The first cases of Pneumocystis carinii (jirovecii) pneumonia among young men, which were subsequently linked to HIV infection, were reported in the MMWR on June 5, 1981 (1). At year-end 2019, an estimated 1.2 million persons in the United States were living with HIV infection (2). Using data reported to the National HIV Surveillance System, CDC estimated the annual number of new HIV infections (incidence) among persons aged ≥13 years in the United States during 1981-2019. Estimated annual HIV incidence increased from 20,000 infections in 1981 to a peak of 130,400 infections in 1984 and 1985. Incidence was relatively stable during 1991-2007, with approximately 50,000-58,000 infections annually, and then decreased in recent years to 34,800 infections in 2019. The majority of infections continue to be attributable to male-to-male sexual contact (63% in 1981 and 66% in 2019). Over time, the proportion of HIV infections has increased among Black/African American (Black) persons (from 29% in 1981 to 41% in 2019) and among Hispanic/Latino persons (from 16% in 1981 to 29% in 2019). Despite the lack of a cure or a vaccine, today's HIV prevention tools, including HIV testing, prompt and sustained treatment, preexposure prophylaxis, and comprehensive syringe service programs, provide an opportunity to substantially decrease new HIV infections. Intensifying efforts to implement these strategies equitably could accelerate declines in HIV transmission, morbidity, and mortality and reduce disparities.

Human mobility is a primary driver of infectious disease spread. However, existing data is limited in availability, coverage, granularity, and timeliness. Data-driven forecasts of disease dynamics are crucial for decision-making by health officials and private citizens alike. In this work, we focus on a machine-learned anonymized mobility map (hereon referred to as AMM) aggregated over hundreds of millions of smartphones and evaluate its utility in forecasting epidemics. We factor AMM into a metapopulation model to retrospectively forecast influenza in the USA and Australia. We show that the AMM model performs on-par with those based on commuter surveys, which are sparsely available and expensive. We also compare it with gravity and radiation based models of mobility, and find that the radiation model's performance is quite similar to AMM and commuter flows. Additionally, we demonstrate our model's ability to predict disease spread even across state boundaries. Our work contributes towards developing timely infectious disease forecasting at a global scale using human mobility datasets expanding their applications in the area of infectious disease epidemiology.