HAL-UJM
Not a member yet
95306 research outputs found
Sort by
Is the brainstem involved in Robin Sequence? Results of heart rate analysis Dysrobin
No full textInternational audienc
Profile and Usefulness of Serum Cytokines to Predict Prognosis in Myelin Oligodendrocyte Glycoprotein Antibody−Associated Disease
No full textInternational audienc
Score MAS et variables biomécaniques : degré d'accord entre deux kinésithérapeutes sur un même patient
No full textInternational audienc
Contribution des pratiques artistiques performatives au déploiement d'un espace d'apprentissage vivant (ré)conciliant savoir et être
No full textInternational audienceCet article se propose de tisser des liens entre théâtre et arts plastiques en s’appuyant sur leur caractère praxique. Nous abordons les questions épistémologiques liées à la disciplinarisation des arts plastiques au regard des enjeux de l’art tout en questionnant les modalités didactiques de cet enseignement en les reliant à la pratique théâtrale. Cette approche est accompagnée de l’analyse d’un projet arts de la scène où nous exposons comment les dialogues entre les deux domaines ont une incidence sur le corps de l’élève en action, en relation avec ses pairs mais aussi en relation avec l’espace comme lieu du faire
Dupilumab in atopic-dermatitis-like eczema associated with inborn errors of immunity: A nationwide study
No full textInternational audienc
Enhancing healthcare resource allocation through large language models
No full textInternational audienceRecognizing the growing capabilities of large language models (LLMs) and their potential in healthcare, this study explores the application of LLMs in healthcare resource allocation using Prompt Engineering, Retrieval-Augmented Generation (RAG), and Tool Utilization. It addresses both optimizable and non-optimizable challenges in allocating operating rooms (ORs), postoperative beds, and surgeons, while also identifying key factors like ethical and legal constraints through a medical knowledge Q&A survey. Among the seven evaluated LLMs, including LaMDA 2, PaLM 2, and Qwen, ChatGPT-4o demonstrated superior performance by reducing OR and surgeon overtime, alleviating peak bed demand, and achieving the highest accuracy in medical knowledge queries. Comprehensive comparisons with traditional methods (exact and heuristic algorithm), varying problem sizes, and hybrid approaches from the literature revealed that as problem size increased, LLMs performed better and faster by integrating historical experience with new data. They adapted to changes in problem scale or demand without requiring re-optimization, effectively addressing the runtime limitations of traditional methods. These findings underscore the potential of LLMs in advancing dynamic and efficient healthcare resource management