Publications by authors named "Sophia Denizon-Arranz"

Objectives: We evaluate the effectiveness of large language models (LLMs), specifically GPT-based (GPT-3.5 and GPT-4) and Llama-2 models (13B and 7B architectures), in autonomously assessing clinical records (CRs) to enhance medical education and diagnostic skills.

Materials And Methods: Various techniques, including prompt engineering, fine-tuning (FT), and low-rank adaptation (LoRA), were implemented and compared on Llama-2 7B.

View Article and Find Full Text PDF

From the beginning of their clinical training, medical students demonstrate difficulties when incorporating patient perspectives. This study aimed to assess if students, after an instructional programme, increased their sensitivity towards patients' needs and carried out bidirectional conversations. An observational study involving 109 medical students prior to their clerkships was designed.

View Article and Find Full Text PDF

Background: Higher education training in Medicine has considerably evolved in recent years. One of its main goals has been to ensure the training of students as future adequately qualified general practitioners (GPs). Tools need to be developed to evaluate and improve the teaching of Urology at the undergraduate level.

View Article and Find Full Text PDF

Simulations with standardized patients (SP) have long been used for teaching/assessing communication skills. The present study describes and evaluates an experiential training methodology aimed at medical students and based on interviews with standardized simulated patients. The training was focused on developing basic communication skills and taking medical histories.

View Article and Find Full Text PDF

Aim: Family medicine deals with certain aspects and perspectives that are often left behind in the training of other levels of care, thus the need for medical students to make contact with Primary Care is of increasing importance. The aim of this study is to evaluate the reliability of the questionnaire of the UNIMEDIFAM group (FIS PI070975) for the long-term outcome of expectations and knowledge about family medicine.

Design: Reliability of a questionnaire.

View Article and Find Full Text PDF