Salazar-Vizcaya L, Kusejko K, Schmidt AJ, et al. - Considering the possibility that the impact of behavioral interventions to prevent transmission of sexually transmitted infections could be improved via separately addressing specific groups of people who share patterns of behavioral change, researchers here suggested a method based on machine learning that may allow the identification of such groups among men who have sex with men. Based on the recognition of similarities and differences in longitudinal patterns of condomless anal intercourse with nonsteady partners (nsCAI) in the HIV Cohort Study over the last 18 years, they identified 4 “behavioral clusters” by means of unsupervised learning. Behavioral clusters exhibited highly dissimilar behavioral patterns, including drastic, atypical changes. The patterns imply that the overall rise in the frequency of nsCAI is largely attributable to 2 clusters, accounting for a third of the population.