Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: a multicentre survey.

OBJECTIVES: To explore the attitudes of United Kingdom (UK) medical students regarding artificial intelligence (AI), their understanding, and career intention towards radiology. We also examine the state of education relating to AI amongst this cohort. METHODS: UK medical students were invited to complete an anonymous electronic survey consisting of Likert and dichotomous questions. RESULTS: Four hundred eighty-four responses were received from 19 UK medical schools. Eighty-eight percent of students believed that AI will play an important role in healthcare, and 49% reported they were less likely to consider a career in radiology due to AI. Eighty-nine percent of students believed that teaching in AI would be beneficial for their careers, and 78% agreed that students should receive training in AI as part of their medical degree. Only 45 students received any teaching on AI; none of the students received such teaching as part of their compulsory curriculum. Statistically, students that did receive teaching in AI were more likely to consider radiology (p = 0.01) and rated more positively to the questions relating to the perceived competence in the post-graduation use of AI (p = 0.01-0.04); despite this, a large proportion of students in the taught group reported a lack of confidence and understanding required for the critical use of healthcare AI tools. CONCLUSIONS: UK medical students understand the importance of AI and are keen to engage. Medical school training on AI should be expanded and improved. Realistic use cases and limitations of AI must be presented to students so they will not feel discouraged from pursuing radiology.

Pediatric Esophageal Dilatations: A Cross-Specialty Experience.

Aim of the Study: Esophageal dilatations are commonly performed in pediatric patients who have undergone an esophageal atresia/tracheoesophageal fistula (EA/TEF) repair or following caustic injury. We sought to compare the practice of esophageal dilatation across different specialties. Methods: We analyzed all patients who had an esophageal dilatation at our center between April 2014 and December 2018. Patients were identified via prospectively maintained databases and clinical coding records. Patients had a combination of dilatations under each specialty: interventional radiology (IR), surgery, and gastroenterology. Results: Thirty-five individual patients underwent 226 dilatations, median dilatations per patient was 3 (1-40). The median age at first dilatation was 18 months (1-194 months). Sixty-eight percent of patients had a previous EA/TEF repair. IR performed 59% of dilatations, surgeons 26%, and 15% by gastroenterologists. Surgeons more frequently were performing initial dilatations (P < .05) and performed more dilatations in EA/TEF patients (P < .0001). There was a significant difference between the time from a surgical dilatation until the next dilatation, 3.7 months, compared with an IR dilatation, 1.8 months (ANOVA, P < .05). Surgeons more frequently increased the size of balloon used (57% versus 33% versus 39%, P < .01). There was no significant difference in balloon size between specialties or in the incremental increase in size between subsequent dilatations. There was one postprocedure perforation, managed conservatively (complication rate = 0.4%). Conclusion: We have demonstrated that on average, patients wait longer after a surgical dilatation until their next procedure, and surgical teams are more likely to increase the size of the dilating balloon. Surgeons tend to be more involved in their postoperative patients in the initial phases of stricture management. Our results suggest the feasibility and safety of a multispecialty approach for these patients.

Extravascular findings during upper limb computed tomographic angiography focusing on undiagnosed malignancy.

BACKGROUND: Computer tomography angiography (CTA) has been an established method for diagnostic vascular disease of lower limbs. Recently, the method is widely used for diagnosis of vascular pathologies in the upper limbs too. It also has increased the possibilities of this scans being reviewed by no specially trained radiologists. This increases the risk of incidental non vascular findings to be missed or misinterpreted. The study is focusing in the frequency of extravascular incidental finding (EVIF) and highlights the importance for both the reporting radiologist and the referring physician recognizing the frequency of EVIFs. AIM: To analyse the frequency of EVIF identified on computed angiography (CT) of the upper limb. METHODS: A total of 1383 CT angiographic studies of the peripheral arterial system were performed between August 2015 and August 2017. All upper limb CTAs (n = 79) were retrospectively reviewed for the presence of non-vascular incidental findings within the chest, abdomen/pelvis, musculoskeletal system or head and neck. These EVIFs were subsequently grouped into 3 categories based on clinical significance. EVIFs of immediate clinical relevance were included in category A, findings considered indeterminate but most likely benign were placed in category B, while incidental findings of no clinical significance were included in category C. RESULTS: Complete imaging datasets were available in 74/79 (93.7%). Patient demographics included 39 (52.7%) females and 35 (47.2%) males with a mean age of 59 ± 19.5 years (range 19-93 years). A total of 153 EVIFs were reported in 52 patients (70.3%). Of these, 44 EVIFs (28.7%) were found in the chest, 83 (54.2%) in the abdomen, 14 (9.2%) in the musculoskeletal system and 9 (5.8%) in the head and neck. Thirteen EVIFs (8.4%) identified in 11 patients were noted to be of immediate clinical significance (Category A), 50 EVIFs (32.3%) were identified in 20 patients and were considered indeterminate but most likely benign, while the remaining 91 EVIFs (59.5%) identified in 21 patients were determined to be of no clinical significance (Category C). One index case of malignancy (1.3%) and four cases of new disseminated metastatic disease (5.4%) were identified. CONCLUSION: Our study of upper limb CTA examinations demonstrated a frequency of 8.4% for extravascular incidental findings of immediate clinical significance. We highlight the importance for both the reporting radiologist and the referring physician of the need to recognize the frequency with which EVIFs are identified in the upper limb peripheral arterial system and of the necessity for further clinical and imaging work-up.