Browsing by Author "Schuit Condell, Gregory Kees"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Enhancing Feedback Uptake and Self-Regulated Learning in Procedural Skills Training
    (2024) Villagrán Gutiérrez, Ignacio Andrés; Hernández Román, Rocío Belén; Schuit Condell, Gregory Kees; Neyem, Hugo Andrés; Fuentes Cimma, Javiera Carolina; Larrondo Vergara, María Loreto; Margozzini Delorenzo, Elisa; Hurtado Bunster, María Teresa; Iriarte Vásquez, Zoe; Miranda Mendoza, Constanza Sofía; Varas Cohen, Julián Emanuel; Hilliger Carrasco, Isabel
    Remote technology has been widely incorporated into health professions education. For procedural skills training, effective feedback and reflection processes are required. Consequently, supporting a self-regulated learning (SRL) approach with learning analytics dashboards (LADs) has proven beneficial in online environments. Despite the potential of LADs, understanding their design to enhance SRL and provide useful feedback remains a significant challenge. Focusing on LAD design, implementation, and evaluation, the study followed a mixed-methods two-phase design-based research approach. The study used a triangulation methodology of qualitative interviews and SRL and sensemaking questionnaires to comprehensively understand the LAD’s effectiveness and student SRL and feedback uptake strategies during remote procedural skills training. Initial findings revealed the value students placed on performance visualization and peer comparison despite some challenges in LAD design and usability. The study also identified the prominent adoption of SRL strategies such as help-seeking, elaboration, and strategic planning. Sensemaking results showed the value of personalized performance metrics and planning resources in the LAD and recommendations to improve reflection and feedback uptake. Subsequent findings suggested that SRL levels significantly predicted the levels of sensemaking. The students valued the LAD as a tool for supporting feedback uptake and strategic planning, demonstrating the potential for enhancing procedural skills learning.
  • Thumbnail Image
    Item
    Inovações no treinamento cirúrgico: explorando o papel da inteligência artificial e dos grandes modelos de linguagem (LLM)
    (2023) Varas Cohen, Julián Emanuel; Valencia Coronel, Brandon; Villagrán Gutiérrez, Ignacio Andrés; Escalona Vivas, Gabriel Enrique; Hernández Román, Rocío Belén; Schuit Condell, Gregory Kees; Duran Espinoza, Valentina Alexandra; Lagos Villaseca, Antonia Elisa; Jarry Trujillo, Cristián Ignacio; Neyem, Hugo Andrés; Achurra Tirado, Pablo Andrés
    O cenário do treinamento cirúrgico está evoluindo rapidamente com o surgimento da inteligência artificial (IA) e sua integração na educação e simulação. Este artigo explora as aplicações e benefícios potenciais do treinamento cirúrgico assistido por IA, em particular o uso de modelos de linguagem avançados (MLAs), para aprimorar a comunicação, personalizar o feedback e promover o desenvolvimento de habilidades. Discutimos os avanços no treinamento baseado em simulação, ferramentas de avaliação impulsionadas por IA, sistemas de avaliação baseados em vídeo, plataformas de realidade virtual (RV) e realidade aumentada (RA), e o papel potencial dos MLAs na transcrição, tradução e resumo do feedback. Apesar das oportunidades promissoras apresentadas pela integração da IA, vários desafios devem ser abordados, incluindo precisão e confiabilidade, preocupações éticas e de privacidade, viés nos modelos de IA, integração com os sistemas de treinamento existentes, e treinamento e adoção de ferramentas assistidas por IA. Ao abordar proativamente esses desafios e aproveitar o potencial da IA, o futuro do treinamento cirúrgico pode ser remodelado para proporcionar uma experiência de aprendizado mais abrangente, segura e eficaz para os aprendizes, resultando em melhores resultados para os pacientes.
  • Thumbnail Image
    Item
    Perceptual Evaluation of GANs and Diffusion Models for Generating X-Rays
    (2025) Schuit Condell, Gregory Kees; Parra Santander, Denis Alejandro; Besa Correa, Cecilia
    Generative image models have achieved remarkable progress in both natural and medical imaging. In the medical context, these techniques offer a potential solution to data scarcity-especially for low-prevalence anomalies that impair the performance of AI-driven diagnostic and segmentation tools. However, questions remain regarding the fidelity and clinical utility of synthetic images, since poor generation quality can undermine model generalizability and trust. In this study, we evaluate the effectiveness of state-of-the-art generative models-Generative Adversarial Networks (GANs) and Diffusion Models (DMs)-for synthesizing chest X-rays conditioned on four abnormalities: Atelectasis (AT), Lung Opacity (LO), Pleural Effusion (PE), and Enlarged Cardiac Silhouette (ECS). Using a benchmark composed of real images from the MIMIC-CXR dataset and synthetic images from both GANs and DMs, we conducted a reader study with three radiologists of varied experience. Participants were asked to distinguish real from synthetic images and assess the consistency between visual features and the target abnormality. Our results show that while DMs generate more visually realistic images overall, GANs can report better accuracy for specific conditions, such as absence of ECS. We further identify visual cues radiologists use to detect synthetic images, offering insights into the perceptual gaps in current models. These findings underscore the complementary strengths of GANs and DMs and point to the need for further refinement to ensure generative models can reliably augment training datasets for AI diagnostic systems.