Review on Artificial Intelligence applied to Cardiovascular Disease Management in Latin America

Abstract

Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, with Latin America facing unique challenges due to socioeconomic disparities, limited healthcare resources, and fragmented medical infrastructures. Artificial Intelligence (AI) has emerged as a transformative technology in CVD management, offering potential solutions for early diagnosis, risk stratification, and treatment optimization. However, the adoption of AI in Latin America remains underexplored. This narrative review synthesizes the current state of AI applications in cardiovascular healthcare across the region, analyzing trending research, challenges, and opportunities based on 22 selected studies. The findings highlight a growing interest in AI-driven predictive models, clinical decision support systems, and remote monitoring technologies. Machine learning (ML) techniques have demonstrated promising results in improving CVD diagnosis and prognosis. However, significant barriers such as data scarcity, interoperability challenges, and regulatory limitations hinder widespread clinical implementation. Several studies utilized local datasets, while others relied on international repositories, raising concerns about model generalizability to Latin American populations. Despite these limitations, AI presents an opportunity to bridge healthcare gaps by enabling more efficient and accessible CVD management. This review underscores the need for region-specific AI research, enhanced data-sharing frameworks, and collaborative efforts among healthcare institutions, policymakers, and technology developers. By addressing these challenges, AI has the potential to substantially advance cardiovascular healthcare in Latin America, improving patient outcomes and reducing the burden of CVDs in resource-limited settings. Clinical Relevance: This review evaluates AI's role in cardiovascular disease management in Latin America, identifying key techniques, ML implementations, challenges and opportunities.