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
To evaluate if union of clavicle fractures can be predicted at six weeks post-injury by the presence of bridging callus on ultrasound. Adult patients managed nonoperatively with a displaced mid-shaft clavicle were recruited prospectively. Ultrasound evaluation of the fracture was undertaken to determine if sonographic bridging callus was present. Clinical risk factors at six weeks were used to stratify patients at high risk of nonunion with a combination of Quick Disabilities of the Arm, Shoulder and Hand questionnaire (QuickDASH) ≥ 40, fracture movement on examination, or absence of callus on radiograph.Aims
Methods
Follow-up radiographs are usually used as the
reference standard for the diagnosis of suspected scaphoid fractures. However,
these are prone to errors in interpretation. We performed a meta-analysis
of 30 clinical studies on the diagnosis of suspected scaphoid fractures,
in which agreement data between any of follow-up radiographs, bone scintigraphy,
magnetic resonance (MR) imaging, or CT could be obtained, and combined
this with latent class analysis to infer the accuracy of these tests
on the diagnosis of suspected scaphoid fractures in the absence
of an established standard. The estimated sensitivity and specificity
were respectively 91.1% and 99.8% for follow-up radiographs, 97.8%
and 93.5% for bone scintigraphy, 97.7% and 99.8% for MRI, and 85.2%
and 99.5% for CT. The results were generally robust in multiple
sensitivity analyses. There was large between-study heterogeneity
for the sensitivity of follow-up radiographs and CT, and imprecision
about their sensitivity estimates. If we acknowledge the lack of a reference standard for diagnosing
suspected scaphoid fractures, MRI is the most accurate test; follow-up
radiographs and CT may be less sensitive, and bone scintigraphy
less specific.
A suspected fracture of the scaphoid remains difficult to manage despite advances in knowledge and imaging methods. Immobilisation and restriction of activities in a young and active patient must be balanced against the risks of nonunion associated with an undiagnosed and undertreated fracture of the scaphoid. The assessment of diagnostic tests for a suspected fracture of the scaphoid must take into account two important factors. First, the prevalence of true fractures among suspected fractures is low, which greatly reduces the probability that a positive test will correspond with a true fracture, as false positives are nearly as common as true positives. This situation is accounted for by Bayesian statistics. Secondly, there is no agreed reference standard for a true fracture, which necessitates the need for an alternative method of calculating diagnostic performance characteristics, based upon a statistical method which identifies clinical factors tending to associate (latent classes) in patients with a high probability of fracture. The most successful diagnostic test to date is MRI, but in low-prevalence situations the positive predictive value of MRI is only 88%, and new data have documented the potential for false positive scans. The best strategy for improving the diagnosis of true fractures among suspected fractures of the scaphoid may well be to develop a clinical prediction rule incorporating a set of demographic and clinical factors which together increase the pre-test probability of a fracture of the scaphoid, in addition to developing increasingly sophisticated radiological tests.
Restoration of hand function is rarely achieved after a complete closed traction lesion of the supraclavicular brachial plexus. We describe the injury, treatment, rehabilitation and long-term results of two patients who regained good function of the upper limb and useful function in the hand after such an injury. Successful repairs were performed within six days of injury. Tinel’s sign proved accurate in predicting the ruptures and the distribution of pain was accurate in predicting avulsion. The severe pain that began on the day of injury resolved with the onset of muscle function. Recovery of muscle function preceded recovery of sensation. Recovery of the function of C and Aδ fibres was the slowest of all.
The diagnosis of nerve injury using thermotropic liquid crystal temperature strips was compared blindly and prospectively against operative findings in 36 patients requiring surgical exploration for unilateral upper limb lacerations with suspected nerve injury. Thermotropic liquid crystal strips were applied to affected and non-affected segments in both hands in all subjects. A pilot study showed that a simple unilateral laceration without nerve injury results in a cutaneous temperature difference between limbs, but not within each limb. Thus, for detection of a nerve injury, comparison was made against the unaffected nerve distribution in the same hand. Receiver operating characteristic curve analysis showed that an absolute temperature difference ≥ 1.0°C was diagnostic of a nerve injury (area under the curve = 0.985, sensitivity = 100%, specificity = 93.8%). Thermotropic liquid crystal strip assessment is a new, reliable and objective method for the diagnosis of traumatic peripheral nerve injuries. If implemented in the acute setting, it could improve the reliability of clinical assessment and reduce the number of negative surgical explorations.
Our aim was to determine the clinical value of MRI and CT arthrography in predicting the presence of loose bodies in the elbow. A series of 26 patients with mechanical symptoms in the elbow had plain radiography, MRI and CT arthrography, followed by routine arthroscopy of the elbow. The location and number of loose bodies determined by MRI and CT arthrography were recorded. Pre-operative plain radiography, MRI and CT arthrography were compared with arthroscopy. Both MRI and CT arthrography had excellent sensitivity (92% to 100%) but low to moderate specificity (15% to 77%) in identifying posteriorly-based loose bodies. Neither MRI nor CT arthrography was consistently sensitive (46% to 91%) or specific (13% to 73%) in predicting the presence or absence of loose bodies anteriorly. The overall sensitivity for the detection of loose bodies in either compartment was 88% to 100% and the specificity 20% to 70%. Pre-operative radiography had a similar sensitivity and specificity of 84% and 71%, respectively. Our results suggest that neither CT arthrography nor MRI is reliable or accurate enough to be any more effective than plain radiography alone in patients presenting with mechanical symptoms in the elbow.
