eight to nine weeks after injury should be considered for specific anti-inflammatory treatment.
In fully-grown mongrel dogs, diaphyseal ulnar defects 25 mm long were stabilised by screws and plates, and were temporarily filled with silicone rubber blocks. After eight weeks the block was replaced either by fresh autogeneic cancellous bone, allogeneic deep-frozen cancellous bone, allogeneic decalcified bone matrix, or bone matrix gelatin. After 24 weeks the implants were evaluated by radiography, histology, and measurements of new bone volume, using computer-assisted density registration on microradiographs. Only the autogeneic bone grafts led to healing in all instances. Bone regeneration in the other groups was not significantly better than in the sham group in which no graft was employed. Decalcified bone matrix proved ineffective.
