Factors associated with dropout in a long term observational cohort of fishing communities around lake Victoria, Uganda

Abstract

Background: Fishing communities are potentially suitable for Human immunodeficiency virus (HIV) efficacy trials due to their high risk profile. However, high mobility and attrition could decrease statistical power to detect the impact of a given intervention. We report dropout and associated factors in a fisher-folk observational cohort in Uganda.

Methods: Human immunodeficiency virus-uninfected high-risk volunteers aged 13-49 years living in five fishing communities around Lake Victoria were enrolled and followed every 6 months for 18 months at clinics located within each community. Volunteers from two of the five communities had their follow-up periods extended to 30 months and were invited to attend clinics 10-40 km (km) away from their communities. Human immunodeficiency virus counseling and testing was provided, and data on sexual behaviour collected at all study visits. Study completion was defined as completion of 18 or 30 months or visits up to the date of sero-conversion and dropout as missing one or more visits. Discrete time survival models were fitted to find factors independently associated with dropout.

Results: A total of 1000 volunteers (55% men) were enrolled. Of these, 91.9% completed 6 months, 85.2% completed 12 months and 76.0% completed 18 months of follow-up. In the two communities with additional follow-up, 76.9% completed 30 months. In total 299 (29.9%) volunteers missed at least one visit (dropped out). Dropout was independently associated with age (volunteers aged 13-24 being most likely to dropout), gender [men being more likely to dropout than women [adjusted hazard ratio (aHR) 1.4; 95% confidence interval (CI) 1.1-1.8)], time spent in the fishing community (those who stayed <1 year being most likely to dropout), History of marijuana use (users being more likely to dropout than non-users [1.7; (1.2-2.5)], ethnicity (non-Baganda being more likely to dropout than Baganda [1.5; (1.2-1.9)], dropout varied between the five fishing communities, having a new sexual partner in the previous 3 months [1.3 (1.0-1.7)] and being away from home for ≥2 nights in the month preceding the interview [1.4 (1.1-1.8)].

Conclusion: Despite a substantial proportion dropping out, retention was sufficient to suggest that by incorporating retention strategies it will be possible to conduct HIV prevention efficacy trials in this community.

Fig. 1

Study profile