Comparison of Cox Proportional Hazard Models with Interaction and Without Interaction in Heart Failure Patients

Authors

  • Bunga Nafandra Universitas Negeri Padang
  • Tessy Octavia Mukhti universitas Negeri Padang
  • Yoli Marda Novi Universitas Negeri Padang
  • Nurul Mulya Syahwa Universitas Negeri Padang
  • Olga Afrilly Putri Universitas Negeri Padang

DOI:

https://doi.org/10.24036/ujsds/vol3-iss2/342

Keywords:

survival analysis, Cox Proportional Hazard, heart failure, variable interaction, survival time

Abstract

 Heart failure is one of the disorders that attack the heart and is a major cause of morbidity and mortality. There is a 5% prevalence of heart failure in Indonesia in 2020. By utilizing survival analysis, this study aims to compare the Cox proportional hazard model with interaction and without interaction, and identify factors that significantly affect the survival time of heart failure patients. The research data is secondary data consisting of 299 heart failure patient data with several variables including high blood pressure, anemia status, and age. Through the stages of analysis that have been carried out, it is found that the variables of high blood pressure and age have a significant effect on the survival time of heart failure patients, while the anemia variable and the interaction between independent variables do not have a significant relationship with survival time. In addition, based on the AIC value, it is also found that the model without interaction is better than the model with interaction, which is characterized by a smaller AIC value in the model without interaction. Based on the best model, patients with high blood pressure have a 1.52 times higher chance of dying than patients without high blood pressure. In addition, the probability of death increased by 4.33% for every one-year increase in patient age. This study concludes that the model without interaction is more suitable for describing the relationship between independent variables and survival time in heart failure patients.

Published

2025-05-31

How to Cite

Bunga Nafandra, Tessy Octavia Mukhti, Yoli Marda Novi, Nurul Mulya Syahwa, & Olga Afrilly Putri. (2025). Comparison of Cox Proportional Hazard Models with Interaction and Without Interaction in Heart Failure Patients. UNP Journal of Statistics and Data Science, 3(2), 130–139. https://doi.org/10.24036/ujsds/vol3-iss2/342

Most read articles by the same author(s)

1 2 3 > >>