Artificial Intelligence for Health Equity and Health Security in Northern Nigeria: A Scoping Synthesis of Evidence, Health-System Readiness, and A Framework for Responsible Public Health Transformation

Abstract

Artificial intelligence (AI) is moving from experimental applications toward practical use in healthcare, public health intelligence, health communication, diagnostics, workforce support and health-system management. Its potential is especially relevant to Northern Nigeria, where substantial public health needs coexist with socioeconomic deprivation, nutrition insecurity, infectious disease threats, maternal and child health inequalities, insecurity, population displacement and uneven health-system capacity. Yet AI readiness and evidence of real-world benefit remain uneven, and poorly governed deployment could reproduce or deepen existing inequities.To synthesise current evidence on the potential contribution of AI to health equity and health security in Northern Nigeria, examine the region’s public health and health-system context, identify opportunities and implementation constraints, and propose an evidence-informed framework for responsible AI-enabled public health transformation.The paper uses a scoping synthesis and policy-framework approach. Peer-reviewed literature and authoritative institutional sources concerning AI, machine learning, digital health, health systems, public health surveillance, nutrition, maternal and child health, ethics and governance were examined, with emphasis on Nigeria, Africa and low- and middle-income countries. Updated contextual evidence was drawn from the 2024 Nigeria Demographic and Health Survey, the 2022 Nigeria Multidimensional Poverty Index, Nigeria’s National Artificial Intelligence Strategy, the Federal Ministry of Health and Social Welfare’s State of Health of the Nation reporting, WHO guidance and recent African evidence. Evidence was synthesised thematically rather than statistically pooled.The literature supports potential applications of AI in disease surveillance, epidemic intelligence, nutrition early warning, maternal and child health risk stratification, multilingual health communication, workforce decision support and resource optimisation. However, evidence from low-resource settings remains dominated by small-scale, research-oriented or externally funded projects, with limited national or state-level implementation evidence. Key constraints include fragmented and incomplete data, interoperability gaps, weak digital infrastructure, limited technical and AI literacy, insufficient local validation, algorithmic bias, cybersecurity and privacy risks, and variable institutional ability to act on AI-generated signals. Current Nigerian policy developments including the National AI Strategy and the Nigeria Data Protection Act provide an emerging governance foundation, but health-sector implementation requires stronger operational mechanisms. AI should be treated as a health-system capability rather than a stand-alone technology. Northern Nigeria would benefit from a problem-first, equity-centred and human-supervised approach that links high-priority public health needs to reliable data, local validation, workforce capability, accountable governance and response capacity. The paper proposes the AI–PUBLIC HEALTH–NIGERIA Framework, alongside a phased implementation roadmap, as a practical architecture for responsible adoption.