Theoretical Foundations of Integrating Artificial Intelligence into Preventive Care Models in Family Medicine

Abstract

This study critically explores the theoretical foundations guiding the integration of artificial intelligence (AI) into preventive care models within family medicine. While AI offers substantial benefits in early disease prediction, risk stratification, and decision support, the research reveals a persistent gap between technical implementation and theoretical, ethical, and contextual frameworks. Most studies rely heavily on electronic health records (EHRs) from high-income countries, neglecting cultural diversity and real-world applicability. The Technology Acceptance Model (TAM), Human-Centered AI (HCAI), and Explainable AI (XAI) frameworks offer valuable guidance but are inconsistently applied. Moreover, participatory design and equity-focused strategies are largely absent, raising concerns about inclusivity and long-term sustainability. The findings underscore the need for multi-theoretical, ethically grounded, and human-centered approaches to ensure that AI systems not only function effectively but also align with the holistic and patient-focused values of family medicine.