Machine Learning Applications in Operating Room Scheduling
M. Chavosh Nejad
Ph.D. candidate, Aalborg University, CHOIR Visitor
The demand for surgical services has increased during the recent years. From the other side, hospitals suffer from surgical resource limitations to satisfy the increasing demand for surgical services. While surgical infrastructure development is an expensive, time-consuming process, improving the efficiency of utilizing current resources can help hospitals in providing surgical services for their patients. This PhD thesis focuses on improving the efficiency of operating room (OR) scheduling at Aalborg University Hospital (AUH) to address long patient waiting times in Denmark's healthcare system. The current manual scheduling process does not utilize historical surgical data, leading to inefficiencies. The research aims to analyze past surgical data using machine learning (ML) to predict surgery duration as a key uncertainty factor in OR and distinguish patients through clustering for a better scheduling practice. Based on these insights, optimization methods will be applied to enhance OR scheduling, ultimately improving resource utilization and reducing patient transfers. The expected contribution is a scheduling model that integrates ML and optimization techniques to better manage OR uncertainties, increasing hospital efficiency and patient satisfaction.
Chavosh joined Aalborg University, Denmark, in June 2022, after completing both my bachelor’s and master’s degrees in Industrial Engineering from top universities in Iran. His research interests are in applications of machine learning in healthcare systems, organizational operation optimization, and formulating operational strategies under uncertainty.
Prediction and Optimization for a better railway system
Professor Francesco Corman
ETH Zurich
This talk reports on different challenges and opportunities for optimization in traffic control in railway systems. From the point of view of determining a control objective to support automatic decision, the challenge is how to understand the impact of a decision in terms of system performance. Almost all of those problems have to deal with unknown future states, which must be predicted, typically by model-based or black box approaches, also based on advanced analytics. Once an objective function and optimization variables are determined, optimization models can help finding a solution quickly and effectively. Further challenges are the acceptance of decision stakeholders, within the control room, but also within the travelers and operators, or the direct implementation in automatic digital control. For passenger oriented traffic control, this is particularly interesting and challenging, due to the large amount of possible decision per decision maker; of decision makers; and of data that can partially describe those aspects, which calls for machine learning approaches.
Francesco Corman is associate professor of Transport Systems at the Institute of Transport Planning and Systems, Swiss Federal Institute of Technology, ETH Zurich. He has a PhD in Transport Sciences from TUDelft, the Netherlands, on operations research techniques for realtime railway traffic control. His main research interests are in the application of quantitative methods and operations research to transport sciences, especially on the operational perspective, public transport, railways and logistics. Current research projects tackle analytics for public transport, energy efficiency in railway operations, railway traffic control systems, optimization in logistics chains, integration of maintenance in transport systems operations.