Development of a Machine Learning Modelling Tool for Predicting HIV Incidence Using Public Health Data from a County in the Southern United States

Abstract

Background: Recent advancements in Machine Learning (ML) have significantly improved the accuracy of models predicting HIV incidence. These models typically utilize electronic medical records and patient registries. This study aims to broaden the application of these tools by utilizing de-identified public health datasets for notifiable sexually transmitted infections (STIs) from a southern U.S. County known for high HIV incidence rates. The goal is to assess the feasibility and accuracy of ML in predicting HIV incidence, which could potentially inform and enhance public health interventions.

Methods: We analyzed two de-identified public health datasets, spanning 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 algorithms were trained and evaluated for predicting HIV incidence, using metrics such as accuracy, precision, recall, and F1 score.

Results: The study included 85,224 individuals, with 2,027 (2.37%) newly diagnosed with HIV during the study period. The ML models demonstrated high performance in predicting HIV incidence among males and females. Influential predictive features for males included age at STI diagnosis, previous STI information, provider type, and SVI. For females, they included age, ethnicity, previous STIs 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.

Keywords: EHE; HIV; artificial intelligence; machine learning; public health.