Publications by authors named "A Ouertani Meddeb"
Rationale And Objectives: Training Convolutional Neural Networks (CNN) requires large datasets with labeled data, which can be very labor-intensive to prepare. Radiology reports contain a lot of potentially useful information for such tasks. However, they are often unstructured and cannot be directly used for training.
View Article and Find Full Text PDFBackground High-quality translations of radiology reports are essential for optimal patient care. Because of limited availability of human translators with medical expertise, large language models (LLMs) are a promising solution, but their ability to translate radiology reports remains largely unexplored. Purpose To evaluate the accuracy and quality of various LLMs in translating radiology reports across high-resource languages (English, Italian, French, German, and Chinese) and low-resource languages (Swedish, Turkish, Russian, Greek, and Thai).
View Article and Find Full Text PDFAn easy and efficient approach for the synthesis of highly regioselective functionalized dihydronaphthalen-1(2)-one family of α-tetralones from functionalized tetralone precursors which derived from Morita-Baylis-Hillman (MBH) adducts as starting substrates has been developed. The target dihydronaphthalen-1(2)-ones are obtained through the oxidation of tetrahydronaphthalenes (THN) using DDQ as the oxidizing agent, conducted in aqueous acetic acid at reflux conditions. The yields obtained ranged from 90 to 98%.
View Article and Find Full Text PDFArticle Synopsis
- A study evaluated the effectiveness of open-source large language models (LLMs) in extracting clinical data from unstructured mechanical thrombectomy reports for ischemic stroke patients.
- Three models (Mixtral, Qwen, BioMistral) were tested using data from two institutions, showing varying performance in precision and recall for clinical data categories.
- The findings suggest that LLMs, especially when combined with a human-in-the-loop approach, can significantly improve the efficiency and accuracy of clinical data extraction, with time savings of around 65.6% per case.
Objective: To establish a deep learning model for the detection of hypoxic-ischemic encephalopathy (HIE) features on CT scans and to compare various networks to determine the best input data format.
Methods: 168 head CT scans of patients after cardiac arrest were retrospectively identified and classified into two categories: 88 (52.4%) with radiological evidence of severe HIE and 80 (47.