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:
The quantification of local bone blood flow in man has not previously been possible, despite its importance in the study of normal and pathological bone. We report the use of positron emission tomography, using 15O-labelled water, to measure bone blood flow in patients with closed unilateral fractures of the tibia. We compared fractured and unfractured limbs; alterations in blood flow paralleled those found in animal models. There was increased tibial blood flow at the fracture site as early as 24 hours after fracture, reaching up to 14 times that in the normal limb at two weeks. Blood flow increase was less in displaced than in undisplaced fractures. The muscle to bone ratios of blood flow were similar to those in previous animal work using other techniques. Positron emission tomography will allow study of human bone blood flow in vivo in a wide variety of pathological conditions.
We have assessed the current range of synthetic splinting bandages, using physical and mechanical tests and the subjective opinions of patients, volunteers and orthopaedic staff. Modern bandages have some better properties than standard plaster bandage but do not conform as well, are more expensive, and potentially more hazardous.
