Condom use rather than serosorting explains differences in HIV incidence among men who have sex with men

Background: HIV incidence is high and increasing among men who have sex with men (MSM) attending the Sexually Transmitted Infection (STI) Outpatient Clinic in Amsterdam but remains low among MSM in the Amsterdam Cohort Studies (ACS). We studied whether sexual behaviors in these 2 groups are consistent with serosorting and if serosorting explains the difference in HIV incidence. Methods: In 2004 to 2006, a survey of sexual behaviors and HIV status regarding up to 4 traceable partners in the prior 6 months was performed in MSM attending the STI Outpatient Clinic (high-risk) and in MSM in the ACS (lower risk). Moreover, pooled information was collected on anonymous partners. We used logistic regression to test whether sexual behaviors are consistent with serosorting and to test whether risk group is associated with having concordant traceable partners among men reporting unprotected anal intercourse (UAI). Results: We included 513 MSM (54% lower risk and 75% HIV-negative). Lower risk and high-risk MSM with concordant traceable partners were more likely to have UAI than MSM with discordant partners or partners of unknown HIV status (P < 0.001). Risk group was not associated with having concordant UAL Compared with lower risk MSM, however, high-risk MSM frequently had UAI with nonconcordant traceable partners and with anonymous partners. Conclusions: Sexual risk behaviors with traceable partners are consistent with serosorting. Nonetheless, the higher level of UAI with anonymous or nonconcordant traceable partners more likely explains the increasing HIV incidence seen among STI Outpatient Clinic attendees than a difference in serosorting behavior.