Evaluation of a context-aware chatbot using retrieval-augmented generation for answering clinical questions on medication-related osteonecrosis of the jaw.

The potential of large language models (LLMs) in medical applications is significant, and Retrieval-augmented generation (RAG) can address the weaknesses of these models in terms of data transparency and scientific accuracy by incorporating current scientific knowledge into responses. In this study, RAG and GPT-4 by OpenAI were applied to develop GuideGPT, a context aware chatbot integrated with a knowledge database from 449 scientific publications designed to provide answers on the prevention, diagnosis, and treatment of medication-related osteonecrosis of the jaw (MRONJ). A comparison was made with a generic LLM ("PureGPT") across 30 MRONJ-related questions.

Effects of a Diet of Extract on Growth, Biochemistry, Metabolism, and Gut Microbiota of Rabbits ).

The rabbit farming industry is growing due to the rising demand for healthy, sustainable meat. Rabbit meat's nutritional benefits and low environmental impact appeal to health-conscious consumers. To enhance economic sustainability, efforts focus on reducing disease susceptibility and antibiotic use through improved biosecurity and natural additives, such as organosulphur compounds from plants, which have shown promise in studies for boosting productivity and health.

Pipeline for Planning and Execution of Transcranial Ultrasound Neuromodulation Experiments in Humans.

Transcranial ultrasound stimulation (TUS) is an emerging non-invasive neuromodulation technique capable of manipulating both cortical and subcortical structures with high precision. Conducting experiments involving humans necessitates careful planning of acoustic and thermal simulations. This planning is essential to adjust for bone interference with the ultrasound beam's shape and trajectory and to ensure TUS parameters meet safety requirements.