A Predictive Model for One's Ability to Pay for Pre-Exposure Prophylaxis (PrEP) Services in Uganda

Overview

Across sub-Saharan Africa, HIV remains one of the most devastating public health crises of our time yet one of the most effective prevention tools, PrEP, is still not reaching the people who need it most.Identifying and reaching high-risk populations eligible for pre-exposure prophylaxis (PrEP) is a persistent challenge for health systems and implementing partners. Without precise, data-driven insight into where and when to deploy services, resources are often misallocated leaving the most vulnerable communities underserved.This project uses machine learning and AI models to identify, quantify, and map populations at highest risk of HIV who are eligible for PrEP. By generating granular, data-driven insights on where and when to deploy services—particularly among populations best positioned to access and sustain treatment the tool empowers implementing partners to target interventions with far greater precision.The result is smarter resource allocation, wider reach, and measurably stronger impact in PrEP delivery. By ensuring prevention tools get to the right people at the right time, the project offers a scalable, responsible AI model for HIV prevention that could help bend the curve on new infections across the region.