Tracking funding disparities in global health aid with machine learning

Reducing the global burden of disease is crucial for improving health outcomes worldwide. However, misalignment between health aid and country-level disease burden leaves vulnerable populations without necessary support for major health challenges, particularly in the least developed countries. In this paper, we develop a machine learning pipeline using large language models to track flows in official development assistance (ODA) earmarked for health and identify aid-burden misalignment. Specifically, we classified 3.7 million development aid projects from 2000 to 2022 (USD [~]332 billion) into 17 major categories of communicable, maternal, neonatal, and nutritional diseases (CMNNDs) and non-communicable diseases (NCDs). We then compared the rank of per capita ODA disbursement against the rank of disease burden (i.e., disability-adjusted life years [DALYs]) to identify relative aid-burden misalignment at the country level. Even though funding and disease burden are significantly correlated for many diseases, there are notable disparities. For example, NCDs account for 59.5% of global DALYs but received only 2.5% of health-related ODA. This disparity is particularly concerning because, in low and middle-income countries, there is an increasing double burden: not only from the traditional burden of CMNNDs, but also from the rising burden of NCDs. Our results also show that several regions face severe aid-burden misalignment across multiple diseases including Central Africa and parts of South Asia and West Africa. Our results identify health disparities to inform public policy decisions in development aid assistance. Overall, our machine learning approach supports the targeted allocation of health aid where it is most needed, thereby reducing the global burden of diseases.