Tracking funding disparities in global health aid with machine learning.

Machine learning reveals that NCDs account for 59.5% of global DALYs but only 2.5% of health aid from 2000 to 2022.

• Why it matters: Addressing funding disparities is vital to ensure vulnerable populations receive adequate support for major health challenges, especially in low- and middle-income countries facing dual disease burdens.
• What they did: A machine learning pipeline analyzed 3.7 million development aid projects totaling approximately USD 332 billion, classifying them into 17 disease categories and comparing aid disbursement ranks with DALY-based disease burdens.
• The result: Findings highlight significant aid-burden misalignments across regions like Central Africa and South Asia, providing insights to guide more equitable and targeted health aid policies worldwide.