Abstract
Artificial intelligence (AI) has become a strategic technology for global health, with increasing relevance amid the climate emergency and persistent digital inequalities. This study examines how AI has been applied in Brazilian healthcare through a scoping review with an in-depth methodological synthesis, focusing on Transfer Learning (TL) and Federated Learning (FL) as approaches to address data scarcity, privacy, and technological dependence. We searched PubMed, SciELO, and the CNPq Theses and Dissertations Repository for peer-reviewed studies on AI applications in Brazil, screened titles using AI-assisted tools with manual validation, and analyzed thematic patterns across methodological and infrastructural dimensions. Among 349 studies retrieved, six explicitly used TL or FL. These techniques were frequently implemented through multi-country research consortia, demonstrating scalability and feasibility for collaborative model training under privacy constraints. However, they remain marginal in mainstream practice despite their ability to deploy AI solutions with limited computational resources while preserving data sovereignty. The findings indicate an emerging yet uneven integration of resource-aware AI in Brazil, underscoring its potential to advance equitable innovation and digital autonomy in health systems of the Global South.