Search

Objective: This study utilizes geospatial analytic techniques to examine HIV hotspots in Alabama leveraging Medicaid utilization data., Methods: This cross-sectional study leveraged Medicaid utilization data from Alabama's 67 counties, averaging 9,861 Medicaid recipients aged > 18 years old per county. We used Alabama Medicaid administrative claims data from January 1, 2016, to December 31, 2020, to identify individuals with HIV. Using Microsoft SQL Server, we obtained the average annual count of HIV Medicaid claims in each of the 67 Alabama counties (numerator) and the number of adult Medicaid recipients in each county (denominator), and standardized with a multiplier of 100,000. We also examined several other area-level summary variables (e.g., non-high school completion, income greater than four times the federal poverty level, social associations, urbanicity/rurality) as social and structural determinants of health. County-boundary choropleth maps were created representing the geographic distribution of HIV rates per 100,000 adult Medicaid recipients in Alabama. Leveraging ESRI ArcGIS and local indicators of spatial association (LISA), results were examined using local Moran's I to identify geographic hotspots., Results: Eleven counties had HIV rates higher than 100 per 100,000. Three were hotspots. Being an HIV hotspot was significantly associated with relatively low educational attainment and less severe poverty than other areas in the state., Conclusions: Findings suggesting that the HIV clusters in Alabama were categorized by significantly less severe poverty and lower educational attainment can aid ongoing efforts to strategically target resources and end the HIV epidemic in U.S.' Deep South., (© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Introduction: This study utilizes a machine learning model to predict unhealthy alcohol use treatment levels among women of childbearing age., Methods: In this cross-sectional study, women of childbearing age (n = 2397) were screened for alcohol use over a 2-year period as part of the AL-SBIRT (screening, brief intervention, and referral to treatment in Alabama) program in three healthcare settings across Alabama for unhealthy alcohol use severity and depression. A support vector machine learning model was estimated to predict unhealthy alcohol use scores based on depression score and age., Results: The machine learning model was effective in predicting no intervention among patients with lower Patient Health Questionnaire (PHQ)-2 scores of any age, but a brief intervention among younger patients (aged 18-27 years) with PHQ-2 scores >3 and a referral to treatment for unhealthy alcohol use among older patients (between the ages of 25 and 50) with PHQ-2 scores >4., Conclusions: The machine learning model can be an effective tool in predicting unhealthy alcohol use treatment levels and approaches., (© The Author(s) 2023. Medical Council on Alcohol and Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)