Machine learning in a DEXA database of HIV patients

The work is based on a DEXA database with information on three diseases, Sarcopenia, Lipodystrophy and Osteoporosis. The information in the database is about patients with AIDS, a disease that today still has a high incidence in the population. The treatments have greatly improved the life expectanc...

Descripción completa

Detalles Bibliográficos
Autor: Piqué Villorbina, Jordi
Tipo de recurso: tesis de maestría
Fecha de publicación:2021
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/139066
Acceso en línea:http://hdl.handle.net/10609/139066
Access Level:acceso abierto
Palabra clave:DEXA
HIV
machine learning
aprenentatge automàtic
aprendizaje automático
Bioinformatics -- TFM
Bioinformàtica -- TFM
Bioinformática -- TFM
Descripción
Sumario:The work is based on a DEXA database with information on three diseases, Sarcopenia, Lipodystrophy and Osteoporosis. The information in the database is about patients with AIDS, a disease that today still has a high incidence in the population. The treatments have greatly improved the life expectancy of patients but have also increased the risk of having some of the three pathologies mentioned. The variables in the database are related to these three diseases. What will be done is a descriptive analysis of the database and a prediction of the diseases, but doing the prediction of one disease through the variables of the other two diseases. The prediction will be made with the best known Machine Learning(ML) algorithms and will be done categorically and numerically. It will also be considered whether the variable total bone mineral density is used to predict the level of osteoporosis. A dynamic report will be created with Rmarkdown that can be used to make predictions with other databases.