Predictors and mortality associated with treatment default in pulmonary tuberculosis

Abstract

Objective: To identify risk factors for default from pulmonary tuberculosis (TB) treatment and to assess mortality associated with default in Estonia.

Design: All patients with culture-confirmed pulmonary TB who started treatment during 2003-2005 were included in a retrospective cohort study.

Results: In 1107 eligible patients, the treatment success rate was 81.5% and the default rate 9.4% (respectively 60.4% and 17.0% in multidrug-resistant TB [MDR-TB]). Independent predictors of treatment default were alcohol abuse (OR 3.22, 95%CI 1.93-5.38), unemployment (OR 3.05, 95%CI 1.84-5.03), MDR-TB (OR 2.17, 95%CI 1.35-3.50), urban residence (OR 1.85, 95%CI 1.00-3.42) and previous incarceration (OR 1.78, 95%CI 1.05-3.03). Of the defaulters, 29.4% died during follow-up (median survival 342.0 days). Cox regression analysis revealed that unemployment was associated with all-cause and TB-related mortality among defaulters (respectively HR 4.58, 95%CI 1.05-20.1 and HR 11.2, 95%CI 1.58-80.2). HIV infection (HR 51.2, 95%CI 6.06-432), sputum smear positivity (HR 9.59, 95%CI 1.79-51.4), MDR-TB (HR 8.56, 95%CI 1.81-40.4) and previous TB (HR 5.15, 95%CI 1.64-16.2) were predictors of TB-related mortality.

Conclusion: The main risk factors for treatment default can be influenced. Interventions to reduce default should therefore concentrate on socially disadvantaged patients and prevention of alcohol abuse, with special attention given to MDR-TB patients.