Hybrid models of operations research and artificial intelligence for integrated operating room scheduling and perioperative patient pathways

The core focus of this research is surgical activity, a key component of hospital management. Surgery involves a wide range of highly specialized human and technological resources and represents the area with the greatest impact not only on patient health outcomes but also on the hospital’s economic performance. Throughout the PhD journey, the research was directed toward the study and implementation of Operation Research (OR) and Machine Learning techniques to provide practical solutions for the management of operating rooms and outpatient surgical scheduling. A data-driven, multi-phase approach was adopted. It began with the analysis of existing hospital information systems to map and understand the complex dynamics occurring within the healthcare setting. This phase was followed by the development of classification, forecasting, and prescriptive models aimed at optimizing surgical processes. These models were then integrated into optimization frameworks and metaheuristic algorithms, with their performance ultimately validated through simulation experiments. The results demonstrated how advanced data analytics can support operational decision-making in hospitals, enabling more efficient use of surgical resources, improving planning accuracy, and ultimately contributing to higher quality and sustainability in healthcare delivery.