How can integrating AI and personalised medicine improve population health management? A human-centred design perspective

Abstract

Background: Healthcare systems worldwide are grappling with profound challenges posed by demographic shifts, the increasing burden of chronic diseases, and escalating healthcare expenditures. Conventional healthcare models, primarily reactive in nature, are proving inadequate in addressing the complex needs of diverse patient populations. Population Health Management (PHM) represents a paradigm shift towards proactive, data-driven approaches aimed at optimizing health outcomes across populations. Concurrently, precision medicine and AI are transforming healthcare delivery by personalised treatments based on individual genetic, environmental, and lifestyle factors. This review investigates how integrating AI and precision medicine into PHM can enhance the delivery of personalized care, improve health outcomes, and mitigate disparities in healthcare access and quality. Guided by the Human-Centred Design (HCD) framework, it explores the intersection of these technologies to propose strategies for effective implementation and future research directions. Objectives and research questions: This study aims to critically evaluate existing literature on PHM, AI, and precision medicine to: • Identify factors influencing population health and personalized care outcomes. • Assess challenges and recommendations for integrating AI and precision medicine into PHM. • Frame research questions around concepts of data-driven healthcare, equity in healthcare delivery, and technological innovation within the HCD framework. Design/methodology: Systematic review methodology is employed to synthesize findings from qualitative interviews, systematic reviews, and expert analyses across various geographic regions and disciplines. Theoretical framework: Human-Centred Design (HCD) guides the integration of AI and precision medicine into PHM, ensuring solutions are patient-centric, inclusive, and ethically sound. Findings: The integration of PHM, precision medicine, and AI holds promise for enhancing personalized healthcare across therapy planning, risk prediction, and diagnosis. Challenges include ethical considerations, data privacy, and algorithmic biases, which must be addressed to realize AI's full potential in healthcare. Research implications and limitations: Implications include informing health policy and management practices to support AI-driven PHM initiatives. Limitations include the lack of empirical studies specifically addressing AI in PHM and the emerging nature of these technologies in healthcare settings. Originality/value: The findings contribute to policymaking by recommending strategies for implementing AI-driven PHM effectively. Further research is needed to empirically validate these strategies and their impact on healthcare outcomes.