Research Paradigms for Health Equity in Intelligent Mobile Healthcare Technologies: A Critical Review

Sustainable Development Goals (SDGs) highlight the importance of considering inequalities in designing, implementing, and operating sustainable intelligent systems for healthcare. These systems often address Health Inequalities during healthcare promotion. Unfortunately, the complexity of these inequalities continuously affects vulnerable populations and developing economies. This is mainly attributed to the variations in social determinants caused by social inequalities among social groups in the general population with their intersecting social factors. Numerous technologies like Mobile Health have been developed to address issues of Equitable access to healthcare. Unfortunately, some of the disruptive underlying innovative technologies facilitating Mobile health for example Machine Learning (ML) and Artificial Intelligence (AI) still exhibit algorithmic unfairness. This is mainly attributed to inequitable healthcare datasets arising from the contextual and intersectional differences among the beneficiaries of the Mobile Health services. Moreover, AI and ML are now globally adopted in establishing sustainable intelligent predictive and preventive Mobile Healthcare systems, despite the lag in shifting and adopting contextually appealing research paradigms for responsibly creating inclusive AI and ML training datasets for Intelligent Healthcare Technologies. This chapter critically reviews conventional research paradigms, their essential elements, and their contextual application in creating AI and ML training datasets for sustainable healthcare and Health Equity. This review finally recommends responsible and Inclusive Intersectional AI research approaches to creating ML and AI Training datasets for Equitable Mobile Health Technologies and sustainable intelligent healthcare systems.