Dramatic improvement in survival among adult Brazilian AIDS patients

Background: Since the last study of survival time among Brazilian AIDS patients, care has improved steadily, culminating in a controversial policy of universal free access to triple antiretroviral treatment since 1996. This large, national study examined how these changes have impacted survival. Methods: Using national data for cases diagnosed in 1995 and 1996, we randomly selected 3930 adult AIDS cases from 18 cities in seven states representing all regions of Brazil. Trained abstracters reviewed medical records, determining dates of diagnosis and death or last contact, exposure category, treatment, and demographics. After review, 2821 cases met the inclusion criteria and were available for Kaplan-Meier and proportional hazards analysis. Data from the earlier study were re-analyzed for comparison. Results: Median survival was 5 months for cases diagnosed in the 1980s, 18 months for those diagnosed in 1995, and 58 months for those diagnosed in 1996. Predictors of longer survival in univariate analysis included antiretroviral treatment, year of diagnosis, higher education, sexual exposure category, female sex, and Pneumocystis carinii pneumonia prophylaxis. In multivariate analysis, the predictive value of most of these was attenuated or disappeared, leaving antiretroviral treatment as the main predictor of survival. Conclusions: Survival time has increased substantially for adult Brazilian AIDS patients. The timing of these gains and analysis of the predictors of survival both indicate antiretroviral treatment as the cause. These findings demonstrate that universal access to antiretroviral treatment in a developing country can produce benefits on the same scale as in richer countries. (C) 2003 Lippincott Williams Wilkins.