1. Comparison of cox regression and parametric methods for elderly respiratory patients in Malaysia.
- Author
-
Zulkifli, Siti Wafiah Hanin Mohd, Samsudin, Humaida Banu, and Majid, Noriza
- Subjects
OLDER patients ,PROPORTIONAL hazards models ,LENGTH of stay in hospitals ,HOSPITAL admission & discharge ,RESPIRATORY diseases ,LUNG diseases - Abstract
Respiratory diseases or lung diseases are becoming one of the leading causes of death in Malaysia and survivability among the elderly when they are hospitalized to these diseases are doubtful. The study aims to compare the efficiency of survival models which are semi-parametric and parametric models in the analysis of length of hospital stay for respiratory diseases in elderly (65 years old and above) patients until recovery and demographics factors associated with length of stay in the hospital. The study was carried out using data for hospital admission and discharge from all goverments hospitals in Malaysia. Cases among the elderly classified under respiratory diseases J00 to J99 from the year 2012 to 2020. Patients' data such as age, gender, ethnicity, marital status and class of respiratory diseases were also selected as potential prognostic factors for semiparametric and parametric models. The survival results for all models showed that patients with the increase in age, Chinese ethnicity, unmarried and admitted with other diseases of respiratory will have a shorter period of stay hence will increase the risk of do not recover during the period of stay in the hospital. It is found that lognormal model is a better fit model than the other semi-parametric by having the lowest AIC and BIC for the respiratory diseases in elderly patient's data. Parametric models may be used to be more accurate and precise results as an alternative to Cox Proportional Hazard Model. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF