Participation, characteristics and retention rates of HIV-positive immigrants in the Swiss HIV Cohort Study

Abstract

Objective: Data from observational cohorts may be influenced by population structure and loss to follow-up (LTFU). Quality of care may be associated with participation in cohort networks. We aimed to study the participation, characteristics and retention rates of immigrants in the Swiss HIV Cohort Study (SHCS).

Methods: We compared enrolment over time (1996-1999, 2000-2003 and 2004-2008) and LTFU between individuals from different geographical regions. In 2008, we performed a cross-sectional survey to investigate the proportion of individuals not participating in the SHCS but who were in care at SHCS institutions. Predictors for LTFU were analysed using Cox proportional hazard models, and those for nonparticipation using logistic regression.

Results: A total of 7840 individuals entered the SHCS during the observation period. The proportion of immigrants increased over time, especially the proportion of women from sub-Saharan Africa, which increased from 21 to 48% during the observation period. Overall LTFU was 3.76 [95% confidence interval (CI) 3.58-3.95]/100, with the highest hazard ratio in men from sub-Saharan Africa (2.82/100 patient-years; 95% CI 2.30-3.46/100), compared with men from northwestern countries. Other predictors for LTFU were age <30 years, lower education, injecting drug use, and higher baseline CD4 cell counts. Participants taking antiretroviral therapy had reduced LTFU. The survey showed that 84% of HIV-infected patients in care at SHCS institutions were enrolled in the cohort. Nonparticipation was more likely among men from non-European regions (odds ratio 2.73; 95% CI 2.29-3.24), women from sub-Saharan Africa (odds ratio 3.01; 95% CI 2.40-3.77) and women from Latin America/Caribbean (odds ratio 2.10; 95% CI 1.30-3.39).

Conclusions: Numbers of HIV-infected immigrants are increasing but they are underrepresented in the SHCS, and immigrants are more likely to be lost to follow-up.