Deep Learning for Forecast Scales to Prescribe Patients at Risk of Gastrointestinal Bleeding

The evolution of medicine in current times has gone hand in hand with technology where more and more solutions are implemented; those supporting certain medical procedures to serve as base in the field of medical  professionals. The process of analyzing data has become an essential resource in the practice of any profession; currently, in hospitals, more specifically in the university hospital La Samaritana. No tool allows the supporting of diagnosis to determine the supply or no, proton pump inhibitors, therefore we have developed an app using a machine learning model, based on decision trees through the weka application, which, after analyzing the data collected, allows the doctor to count with a tool to support this procedure. We hope that with this, doctors can perform an effective analysis before prescribing or not prescribing PPIs.

• Autores: Calderón-Vargas, Carlos; Muñoz Castaño, José; Vargas Rincón, María; Rincón Acosta, Víctor Manuel; Mendieta Hernández, Miguel
• Fecha de publicación: 2021
• Institución: Universidad EAFIT
• Repositorio: Repositorio EAFIT
• Idioma: spa
• OAI Identifier: oai:repository.eafit.edu.co:10784/31017
• Acceso en línea: http://hdl.handle.net/10784/31017
• Palabra clave: Web design; Machine learning; training; decision trees; weka; Diseño web; Machine learning; entrenamiento; árboles de decisión; weka
• License: Acceso abierto