ABSTRACT
Objective Evaluating an artificial intelligence (AI) tool (AIATELLA, version 1.0; AIATELLA Oy, Helsinki, Finland) in interpreting cardiac magnetic resonance (CMR) imaging to produce measurements of the aortic root and valve by comparison of accuracy and efficiency with that of three National Health Service (NHS) cardiologists. Methods AI-derived aortic root and valve measurements were recorded alongside manual measurements from three experienced NHS consultant cardiologists (CCs) over three separate sites in the northeast part of the United Kingdom. The study utilised a comprehensive dataset of CMR images, with the intraclass correlation coefficient (ICC) being the primary measure of concordance between the AI and the cardiologist assessments. Patient imaging was anonymised and blinded at the point of transfer to a secure data server. Results The study demonstrates a high level of concordance between AI assessment of the aortic root and valve with NHS cardiologists (ICC of 0.98). Notably, the AI delivered results in 2.6 seconds (+/- 0.532) compared to a mean of 334.5 seconds (+/- 61.9) by the cardiologists, a statistically significant improvement in efficiency without compromising accuracy. Conclusion AI's accuracy and speed of analysis suggest that it could be a valuable tool in cardiac diagnostics, addressing the challenges of time-consuming and variable clinician-based assessments. This research reinforces AI's role in optimising the patient journey and improving the efficiency of the diagnostic pathway.
ABSTRACT
INTRODUCTION: Focused assessment with sonography for trauma (FAST) ultrasound (US) is a valuable medical examination used in trauma settings, particularly for rapid responses to events such as natural disasters. Although the efficacy and benefits of FAST in patient care have been extensively studied, there is limited research on training medical students in FAST. Previous studies have found that medical students can proficiently perform a FAST US after two days of training. However, these studies exclusively included first-year medical students without considering variations in their medical knowledge. Particularly, the advantage of medical students having US experience before undergoing FAST training has not been previously examined. OBJECTIVES: Assess the performance and knowledge acquisition of medical students with and without prior US experience after completing a FAST training course. METHODS: The study included a total of 71 students, consisting of 33 males and 38 females, who were between the ages of 18 and 31, with an average age of 24.6 and a standard deviation of 2.4. The inclusion criteria targeted first- and second-year medical school students who participated on a volunteer basis. Students were divided into two groups: group A, consisting of those without prior US experience, and group B, made up of those who had previous US experience. All students completed a pre-training survey to share their comfort and confidence in US use and knowledge. A baseline FAST exam was conducted to establish initial performance. A comprehensive three-hour training session was then provided. Post-training, students performed another FAST exam to assess improvement, followed by a post-training survey to evaluate comfort and confidence. RESULTS: Medical students who had prior experience in the US (group B) performed significantly better (p<0.01) in both the pre- and post-training FAST exams when compared to students without previous US experience. Specifically, in locating the liver, right kidney, hepatorenal recess, and left kidney, as well as detecting fluid accumulation when in a supine position. Additionally, medical students with prior US experience (group B) exhibited higher baseline confidence (p<0.005-p<0.01) in their ability to perform a FAST exam, as indicated by the results of the pre-testing survey. CONCLUSION: Previous experience with US significantly boosted confidence and knowledge gains following FAST training. This emphasizes the value of including US training in medical school programs after earlier exposure, offering evident benefits. The study reveals the unexplored benefit of having prior US experience for medical students undergoing FAST training, thus addressing a previously unexplored area in current research. The conclusions stress the necessity of integrating US training into medical school curricula after initial exposure. This understanding can direct medical educators in refining the education process, enabling students to be better equipped for real-world medical situations involving FAST.
ABSTRACT
Conjoined twins are a rare phenomenon estimated to occur in a range between 1 in 49,000 births and 1 in 189,000 births. As a product of monochorionic-monoamniotic pregnancies, they are currently believed to result from late, incomplete fission of the bilaminar embryonic disk at 13-15 days gestation. Conjoined twins are typically classified by the point at which their bodies are joined, with 15 recognized types, five of which account for more than 70% of cases. Fusion of the thorax and upper abdomen (thoraco-omphalopagus) accounts for 28% of all cases. Mortality and morbidity rates remain high irrespective of the point of fusion, with 40-60% of cases being lost to miscarriage and stillbirth, and only about 18% of live births surviving more than 24 hours. Given this prognosis, knowledge of underlying anatomy and clinical imaging is paramount to antenatal diagnosis, assessment of viability, and subsequent management of conjoined twins. A case of thoraco-omphalopagus twins with a single heart and single liver discovered on routine ultrasound at 12 weeks gestation is described.
