Detecting Important Risk Factors of Survival Time of Lung Cancer Patients Using Censored Quintile Regression

Amini, Payam; Abazari, Malek; Alafchi, Behnaz

doi:10.31557/APJCP.2019.20.9.2583

Detecting Important Risk Factors of Survival Time of Lung Cancer Patients Using Censored Quintile Regression

Document Type : Research Articles

Authors

¹ Department of Epidemiology and Reproductive Health, Reproductive Epidemiology Research Center, Royan Institute for Reproductive Biomedicine, ACECR, Tehran, Iran.

² Department of Public Health, School of Public Health, Ardabil University of Medical Sciences, Ardabil, Iran.

³ Department of Biostatistics, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran.

10.31557/APJCP.2019.20.9.2583

Abstract

Objective: Lung cancer is the most frequently diagnosed cancer and the most leading cause of death due to cancer
worldwide. This study aimed to use censored quintile regression model to estimate the effect of potential risk factors
on survival of lung cancer patients. Methods: In this study we used a dataset of a retrospective cohort study conducted
in West Azerbaijan (during 2007 and 2014). Demographic variables included age, and gender and biological variables
included Eastern Cooperative Oncology Group, smoking, tumor type, stage, metastasis, and treatment were investigated
as risk factors of survival of lung cancer patients by using censored quintile regression. Result: The mean (± standard
deviation) age of the 347 lung cancer patients was 63.48 (± 13.55) years. The survival time ranges from 11 to 91. A
total of 240 (67.6%) experienced death by the end of the study. The impact of Eastern Cooperative Oncology Group
(IV), smoking and treatment were significant for most of quintiles (p<0.05). Stage of cancer and metastasis are the other
affective risk factors on the survival of lung cancer patients(p<0.05). It was shown that Eastern Cooperative Oncology,
smoking habit and treatment were significantly associated with a shorter time-to-death progression. Conclusion: As
censored quintile regression could consider time-varying effects and the interpretation of its regression coefficients are
easy it could be an adequate choice for analyzing survival data.

Keywords

Main Subjects