Publications by authors named "A P Osadchiy"
The article describes our experience in developing and training an artificial neural network based on artificial intelligence algorithms for recognizing the characteristic features of benign laryngeal tumors and variants of the norm of the larynx based on the analysis of laryngoscopy pictures obtained during the examination of patients. During the preparation of data for training the neural network, a dataset was collected, labeled and loaded, consisting of 1471 images of the larynx in digital formats (jpg, bmp). Next, the neural network was trained and tested in order to recognize images of the norm and neoplasms of the larynx.
View Article and Find Full Text PDFArticle Synopsis
- Left atrial appendage (LAA) occluder embolization is a rare but critical complication occurring mostly within the first 24 hours after the procedure, with data collected from 67 centers on 108 patients.
- The management strategies included attempting percutaneous retrieval in 75% of cases, while 21.3% of patients underwent surgery without prior attempts, highlighting significant mortality rates associated with multiple retrieval attempts.
- Overall, a major adverse event rate of 43.5% was observed, underscoring the serious risks, including death, particularly following unsuccessful retrievals.