Prediction and optimization techniques to streamline surgical scheduling
Name
862229484-MIT.pdf
Description
Full printable version
Size
12.64 MB
Format
Adobe PDF
Checksum (MD5)
2d7639289d93a6b7688d9300b3c9ed5a
Author(s)
Graue, Ryan M. (Ryan Matthew)
Advisor(s)
Vivek Farias and Deborah Nightingale.
Date Issued
2013
Publisher
Massachusetts Institute of Technology
Abstract
Abstract We have created a set of decision support tools to streamline the surgical case scheduling process by allowing surgical wait list cases (elective cases that cannot be assigned a slot on the operating room schedule at the time of booking) to be confirmed onto the operating room schedule up to three weeks in advance of the day of surgery. Prior to our research, wait list cases could not be confirmed more than a few days prior to the desired day of surgery due to uncertainty about available time prior to the release of dedicated OR capacity. Earlier confirmation of wait list cases serves three purposes: (1) to improve patients' ability to plan logistics to prepare for their visits, (2) to reduce wait list case backlogs for surgeons' offices, and (3) to reduce variability in the total daily caseload through proactive decision making. Our contributions assist scheduling personnel in confirming wait list case dates sooner to help medical institutions achieve these benefits. We have developed two Excel-based pieces of software: a prediction tool and a schedule optimization tool. The prediction tool predicts time that is available each day between one and three weeks in advance to accommodate wait list cases, and the schedule optimization tool automates the consolidation process for all cases that are currently booked on a future date so that rooms and equipment are used as efficiently as possible. Our platform lets users interact with simple GUIs in which they make selections to generate prediction results and optimized daily case schedules. Specifically, our prediction algorithm employs a multiple linear regression model over historical data to forecast unused time, and the optimization tool uses a mixed integer linear program to optimize the daily schedule by consolidating cases into a minimum number of rooms and closing any gaps between cases, subject to constraints that are specific to the facility and the date in question. We have achieved our desired outcome of maximizing operating room resource utilization by giving human schedulers a set of tools to use on a daily basis that simplifies the scheduling process and confirms wait list cases with more advance notice. This system is generalizable to other areas within healthcare delivery environments and any other industry where tasks are scheduled in advance into a fixed set of resources with a record of historical demand over time.
Description
Thesis (M.B.A.)--Massachusetts Institute of Technology, Sloan School of Management; and, (S.M.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics; in conjunction with the Leaders for Global Operations Program at MIT, 2013.
This electronic version was submitted and approved by the author's academic department as part of an electronic thesis pilot project. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from department-submitted PDF version of thesis
Includes bibliographical references (p. 72-76).
Subjects
Aeronautics and Astronautics.
Sloan School of Management.
Leaders for Global Operations Program.
MIT Department
Leaders for Global Operations Program at MIT
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Sloan School of Management
Terms of Use
M.I.T. theses are protected by
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
copyright. They may be viewed from this source for any purpose, but
reproduction or distribution in any format is prohibited without written
permission. See provided URL for inquiries about permission.
Persistent DSpace Link
