Clinician and computer: a study on doctors' perceptions of artificial intelligence in skeletal radiography.

BACKGROUND: Traumatic musculoskeletal injuries are a common presentation to emergency care, the first-line investigation often being plain radiography. The interpretation of this imaging frequently falls to less experienced clinicians despite well-established challenges in reporting. This study presents novel data of clinicians' confidence in interpreting trauma radiographs, their perception of AI in healthcare, and their support for the development of systems applied to skeletal radiography. METHODS: A novel questionnaire was distributed through a network of collaborators to clinicians across the Southeast of England. Over a three-month period, responses were compiled into a database before undergoing statistical review. RESULTS: The responses of 297 participants were included. The mean self-assessed knowledge of AI in healthcare was 3.68 out of ten, with significantly higher knowledge reported by the most senior doctors (Specialty Trainee/Specialty Registrar or above = 4.88). 13.8% of participants reported an awareness of AI in their clinical practice. Overall, participants indicated substantial favourability towards AI in healthcare (7.87) and in AI applied to skeletal radiography (7.75). There was a preference for a hypothetical system indicating positive findings rather than ruling as negative (7.26 vs 6.20). CONCLUSIONS: This study identifies clear support, amongst a cross section of student and qualified doctors, for both the general use of AI technology in healthcare and in its application to skeletal radiography for trauma. The development of systems to address this demand appear well founded and popular. The engagement of a small but reticent minority should be sought, along with improving the wider education of doctors on AI.

Seasonal and climatic variation in the incidence of adult acute appendicitis: a seven year longitudinal analysis.

BACKGROUND: Acute appendicitis represents an extremely common surgical emergency, yet its aetiology remains uncertain. A multifactorial understanding of its causation has emerged along with increasing evidence of seasonal variation. This study seeks to find evidence for such a circannual trend within the United Kingdom (UK), and further assess key meteorological indicators which may be causative of any such variation. METHODS: The patient records of a region health body in the North East of England were retrospectively assessed over a 7-year period. The incident cases of acute appendicitis were recorded and averaged by month before undergoing statistical analysis for variation and correlation with average temperature, sunlight hours, and rainfall. RESULTS: The incidence of acute appendicitis revealed significant seasonal variation with only 38 incident cases in the months of January compared to 73 in July, a 92.1% increase. Only a weak correlation was seen between incidence and average sunlight hours/rainfall, however a significant, positive correlation was found between incidence and average temperature (r = 0.58, p = 0.048). CONCLUSION: Compelling evidence is found to support the existence of a circannual trend for acute appendicitis. Data suggests a seasonal peak in the month of July, accompanied by a low in January, a finding that develops the understanding of this trend from previously equivocal research in the UK. A clear correlation is also established between the incidence of acute appendicitis and average temperature. The 92.1% increase between the coolest and warmest months suggests a greater magnitude for this as a risk factor than has previously been shown.

Reporting Discrepancy Resolved by Findings and Time in 2947 Emergency Department Ankle X-rays.

AIMS: To identify common errors in ankle X-ray reporting between initial interpretation and final assessment at the virtual fracture clinic. Also, to assess time of initial reporting as a causative factor for discrepancy. METHODS: Two thousand nine hundred forty-seven final reports were reviewed by standard of agreement to the initial interpretation. Where discrepancy was found, it was classified and collated by specific finding. Comparison was made between reports with discrepancy and the complete dataset, allowing rates of error by finding to be established. The reports containing discrepancy were further classified by time period, this was compared against an expected value to establish if initial reporting outside of routine working hours was as accurate as that conducted within routine working hours. RESULTS: 94.4% of reports were in agreement with the initial interpretation, 2.9% contained minor discrepancy, and 2.7% major discrepancy. In 45.6% of reports there was no radiologically observable injury. 16.4% of reports contained a lateral malleolar fracture, most commonly Weber type B. 40.0% of all navicular fractures, and 33.3% of all cuboidal fractures were not commented upon in the initial reporting. Lower rates of more frequently observed findings were missed with 2.5% of Weber type B fractures not commented upon. An increased proportion of major discrepancy reports were generated from 00:00 to 07:59 (expected = 15.0%, observed = 22.2%; p = 0.07908). Similarly, a greater than expected number of minor discrepancy reports were found between 20:00 and 23:59 (expected = 18.0%, observed = 34.1%, p = 0.00025). CONCLUSIONS: The initial reporting of ankle X-rays in the emergency department is performed to a high standard, however serious missed findings emphasise the need for timely senior review. Reporters should increase their awareness of navicular, cuboid, talar, and Weber A fractures which were missed at disproportionate rates. This study also finds evidence to support increased rates of error in initial reporting of ankle X-rays outside of normal working hours (17:00-07:59), particularly with a significantly increased rate of minor discrepancy seen from 20:00 to 23:59.