Rapid formation of aortoesophageal fistula complicated by mycotic thoracic aortic aneurysm secondary to infective endocarditis.

A 73-year-old man was admitted with four weeks of intermittent fever. He had a history of total aortic arch replacement for aortic arch aneurysm four years prior. CT scans showed no abnormalities before admission. Repeated blood cultures yielded Streptococcus anginosus and Prevotella melaninogenica, suggesting infective endocarditis (IE). Transesophageal echocardiography revealed a vegetation on the aortic valve, confirming IE. He suddenly presented with massive hematemesis and hypotension. Endoscopy revealed an elevated lesion with a laceration but no active bleeding in the esophagus. CT scans showed a thoracic aneurysm involving the esophagus. A diagnosis of aortoesophageal fistula (AEF) complicated by mycotic thoracic aortic aneurysm (MTAA) was made, and he underwent stent graft interpolation followed by minimally invasive esophagectomy. MTAAs are more prone to rupture than arteriosclerotic aneurysms as they are usually not true but pseudoaneurysms. Antecedent infection, including endocarditis, sepsis, predisposes to MTAA. AEF is a rare but life-threatening cause of gastrointestinal bleeding characterized by Chiari's triad. There have been no reports of such rapid formation of AEF after the graft replacement, as shown here. A recent article reported a rapid formation (16 days) of AEF after thoracic endovascular aortic repair, emphasizing prosthetic infection as the most important risk factor. Our case underscores the importance of suspecting AEF and conducting repeated appropriate examinations even if initial examinations do not reveal any aneurysms.

Comparison of the Ability of Artificial-Intelligence-Based Computer-Aided Detection (CAD) Systems and Endoscopists to Detect Colorectal Neoplastic Lesions on Endoscopy Video.

Artificial-intelligence-based computer-aided diagnosis (CAD) systems have developed remarkably in recent years. These systems can help increase the adenoma detection rate (ADR), an important quality indicator in colonoscopies. While there have been many still-image-based studies on the usefulness of CAD, few have reported on its usefulness using actual clinical videos. However, no studies have compared the CAD group and control groups using the exact same case videos. This study aimed to determine whether CAD or endoscopists were superior in identifying colorectal neoplastic lesions in videos. In this study, we examined 34 lesions from 21 cases. CAD performed better than four of the six endoscopists (three experts and three beginners), including all the beginners. The time to lesion detection with beginners and experts was 2.147 ± 1.118 s and 1.394 ± 0.805 s, respectively, with significant differences between beginners and experts (p < 0.001) and between beginners and CAD (both p < 0.001). The time to lesion detection was significantly shorter for experts and CAD than for beginners. No significant difference was found between experts and CAD (p = 1.000). CAD could be useful as a diagnostic support tool for beginners to bridge the experience gap with experts.