Application of logistic regression models to cancer patients: A case study of data from Jigme Dorji Wangchuck National Referral Hospital (JDWNRH) in Bhutan

Abstract

© Published under licence by IOP Publishing Ltd. Cancer is an uncontrolled disease caused by a damage to the cell's DNA. Cancer rates are increasing every year and is the biggest concern in many countries including Bhutan. Bhutan being a very small country loses around 100 to 200 patients every year due to cancer. This study involved 3013 cancer patients who are treated at Jigme Dorji Wangchuck National Referral Hospital (JDWNRH) from 2010 to 2016. Those patients who cannot be treated in the country are referred out to other countries for treatment. This study is to identify the factors that affect the survival of all cancer patients as well as male and female patients separately. This has been done using logistic regression model where the dependent variable is the patient's last status. The best fitted model was obtained from the analysis of deviance. The test showed that the last status of the patient and the variables of personal and clinical data are mostly significant at p-value less than 0.05. The factors affecting the last status of cancer are age, length of stay and the cancer site. Cancer site is one of the main factors that affect the survival of both male and female patients.