BALTIMORE, February 12, 2026 — New research published in the INFORMS journal Operations Research shows that healthcare systems can substantially reduce overtime, idle time and overall staffing costs by adopting a multilocation, dynamic staff-planning model for anesthesiologists. The study is based on the University of Pittsburgh Medical Center (UPMC), which cut daily overtime and idle time across 11 hospitals, generating over $800,000 in annual cost savings.
The INFORMS study “Multilocation, Dynamic Staff Planning for a Healthcare System: Methodology and Application” was authored by Sandeep Rath of the Indian School of Business, Kumar Rajaram of UCLA Anderson School of Management and Mark E. Hudson and Aman Mahajan of the University of Pittsburgh Medical Center.
Healthcare systems nationwide face rising costs, workforce shortages and high demand variability, especially in operating rooms, where daily anesthesia requirements fluctuate sharply due to unpredictable case volumes and surgery durations. Planning anesthesiology coverage is particularly complex because assignments must balance clinician availability, individual hospital credentialing constraints, fairness rules for on-call duties and the need to minimize both costly overtime and under-utilized idle time.
“Staffing anesthesiologists in a multilocation health system is extremely difficult because demand is highly uncertain even a few days before surgery,” said Rath. “By formulating this as a multistage robust optimization problem, we were able to create a practical and implementable model that accounts for individual-level assignment constraints while reducing system-wide costs.”
To address these challenges, the researchers developed a three-stage optimization model that assigned anesthesiologists to locations or an on-call pool six weeks before surgery, redeployed on-call physicians based on updated forecasts three days before surgery and then accounted for realized workloads on the day of surgery. The model incorporated individual provider constraints, fairness requirements and uncertainty in both surgery volume forecasts and total anesthesia hours.
“We show that combining an on-call structure with robust, data-driven planning can substantially reduce overtime and idle time,” said Rajaram. “Our approach also demonstrates how fairness constraints, such as ensuring no one is placed on consecutive on-call days, can be integrated without sacrificing efficiency.”
The model was implemented and validated within UPMC’s Department of Anesthesiology and Perioperative Medicine, which coordinates staffing across 11 operating room suites in the Pittsburgh region. The results were significant: the system reduced daily overtime by nearly 13 hours and idle time by 14 hours, generating $8,382 in daily cost reductions. Even after including additional compensation for on-call duties, the net savings totaled $2,199 per day, or more than $800,000 per year.
“By optimizing our on-call staffing system, we created a more efficient and predictable schedule for anesthesiologists while reducing unnecessary costs,” Hudson said. “This model provides a blueprint for other departments and health systems facing similar operational challenges.”
Beyond the immediate cost savings, the study also provides managerial insights regarding the value of improved short-term forecasts, the importance of location flexibility in clinician assignments and the operational implications of fairness constraints.
“Our methodology generalizes easily to other clinical staffing areas, such as nurse scheduling, where uncertainty and fairness are major concerns,” Mahajan added. “This kind of dynamic, data-driven approach is critical to improving efficiency in modern healthcare.”
The authors note that this is one of the first large-scale implementations of individual-level, adaptive staff planning across a multilocation healthcare system, offering a framework that can be extended to hospital networks nationwide.
The full study can be found here.
About INFORMS
INFORMS is the world’s largest association for professionals and students in operations research (O.R.), AI, analytics, data science and related disciplines, serving as a global authority in advancing cutting-edge practices and fostering an interdisciplinary community of innovation. INFORMS empowers its community to enhance organizational performance and drive data-driven decision-making through its journals and resources. Learn more at www.informs.org or @informs.
About Operations Research
Operations Research, a leading INFORMS journal, publishes high-quality papers that represent the true breadth of the methodologies and applications that define O.R.
Contact:
Rebecca Seel
Public Affairs Specialist
(443) 757-3578
# # #
Media Contact
Jeff Cohen
Chief Strategy Officer
INFORMS
Catonsville, MD
[email protected]
443-757-3565