Search

Background Advancements in machine learning (ML) have improved the accuracy of models that predict human immunodeficiency virus (HIV) incidence. These models have used electronic medical records and registries. We aim to broaden the application of these tools by using deidentified public health datasets for notifiable sexually transmitted infections (STIs) from a southern US county known for high HIV incidence. The goal is to assess the feasibility and accuracy of ML in predicting HIV incidence, which could inform and enhance public health interventions. Methods We analyzed 2 deidentified public health datasets from January 2010 to December 2021, focusing on notifiable STIs. Our process involved data processing and feature extraction, including sociodemographic factors, STI cases, and social vulnerability index (SVI) metrics. Various ML models were trained and evaluated for predicting HIV incidence using metrics such as accuracy, precision, recall, and F1 score. Results We included 85 224 individuals; 2027 (2.37%) were newly diagnosed with HIV during the study period. The ML models demonstrated high performance in predicting HIV incidence among males and females. Influential features for males included age at STI diagnosis, previous STI information, provider type, and SVI. For females, predictive features included age, ethnicity, previous STI information, overall SVI, and race. Conclusions The high accuracy of our ML models in predicting HIV incidence highlights the potential of using public health datasets for public health interventions such as tailored HIV testing and prevention. While these findings are promising, further research is needed to translate these models into practical public health applications. [ABSTRACT FROM AUTHOR]

Despite universal prenatal syphilis screening recommendations and availability of effective antibiotic treatment, syphilis prevalence during pregnancy and the incidence of congenital syphilis have continued to increase in the United States (1,2). Concurrent increases in methamphetamine, injection drug, and heroin use have been described in women with syphilis (3). CDC used data on births that occurred during January 1, 2018-December 31, 2021, from two states (Arizona and Georgia) that participate in the Surveillance for Emerging Threats to Pregnant People and Infants Network (SET-NET) to describe the prevalence of substance use among pregnant persons with syphilis by congenital syphilis pregnancy outcome (defined as delivery of a stillborn or live-born infant meeting the surveillance case definition for probable or confirmed congenital syphilis). The prevalence of substance use (e.g., tobacco, alcohol, cannabis, illicit use of opioids, and other illicit, nonprescription substances) in persons with a congenital syphilis pregnancy outcome (48.1%) was nearly double that among those with a noncongenital syphilis pregnancy outcome (24.6%). Persons with a congenital syphilis pregnancy outcome were six times as likely to report illicit use of opioids and four times as likely to report using other illicit, nonprescription substances during pregnancy than were persons with a noncongenital syphilis pregnancy outcome. Approximately one half of persons who used substances during pregnancy and had a congenital syphilis pregnancy outcome had late or no prenatal care. Tailored interventions should address barriers and facilitators to accessing screening and treatment for syphilis among persons who use substances. The need for syphilis screening and treatment should be addressed at any health care encounter during pregnancy, especially among persons who use substances., Competing Interests: All authors have completed and submitted the International Committee of Medical Journal Editors form for disclosure of potential conflicts of interest. Elizabeth Burkhardt reports support from the Georgia Department of Public Health to attend conferences with topics on sexually transmitted diseases, including congenital syphilis. Kathryn Miele reports support from the Infectious Diseases Society for Obstetrics and Gynecology for meeting registration. Dana Meaney-Delman reports annual support from the American Board of Obstetrics and Gynecology to serve as Board Examiner for OBGYN certifying exam. No other potential conflicts of interest were disclosed.

The Patient Protection and Affordable Care Act of 2010 is the most important US health legislation since the creation of Medicare and Medicaid in 1965. Repeated attempts at a complete overhaul of the health care system under various administrations and 4 decades of incrementalism in our approach to health policy making paved the way for this historic legislation. Major components of the recently enacted legislation include a substantial expansion of the Medicaid program to include 17.1 million currently uninsured adults with incomes below 133% of the federal poverty line, a mandated minimum health benefits package, a renewed focus on prevention, the establishment of state health exchanges with special provisions to permit affordability by those with incomes below 400% of the federal poverty line, and the establishment of high-risk health insurance pools for patients who were previously denied coverage because of preexisting conditions. The time for change was long overdue. Although many challenges exist, particularly for the states, in the implementation phase of the Affordable Care Act, the benefit to low-income cancer patients is increased access to guideline-recommended levels of screening, diagnostic, treatment, and follow-up services.