Background
Infective endocarditis (IE) is a serious infection with high morbidity and mortality that involves the endocardial lining of the heart. Most cases of IE are due to bacteria although other atypical microorganisms can also be involved. Procalcitonin (PCT) is a biomarker that is used in the diagnosis of bacterial infections.
Case summary
We present the case of a 54-year-old patient with bacterial endocarditis who has been regularly visiting his cardiologist for follow-up on a mitral valve prolapse and moderate mitral regurgitation (MR) for the last 11 years. During his last visit transthoracic echocardiography (TTE) showed a previously non-existent structure on the posterior mitral valve leaflet (PMVL) with severe MR. Blood cultures were positive for Streptococcus viridans. On admission he had elevated levels of PCT and C-reactive protein (CRP) which returned to normal values after 4 weeks of intravenous antibiotic therapy. His follow-up blood cultures, taken after normalization of PCT, did not show bacterial growth; however, on TTE he had severe mitral regurgitation and a persistent vegetation which had slightly increased in size after completion of the full antibiotic course. He was referred for mitral valve replacement (MVR) surgery.
Discussion
Normalization of procalcitonin levels may correlate with negative blood cultures in cases of IE with residual vegetations. The optimal time for surgery in such patients is difficult to define but even in circumstances with less infective organisms such as S. viridans and late in the course of the disease residual vegetations remain a serious risk factor for embolic events. Randomized controlled clinical trials are needed in order to have better recommendations with solid evidence regarding prophylaxis and treatment in IE.
Extracting the most important part of legislation documents has great business value because the texts are usually very long and hard to understand. The aim of this article is to evaluate different algorithms for text summarization on EU legislation documents. The content contains domain-specific words. We collected a text summarization dataset of EU legal documents consisting of 1563 documents, in which the mean length of summaries is 424 words. Experiments were conducted with different algorithms using the new dataset. A simple extractive algorithm was selected as a baseline. Advanced extractive algorithms, which use encoders show better results than baseline. The best result measured by ROUGE scores was achieved by a fine-tuned abstractive T5 model, which was adapted to work with long texts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.