Ph.D. Student: Jose Antonio Delgado
Advisors: Carlos García, Sebastián Ventura
Started on: April 2016
Keywords: colorectal cancer, data learning, classification, association rules
There are some works applying data mining models to patients suffering from colorectal cancer that try to predict the survival of those patients. However, in the context of a public and universal healthcare system it is necessary, and this is our main objective, to deploy machine learning models that focus not only on predicting patients with a good prognosis but also on predicting the factors that could produce some complications in those patients that may cause re-admisions and recidives of the tumour. We think that detecting complications as soon as possible is a key point that will benefit the patients because they get an early diagnosis that could increase their survival probability.
The partial objectives are the following:
- Applying the classic data mining models to the colorectal cancer database in order to study their behavior in this problem.
- Deploying our own knowledge discovery model for patients suffering from colorectal cancer in Andalucia.
- Comparing our model with the existing ones in order to check its performance.
The development of this thesis is being supported by:
- Spanish Ministry of Science and Competitiveness, project TIN-2017-83445-P.
PUBLICATIONS ASSOCIATED WITH THIS THESIS
- J.A. Delgado-Osuna, C. García-Martínez, S. Ventura, and J. Gómez Barbadillo. Obtaining tractable and interpretable descriptions for cases with complications from a colorectal cancer database. In proceedings of 32nd IEEE International Symposium on Computer-Based Medical Systems., pp. 459-464. 2019.