KIU Publications

Substantial yet preventable maternal and neonatal mortality persists across low- and middle-income countries (LMICs), where shortages of skilled maternal and child health (MCH) nurses, inadequate infrastructure and socioeconomic inequalities continue to limit access to quality care. Artificial intelligence (AI), particularly machine-learning-driven decision-support and predictive systems, is increasingly proposed to strengthen MCH services through risk stratification, early diagnosis and clinical decision-making. However, evidence supporting its equitable, contextually appropriate and sustainable implementation in resource-constrained settings remains limited. Existing literature has inadequately addressed the structural, ethical and relational dimensions of AI adoption from a nursing perspective, and there is a lack of frameworks integrating equity, nurse-led governance and contextual adaptation for LMICs. Drawing on a purposive narrative review, this Perspective proposes an equity-centred, nurse-led framework for AI-assisted MCH nursing in low-resource settings. The framework comprises six interdependent domains: contextual algorithm validation, humanised and relational nursing care, community co-design and engagement, digital equity and inclusion, transparent data governance, and longitudinal monitoring and evaluation. Its novelty lies in positioning equity as a prerequisite for deployment, identifying the nursepatient relationship as the principal mechanism through which AI influences outcomes, and assigning governance authority to nurses and communities. A phased implementation pathway is proposed to guide responsible deployment. The framework remains conceptual and requires prospective empirical validation. Responsible AI integration in MCH nursing demands equity-centred governance, investment in nursing capacity, community participation and locally grounded validation strategies.