Integrating Artificial Intelligence (AI) with healthcare offers transformative opportunities to enhance the management of healthcare operations, including continuity of care and resource efficiency. This study presents a Machine Learning (ML)-based framework to improve patient care transitions by identifying and prioritizing interventions for individuals at high risk of care fragmentation. Using a rich, longitudinal dataset spanning over a decade of patient hospitalization records, our predictive-prescriptive analytics model proactively identifies at-risk patients, optimizing resource allocation and mitigating disruptions in care provision. We benchmark our AI-driven approach against conventional strategies, including random and naïve interventions, demonstrating significant efficiency gains in cost savings and equitable resource allocations among equity-seeking groups. A key contribution of this work is the explicit consideration of fairness in decision-making, analyzing the trade-offs between operational efficiency and fairness, a key ethical consideration. Our findings highlight AI’s potential to streamline healthcare operations while balancing equity and efficiency, informing broader strategies for responsible and cost-effective healthcare management. By addressing biases and improving care continuity for vulnerable populations, this study advances the methodological and practical aspects of AI applications in healthcare as well as the ethical discourse surrounding its deployment. Our approach provides a novel perspective on leveraging emerging technologies, such as AI, to enhance patient outcomes while upholding principles of fairness and accountability.