Published Paper Details:

The COVID-19 pandemic has revealed critical vulnerabilities in global healthcare supply chains, highlighting the urgent need for predictive, resilient, and intelligent systems. Artificial Intelligence (AI), particularly in the form of predictive analytics, offers transformative potential for enhancing demand forecasting and risk mitigation in healthcare logistics. This review synthesizes the state-of-the-art AI techniques used in healthcare supply chains, emphasizing machine learning (ML), deep learning (DL), hybrid approaches, and federated learning. The paper critically compares experimental outcomes across models, discusses implementation challenges, proposes a theoretical AI-integrated supply chain model, and highlights real-world use cases. Findings indicate that AI-based forecasting models significantly outperform traditional statistical methods, particularly in volatile and high-demand scenarios. However, barriers such as data privacy, infrastructure gaps, and ethical concerns remain. The review concludes with a roadmap for future research and strategic adoption of AI in healthcare logistics, promoting more resilient, transparent, and equitable health systems.