Do Web-Based and Clinic Samples of Gay Men Living With HIV Differ on Self-Reported Physical and Psychological Symptoms? A Comparative Analysis

Background: Although the Internet is commonly used to recruit samples in studies of human immunodeficiency virus (HIV)-related risk behaviors, it has not been used to measure patient-reported well-being. As the burden of long-term chronic HIV infection rises, the Internet may offer enormous potential for recruitment to research and interventions. Objective: This study aimed to compare two samples of gay men living with HIV, one recruited via the Web and the other recruited in outpatient settings, in terms of self-reported physical and psychological symptom burden. Methods: The Internet sample was recruited from a UK-wide Web-based survey of gay men with diagnosed HIV. Of these, 154 respondents identified themselves as resident in London and were included in this analysis. The HIV clinic sample was recruited from five HIV outpatient clinics. Of these participants, 400 gay men recruited in London clinics were included in this analysis. Results: The Web-based sample was younger than the clinic sample (37.3 years, SD 7.0 vs 40.9 years, SD 8.3), more likely to be in paid employment (72.8%, 99/136 vs 60.1%, 227/378), less likely to be on antiretroviral therapy (ART) (58.4%, 90/154 vs 68.0%, 266/391), and had worse mean psychological symptom burden compared to the clinic sample (mean scores: 1.61, SD 1.09 vs 1.36, SD 0.96) but similar physical symptom burden (mean scores: 0.78, SD 0.65 vs 0.70, SD 0.74). In multivariable logistic regression, for the physical symptom burden model, adjusted for age, ethnicity, employment status, and ART use, the recruitment setting (ie, Web-based vs clinic) was not significantly associated with high physical symptom score. The only variable that remained significantly associated with high physical symptom score was employment status, with those in employment being less likely to report being in the upper (worst) physical symptom tertile versus the other two tertiles (adjusted OR 0.41, 95% CI 0.28-0.62, P<.001). For the psychological symptom burden model, those recruited via the Web were significantly more likely to report being in the upper (worst) tertile (adjusted OR 2.20, 95% CI 1.41-3.44, P=.001). In addition, those in employment were less likely to report being in the upper (worst) psychological symptom tertile compared to those not in employment (adjusted OR 0.32, 95% CI 0.21-0.49, P<.001). Conclusions: Our data have revealed a number of differences. Compared to the clinic sample, the Web-based sample had worse psychological symptom burden, younger average age, higher prevalence of employment, and a lower proportion on ART. For future research, we recommend that Web-based data collection should include the demographic variables that we note differed between samples. In addition, we recognize that each recruitment method may bring inherent sampling bias, with clinic populations differing by geographical location and reflecting those accessing regular medical care, and Web-based sampling recruiting those with greater Internet access and identifying survey materials through specific searches and contact with specific websites.