Abstract
Rural and underserved communities continue to face barriers to timely and accurate healthcare due to shortages of specialists, limited diagnostic infrastructure, and geographic isolation. Artificial intelligence (AI)-driven diagnostic tools, including machine learning (ML) algorithms, telehealth platforms, and clinical decision support systems, have the potential to address these challenges. A systematic review was conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed, Scopus, Web of Science, and Embase were searched for studies published between January 2010 and April 2025 that evaluated AI-based diagnostic interventions in rural or low-resource settings. Findings were synthesized thematically to assess diagnostic performance, healthcare access, efficiency, and implementation factors. Twenty-six studies met the inclusion criteria, including observational studies, implementation case reports, and systematic reviews. Overall, AI tools were associated with improved diagnostic accuracy, reduced turnaround times, and enhanced access to services through mobile and telehealth applications. Commonly reported barriers included limited digital infrastructure, gaps in provider training, data privacy concerns, and regulatory uncertainty, while enabling factors included community trust, integration with existing health systems, and supportive policy environments. AI-driven diagnostics therefore show considerable promise for reducing inequities in rural healthcare, although successful implementation will require context-specific strategies, sustained infrastructure investment, and strong ethical and regulatory oversight.