Publicación: Application of Machine Learning Algorithms to build a risk score for Pancreatic Cancer using high-throughput epidemiological risk factors
Cargando...
Fecha
2020-03-01
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial.
Resumen
Cancer is one of the most challenging diseases that medical field is facing nowadays. Its incidence numbers are continuously increasing, and they are expected to keep on doing it for the next decades. Pancreatic Cancer is one of the most enigmatic among all the known cancer types. Even though the incidence numbers for PC are not so high as the ones for other diseases, its death ratio is astonishing. Life expectancy for people diagnosed with pancreatic cancer is less than six months. These numbers set up a difficult research environment where the characteristics of a risk population have not been, yet property identified, and where there is a lack of epidemiological information that makes further investigation in early detection very problematic. For the last decades, Artificial Intelligence has been demonstrating its benefits when applied to medical researches, since it can outperform human ability to identify trends and patterns inside huge datasets. In this work, I propose a novel and robust approach to identify the characteristic of a risk population in pancreatic cancer data that has been provided by surveys and researches performed in the whole Europe. This kind of data presents noise, bias and missing values that usually straiten the capabilities of the AI methods. The proposed system uses an ensemble of techniques that brings the ability to first recover the dataset and to later identify the most informative features that can be used to determine the characteristics of a risk population, to build a risk score for the epidemiological factors of Pancreatic Cancer.
Descripción
Categorías UNESCO
Palabras clave
machine learning, pancreatic cancer, PanGen, risk score, risk population, imputation, features selection, epidemiology
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial