Automated Pathologist Scheduling at The Ottawa Hospital

• Published in: INFORMS journal on applied analytics Vol. 49; no. 2; pp. 93 - 103
• Main Authors: Patrick, Jonathan, Montazeri, Amine, Michalowski, Wojtek, Banerjee, Diponkar
• Format: Journal Article
• Language: English
• Published: Institute for Operations Research and the Management Sciences 01.03.2019
• Subjects: Data mining; Hospitals, Public; Human resource management; Information management; Innovations; Medical appointments and schedules; Pathologists; Ontario
• ISSN: 2644-0865; 2644-0873
• DOI: 10.1287/inte.2018.0969

In this paper, we describe the development of a decision support tool to simplify the task of scheduling pathologists to subspecialties in the Department of Pathology and Laboratory Medicine (DPLM) at The Ottawa Hospital. The DPLM employs 30 pathologists who cover 20 subspecialties. The DPLM has up to now relied on a manual monthly scheduling process that an administrative assistant typically spent approximately 30 hours each month to create. To reduce the time required and to better address the goals of the department, we developed an optimization model and a decision support tool that automates the monthly scheduling by optimizing a weighted sum of predetermined performance metrics while respecting a set of constraints. The model is an extension of the classical assignment problem; however, it includes a number of specific requirements and performance metrics unique to pathology. Using the new tool, the administrative assistant can develop a schedule that meets the DPLM's requirements in less than one hour. We demonstrate over a three-month period that this schedule outperforms the manual schedule on all six of the performance metrics established by the department, thus providing better schedules in a fraction of the time.