Tarek Souaid

Aim: Assessing the visual accuracy of two large language models (LLMs) in microbial classification. Materials & methods: GPT-4o and Gemini 1.5 Pro were evaluated in distinguishing Gram-positive from Gram-negative bacteria and classifying them as cocci or bacilli using 80 Gram stain images from a labeled database. Results: GPT-4o achieved 100% accuracy in identifying simultaneously Gram stain and shape for Clostridium perfringens, Pseudomonas aeruginosa and Staphylococcus aureus. Gemini 1.5 Pro showed more variability for similar bacteria (45, 100 and 95%, respectively). Both LLMs failed to identify both Gram stain and bacterial shape for Neisseria gonorrhoeae. Cumulative accuracy plots indicated that GPT-4o consistently performed equally or better in every identification, except for Neisseria gonorrhoeae's shape. Conclusion: These results suggest that these LLMs in their unprimed state are not ready to be implemented in clinical practice and highlight the need for more research with larger datasets to improve LLMs' effectiveness in clinical microbiology.

Aim: This study investigated the association between plasma levels of GDF-15, hs-cTnT and NT-proBNP and the presence of coronary artery disease (CAD) in stable patients referred for elective corona... Plain language summary This study aimed to look at a possible association between blood levels of three molecules (GDF-15, hs-cTnT and N-terminal pro B-type natriuretic peptide [NT-proBNP]) and the...

Aim: Assess the knowledge and behavior of Lebanese parents when it comes to melanoma and its prevention in children. Methods: A survey, to be completed by parents, was sent through children from th...

Bladder cancer (BC) is the most common cancer involving the urinary system and the ninth most common cancer worldwide. Tobacco smoking is the most important environmental risk factor of BC. Several...