Abstract
Maternal mortality remains a critical public health challenge in Pakistan, where socioeconomic disparities, delayed diagnosis of pregnancy-related complications, and limited access to quality maternal healthcare continue to contribute to preventable maternal deaths. Recent advances in artificial intelligence (AI) have created new opportunities to enhance maternal healthcare through predictive analytics that support early identification of high-risk pregnancies and timely clinical interventions. This study examined the effect of AI-driven predictive modeling on maternal mortality risk reduction by integrating socioeconomic and clinical determinants within Pakistan's healthcare system. Grounded in the Health Belief Model (HBM), the study employed a quantitative, explanatory, and cross-sectional research design. Data were collected from 432 healthcare professionals, including obstetricians, gynecologists, medical officers, nurses, midwives, and public health specialists working in public and private healthcare institutions across Pakistan. A structured questionnaire based on validated measurement scales was used, and the proposed research model was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings indicated that AI-driven predictive modeling significantly enhanced early risk identification and contributed to maternal mortality risk reduction. Early risk identification also exerted a significant positive effect on maternal mortality risk reduction and partially mediated the relationship between AI-driven predictive modeling and maternal health outcomes. The results demonstrate that integrating socioeconomic and clinical determinants into AI-assisted predictive systems substantially improves the accuracy of maternal risk assessment, enabling timely interventions, optimized healthcare resource allocation, and evidence-based clinical decision-making. The study contributes to the growing literature on artificial intelligence, maternal healthcare, and digital health by extending the Health Belief Model to AI-enabled predictive healthcare. The findings provide practical guidance for healthcare professionals, policymakers, and digital health stakeholders seeking to strengthen maternal healthcare services and accelerate progress toward achieving Sustainable Development Goal 3 by reducing preventable maternal mortality in Pakistan.