Crimson Publishers Publish With Us Reprints e-Books Video articles


Open Access Biostatistics & Bioinformatics

Modelling Length of Hospital Stay for Tuberculosis Treated in-Patients at Queen Elizabeth Central Hospital: a Competing Risk Perspective

  • Open or Close Halima S Twabi1* and Mavuto Mukaka2,3

    1Mathematical Sciences Department, University of Malawi, Malawi

    2Mahidol-Oxford Tropical Medicine Research Unit, Mahidol University, Thailand

    3Nuffield Department of Medicine Research Building, University of Oxford, UK

    *Corresponding author: Halima Twabi, University of Malawi, Chancellor College, PO. Box 280, Zomba, Malawi, Tel: +265999467366; Email:

Submission: January 29, 2018; Published: February 22, 2018

DOI: 10.31031/OABB.2018.01.000507

ISSN: 2578-0247
Volume1 Issue2


A retrospective cohort study was done on adult Tuberculosis (TB) in-patients from Queen Elizabeth Central Hospital (QECH) Surveillance Programme of In-patients and Epidemiology (SPINE) database to identify factors explaining time to discharge from hospital while accounting for a competing event: death. The study aimed to apply and compare competing risk models on TB data. Semi-parametric Cause-specific hazards (CSH) and Sub-distribution hazard (SDH) models were applied to model the effect of HIV status, age, and Sex in relation to death or discharge from hospital. Test for model assumptions and diagnostics were conducted. Findings showed that the SDH explained best the effect of the covariates to the probability of a patient being discharged or dying. Further the main factors affecting length of hospital stay among TB in-patients were age and HIV Status. HIV positive patients were 17.6% less likely to be discharged from hospital compared to HIV negative patients (p=0.048) and an increase in age, resulted in 2% decrease of chances of discharge. The study showed the importance of using cumulative incidence function for calculating probability of being discharged in the presence of a competing event death. To meet the objective of identifying prognostic factors of discharge in the presence of a competing event, the sub-distribution hazard model explained better the covariate effects on event discharge than the CSH model. The findings emphasize the importance to use competing risk methods which best meet the study objectives.

Keywords: Tuberculosis; Competing risk; Cumulative Incidence Function (CIF); Cause-specific hazards (CSH); Sub-distribution hazards (SDH); Length of hospital stay (LoS)

Abbreviations: CSH: Cause-Specific Hazards; SDH: Sub-Distribution Hazards; CI: Cumulative Incidence

Get access to the full text of this article