Data-Driven Insights into Maternal and Child Health Inequalities in the U.S

• Published in: Current Journal of Applied Science and Technology Vol. 44; no. 8; pp. 98 - 110
• Main Authors: Olatunbosun, Temiloluwa Evelyn, Iheanetu, Cindy Chinonyerem
• Format: Journal Article
• Language: English
• Published: Current Journal of Applied Science and Technology 18.08.2025
• Subjects: Computer Science; Technology for Human Learning
• ISSN: 2457-1024; 2457-1024
• DOI: 10.9734/cjast/2025/v44i84593

Objective: This study explores the emerging role of data analytics in identifying and addressing maternal and child health disparities in low-income U.S. communities. It aims to assess how predictive modeling, geospatial analysis, and natural language processing (NLP) have been applied to expose structural inequities in care and improve health outcomes for marginalized populations in the US. Study Design: The study is structured as a narrative and thematic review, synthesizing academic literature from 2018 to 2025. It integrates findings from peer-reviewed articles, public health reports, and clinical research that employ data-driven tools to understand and intervene in maternal health inequities across demographic, geographic, and socioeconomic dimensions. Methodology: 40 peer-reviewed studies were selected through a systematic search process across databases including PubMed, Scopus, and Google Scholar. The selected literature was categorized and analyzed thematically across key domains: predictive analytics, geospatial mapping, machine learning, bias detection in clinical documentation, and data infrastructure disparities. Results: Findings reveal that while predictive models and geospatial analytics effectively flag high-risk maternal populations and identify “care deserts,” their impact is constrained by data fragmentation, underreporting in marginalized groups, and algorithmic bias in clinical notes. Community-engaged data systems, improved EHR interoperability, and equity-centered dashboard design emerged as critical enablers. Early adoption of NLP and wearable technologies also shows potential for real-time, personalized maternal health surveillance. Conclusions: To move from disparity identification to disparity elimination, data analytics must be integrated into a broader ecosystem of community ownership, ethical design, and policy alignment. Achieving equitable maternal health outcomes will require cross-sector collaboration, real-time analytics infrastructure, and a shift from observational to intervention-oriented models.