Survival outcomes and prognosis in non-small cell lung cancer patients in a tertiary hospital in Spain

• Autor(a) principal: Sousa, Alexandre Miguel Ramos de
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/145231
• topic: Non-small cell lung cancer; survival analysis; Kaplan-Meier estimator; logrank test; Cox proportional-hazard model; Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

Cancer is one of the main causes of mortality in the world and the number of new diagnosed cases are increasing every year. This number is expected to almost double in the next 20 years which causes health organizations to start taking steps to try to stop this increase in cases and to give the best possible care and treatment to cancer patients. With the evolution of technology and its solidification and proven evidence in the health world, it is essential to create projects in order to guarantee the best care and monitoring for patients, to try to prevent the evolution of the disease and understand the type of care that patients need. With this, it is expected that cancer survivors will be able to have a better quality of life and an improvement in the survival rates. The dataset used in this study is from patients diagnosed with lung cancer, one of the most common cancers and with a high mortality rate, specifically non-small cell lung cancer. The aim of the study is to identify risk factors that can affect patient survival. This dissertation discusses how information systems work in the area of health, how data are received, processed and stored. It is also explained how a pre-processing of the data was done in order to adapt the data to the models, a descriptive analysis to better understand our dataset and, lastly, a statistical survival analysis was performed using the Kaplan-Meier estimator, the logrank test and finally, the Cox multivariate proportional-hazard model. This dissertation was carried out within the scope of the European project CLARIFY [1], with the collaboration of the oncology department of the University Hospital Puerta Hierro de Majadahonda.