Browsing by Author "Jarry T., Cristián"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A scalable solution: effective AI implementation in laparoscopic simulation training assessments
    (2025) Cruz, Enrique; Selman, Rafael; Figueroa, Úrsula; Belmar, Francisca; Jarry T., Cristián; Sanhueza, Diego; Escalona, Gabriel; Carnier, Martín; Varas Cohen, Julián
    Purpose Simulation-based training offers considerable benefits in surgical education, especially in mastering minimally invasive techniques such as laparoscopy. However, its widespread adoption faces challenges, particularly in teaching scalability and consistent assessment of trainees’ performance. Artificial Intelligence (AI) has emerged as a promising tool to address these issues, offering possible solutions for optimizing exercise evaluation in simulation programs. This study aims to validate the integration of the YOLO v4 artificial intelligence model into a laparoscopic simulation training program from a video-based feedback-oriented platform. Methods Focusing on object detection and time measurement, the evaluation included a dataset of 7673 videos, extracting 100 random video frames per exercise for object detection with precision, recall, and F1-score calculations based on AI expert tags for each frame, and using 80 videos per exercise for time analysis compared to established times by platform expert teachers. Results With a total of 1100 frames assessed, the YOLO v4 model consistently exhibited high precision with a mean precision of 0.94 and mean recall of 0.89 across object detection tasks, with F1-scores ranging from 0.81 to 0.97. Time measurement accuracy based on 880 assessed videos showed a correlation with mean Pearson correlation coefficient of 0.960 for mean absolute error (MAE) across exercises with the timings of platform expert evaluators. Conclusions The YOLO v4 model proves to be an effective tool for laparoscopic training assessments. The model's high precision and strong correlation with expert assessments demonstrate its usefulness in optimizing the evaluation process in simulated laparoscopic training exercises. This intervention leads the way in surgery education by effectively addressing the need for scalable and standardized assessment methods facilitating the transition towards automated evaluations.
  • Thumbnail Image
    Item
    Desarrollo y evaluación de modelo ex vivo para entrenamiento de anastomosis intracorpórea en hemicolectomía derecha laparoscópica
    (2020) Jarry T., Cristián; Inzunza A., Martín; Bellolio R., Felipe; Marino C., Carlo; Achurra Tirado, Pablo; Varas Cohen, Julián; Larach Kattan, José Tomás
    Introducción: Si bien la anastomosis intracorpórea (AI) ha demostrado beneficios clínicos sobre la anastomosis extracorpórea (AE) en la hemicolectomía derecha laparoscópica (HDL), su aplicación ha sido limitada por su dificultad técnica y curva de aprendizaje más larga. El presente estudio busca desarrollar y evaluar un modelo simulado para entrenar este procedimiento. Materiales y Método: Se desarrolló un modelo en base a tejido ex vivo, con colon porcino e intestino bovino, montados en un simulador de laparoscopía. Este se modificó sucesivamente en base a entrevistas semiestructuradas a cirujanos hasta lograr el modelo final. Para evaluar apariencia y reacción al modelo, coloproctólogos, cirujanos y residentes previamente expuestos a entrenamiento simulado, realizaron una ileotransverso anastomosis mecánica en el modelo y luego contestaron una encuesta. Resultados: Doce sujetos participaron. Cuatro coloproctólogos, 4 residentes de coloproctología, 2 residentes de cirugía general, 1 cirujano general y 1 cirujano digestivo. El 91,6% valoró positivamente la ergonomía lograda, mientras que el 83,3% y 75% valoraron positivamente el uso del instrumental y la relación anatómica entre estructuras, respectivamente. Todos los participantes consideraron el modelo útil para entrenar sutura manual laparoscópica, el 91,6% para entrenar enterotomías y 83,3% para entrenar el uso de endograpadora. Todos declararon que el módulo permite entender y reflexionar sobre la técnica propuesta. Conclusión: Este modelo desarrollado sería útil para entrenar habilidades críticas para realizar una AI en HDL. Su incorporación a un programa de entrenamiento en laparoscopía avanzada podría contribuir a acortar la curva de aprendizaje de este procedimiento.
  • Thumbnail Image
    Item
    HOW I DO IT: Breaking boundaries in surgical education by delivering expert feedback to residents anytime and anywhere. The LAPPCLINIC project
    (Elsevier Inc., 2025) Sanhueza Román, Diego Paolo; Jarry T., Cristián; Varas Cohen, Julián
    Objective: To describe LAPPCLINIC, an innovative web-based platform designed to enhance surgical educationthrough remote and asynchronous feedback by video-analysis of residents’ own surgical procedures. Design: We provide a detailed description of the platform workflow, highlighting key features for enhancing surgical education. Setting: An ongoing multicenter study involving seven surgical residency programs across Chile. Participants: First-year surgical residents from seven different Chilean programs, with feedback provided by five surgeons, experienced in surgical education, who are beyond their learning curves in laparoscopic cholecystectomy and trained in structured quality-feedback delivery. Conclusion: LAPPCLINIC implementation has shown strong resident acceptance and significantly higher evaluation of feedback quality compared to traditional OR-based teaching.