BACKGROUND: The alarming rise in dengue cases and fatalities worldwide necessitates an in-depth analysis of essential public health functions (EPHFs) to fortify the resilience of health systems in the face of upcoming surges. This study focuses on the resilience of Brazil's health system in managing dengue from 2010 to 2024, leveraging machine learning techniques to correlate EPHF variables with dengue outcomes. METHODS: Utilizing public data from DATASUS and IBGE, we evaluated indicators such as healthcare workforce, health facilities, and dengue-specific data. A regression tree analysis identified associations between dengue hospitalizations and dengue deaths among Brazilian capitals, emphasizing the importance of strengthening outpatient services and monitoring systems for resilient performance. FINDINGS: This study revealed that capitals with fewer hospitalizations have seen recent improvements
nevertheless, continuous efforts are vital to prevent sudden surges. These findings underscore the critical role of health surveillance and community involvement in enhancing EPHF performance. INTERPRETATION: This research contributes to understanding the dynamic interactions within health systems and highlights the importance of proactive and integrated public health strategies to manage dengue and similar arboviruses. FUNDING: The present study was funded by the Inova Fiocruz Program, grant 1366515559697323
and by the National Council for Scientific and Technological Development (CNPq), grant 401278/2022-0. Alessandro Jatobá is partially funded by CNPq, grants 307029/2021-2 and 405469/2023-3 and by the Carlos Chagas Filho Foundation for Research Support of the State of Rio de Janeiro (FAPERJ), grant E-26/210.728/2023 and E-26/201.252/2022. Paulo Victor Rodrigues de Carvalho is partially funded by CNPq, grant: 304770/2020-5 and by FAPERJ, grant E-26/203.934/2024.