Clusters of sexual behaviour in HIV-positive men who have sex with men reveal highly dissimilar time trends

BACKGROUND Separately addressing specific groups of people who share patterns of behavioural change might increase the impact of behavioural interventions to prevent transmission of sexually transmitted infections. We propose a method based on machine learning to assist the identification of such groups among men who have sex with men (MSM). METHODS By means of unsupervised learning, we inferred "behavioural clusters" based on the recognition of similarities and differences in longitudinal patterns of condomless anal intercourse with non-steady partners (nsCAI) in the Swiss HIV cohort study over the last 18 years. We then used supervised learning to investigate whether sociodemographic variables could predict cluster membership. RESULTS We identified four behavioural clusters. The largest behavioural cluster (Cluster 1) contained 53% of the study population and displayed the most stable behaviour. Cluster 3 (17% of the study population) displayed consistently increasing nsCAI. Sociodemographic variables were predictive for both of these clusters. The other two clusters displayed more drastic changes: nsCAI frequency in Cluster 2 (20% of the study population) was initially similar to that in Cluster 3, but accelerated in 2010. Cluster 4 (10% of the study population) had significantly lower estimates of nsCAI than all other clusters until 2017, when it increased drastically, reaching 85% by the end of the study period. CONCLUSIONS We identified highly dissimilar behavioural patterns across behavioural clusters, including drastic, atypical changes. These patterns suggest that the overall increase in the frequency of nsCAI is largely attributable to two clusters, accounting for a third of the population.