Modelo piloto de aprendizaje automático para la predicción de mortalidad por Leucemia Mieloide Aguda
Autor:
Hernández-Martínez, Ricardo
Fecha:
22/09/2021Palabra clave:
Tipo de Ítem:
masterThesisResumen:
La Leucemia Mieloide Aguda (LMA) es un tipo de cáncer de sangre que se encuentra entre los primeros con mayor cantidad de casos nuevos reportados en Colombia. El uso de aplicaciones basadas en Inteligencia Artificial ha aumentado en los últimos años, utilizadas como herramientas de apoyo al diagnóstico, pronóstico y tratamiento de enfermedades. En este trabajo se aplicaron algoritmos de aprendizaje supervisado para la creación de un modelo piloto predictivo de mortalidad de pacientes que padecen de LMA, siguiendo la metodología tradicional de proyectos de analítica de datos. Se utilizó para su desarrollo información recopilada en tratamientos bajo el protocolo terapéutico del Programa Español de Tratamientos en Hematología (PETHEMA). El modelo desarrollado alcanzó 0.88 de exactitud, con un AUC de 0.92. Los resultados obtenidos son un indicio favorable de la posibilidad de aplicar la Inteligencia Artificial en el campo de la medicina para el apoyo de la práctica clínica tradicional.
Descripción:
Acute Myeloid Leukemia (AML) is a type of blood cancer among the ones with the highest number of new cases reported in Colombia. Due to this, in recent years the use of applications based on Artificial Intelligence to support the diagnosis, prognosis and treatment of this disease has increased. In this work, the application of supervised learning algorithms is tested for the creation of a predictive pilot model of mortality in patients suffering from AML, following the traditional methodology of data analytics projects. For its development, information collected in treatments under the therapeutic protocol of the Spanish Program for Hematology Treatments (PETHEMA) was used. The developed model reached 0.88 accuracy, with an AUC of 0.92. The results obtained are a favorable indication of the possibility of applying Artificial Intelligence in the field of medicine to support traditional clinical practice.
Ficheros en el ítem
Este ítem aparece en la(s) siguiente(s) colección(es)
Estadísticas de uso
Año |
2012 |
2013 |
2014 |
2015 |
2016 |
2017 |
2018 |
2019 |
2020 |
2021 |
2022 |
2023 |
2024 |
Vistas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
41 |
193 |
280 |
148 |
Descargas |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
0 |
14 |
123 |
163 |
89 |
Ítems relacionados
Mostrando ítems relacionados por Título, autor o materia.
-
Productivity Measurement in Software Engineering: A Study of the Inputs and the Outputs
Hernández-López, Adrián; Colomo-Palacios, Ricardo; Soto-Acosta, Pedro; Casado-Lumbreras, Cristina (International Journal of Information Technologies and Systems Approach, 01/2015)Productivity measurement is constructed by the measure of tree categories of elements: inputs, outputs and factors. This concept, which started being used in the manufacturing industry, has been also a research topic within ... -
Improvement of Memory and Motivation in Language Learning in Primary Education through the Interactive Digital Whiteboard (IDW): The Future in a Post-Pandemic Period
Bautista Vallejo, José Manuel; Hernández-Carrera, Rafael M. ; Moreno-Rodríguez, Ricardo; López-Bastias, José Luis (Sustainability, 10/2020)This paper presents an analysis of the use of an interactive digital whiteboard (IDW) and a computer application called Action Manager (AM), with a sample of 158 sixth-grade students in primary education. Subsequently, a ... -
Secure Information Transmission Device Implemented on an Embedded System using 3DES and AES Algorithms
Martínez Santa, Ricardo ; Martínez Santa, Fernando; Montiel Ariza, Holman (International Journal of Engineering Research and Technology, 2019)The main objective of this article is to implement a hardware-software prototype for sending and receiving secure information between a PC and an embedded system, using cryptographic algorithms 3DES (Triple DES) and 3 ...