Denial of risk behavior does not exclude asymptomatic anorectal sexually transmitted infection in HIV-infected men

Abstract

Background: The Centers for Disease Control recommend screening for asymptomatic sexually transmitted infection (STI) among HIV-infected men when there is self-report of unprotected anal-receptive exposure. The study goals were: (1) to estimate the validity and usefulness for screening policies of self-reported unprotected anal-receptive exposure as a risk indicator for asymptomatic anorectal infection with Neisseria gonorrhoeae (GC) and/or Chlamydia trachomatis (CT). (2) to estimate the number of infections that would be missed if anal diagnostic assays were not performed among patients who denied unprotected anorectal exposure in the preceding month.

Methods and findings: Retrospective analysis in HIV primary care and high resolution anoscopy (HRA) clinics. HIV-infected adult men were screened for self-reported exposure during the previous month at all primary care and HRA appointments. Four sub-cohorts were defined based on microbiology methodology (GC culture and CT direct fluorescent antibody vs. GC/CT nucleic acid amplification test) and clinical setting (primary care vs. HRA). Screening question operating characteristics were estimated using contingency table methods and then pooled across subcohorts. Among 803 patients, the prevalence of anorectal GC/CT varied from 3.5-20.1% in the 4 sub-cohorts. The sensitivity of the screening question for self-reported exposure to predict anorectal STI was higher in the primary care than in the HRA clinic, 86-100% vs. 12-35%, respectively. The negative predictive value of the screening question to predict asymptomatic anorectal STI was > or = 90% in all sub-cohorts. In sensitivity analyses, the probability of being an unidentified case among those denying exposure increased from 0.4-8.1% in the primary care setting, and from 0.9-18.8% in the HRA setting as the prevalence varied from 1-20%.

Conclusion: As STI prevalence increases, denial of unprotected anal-receptive exposure leads to an increasingly unacceptable proportion of unidentified asymptomatic anorectal STI if used as a criterion not to obtain microbiologic assays.

Figure 1. Sensitivities and specificities of screening question to predict asymptomatic anorectal STI according to clinical setting (‘primary care clinic vs. high resolution anoscopy clinic’) and microbiology assay method (‘GC culture and CT direct fluorescent antibody vs. GC/CT nucleic acid amplification test’).

Figure 2. Sensitivity analysis of the probability of unidentified asymptomatic anorectal STI among those denying unprotected anal receptive exposure.

X-axis displays prevalence of asymptomatic STI (C. trachomatis and/or N. gonorrhoeae infection). Y-axis shows the probability defined as one minus negative predictive value of the screening question.

Figure 3. Model to estimate the number of unidentified cases based on a hypothetical cohort of 1000 patients, stratified by prevalence of asymptomatic STI (0.01, 0.05, 0.10, 0.20).

Model assumes that those disclosing unprotected anal receptive exposure would all be screened with a NAAT assay having 100% sensitivity and specificity.