Long-term survival and cause-specific mortality of patients newly diagnosed with tuberculosis in São Paulo state, Brazil, 2010-15: a population-based, longitudinal study

Abstract

Background: Long-term survival and cause-specific mortality of patients who start tuberculosis treatment is rarely described. We aimed to assess the long-term survival of these patients and evaluate the association between vulnerable conditions (social, health behaviours, and comorbidities) and cause-specific mortality in a country with a high burden of tuberculosis.

Methods: In this population-based, longitudinal study in São Paulo state, Brazil, we described the 5-year survival of patients who were newly diagnosed with tuberculosis in 2010. We included patients with newly-diagnosed tuberculosis, aged 15 years or older, and notified to the São Paulo State Tuberculosis Program in 2010. We excluded patients whose diagnosis had changed during follow-up (ie, they did not have tuberculosis) and patients who had multidrug-resistant (MDR) tuberculosis. We selected our population with tuberculosis from the dedicated electronic system TBweb. Our primary objective was to estimate the excess mortality over 5 years and within the group who survived the first year, compared with the general São Paulo state population. We also estimated the association between social vulnerability (imprisonment and homelessness), health behaviours (alcohol and drug use), and comorbidities (diabetes and mental disorders) with all-cause and cause-specific mortality. We used the competing risk analysis framework, estimating cause-specific hazard ratios (HRs) adjusted for potential confounding factors.

Findings: In 2010, there were 19 252 notifications of tuberculosis cases. We excluded 550 cases as patients were younger than 15 years, 556 cases that were not tuberculosis, 2597 retreatments, and 48 cases of MDR tuberculosis, resulting in a final cohort of 15 501 patients with tuberculosis. Over a period of 5 years from tuberculosis diagnosis, 2660 (17%) of 15 501 patients died. Compared with the source population, matched by age, sex, and calendar year, the standardised mortality ratio was 6·47 (95% CI 6·22-6·73) over 5 years and 3·93 (3·71-4·17) among those who survived the first year. 1197 (45%) of 2660 deaths were due to infection. Homelessness and alcohol and drug use were associated with death from infection (adjusted cause-specific HR 1·60, 95% CI 1·39-1·85), cardiovascular (1·43, 1·06-1·95), and external or ill-defined causes of death (1·80, 1·37-2·36). Diabetes was associated with deaths from cardiovascular causes (1·70, 1·23-2·35).

Interpretation: Patients newly diagnosed with tuberculosis were at a higher risk of death than were the source population, even after tuberculosis treatment. Post-tuberculosis sequelae and vulnerability are associated with excess mortality and must be addressed to mitigate the tuberculosis burden worldwide.

Funding: Wellcome Trust.

Figure

Fully adjusted cause-specific HRs for 5-year cause-specific mortality in patients newly diagnosed with tuberculosis Boxes show adjusted cause-specific HRs and error bars show 95% CIs. Arrowheads represents the direction of the CI value, truncated at the horizontal axis limit. HR=hazard ratio.