Applied operations research

In today's dynamic healthcare environment, continuous improvement is essential. Proactive problem-solving allows healthcare professionals to detect potential problems early and find solutions quickly. The Applied Operations Research Program within the Mayo Clinic Kern Center for the Science of Health Care Delivery applies principles from operations research, systems engineering and data science. Program experts identify inefficiencies, guide decision-making, optimize resource allocation, and use and improve outcomes.

The program develops and applies industrial and management engineering methods, along with artificial intelligence technologies, to address complex challenges in healthcare. The team works to enhance the efficiency of healthcare systems, support staff well-being and drive innovations. The program's research improves access, reduces costs, and elevates the quality of safety and patient care across Mayo Clinic.

The program draws on the knowledge and expertise of scientists with diverse backgrounds in:

  • Optimization modeling.
  • Heuristic algorithm modeling.
  • Statistical modeling.
  • Simulation modeling.
  • Machine learning modeling.

Working in collaboration with clinical teams across Mayo Clinic, the program delivers evidence-based solutions that change how healthcare is delivered.

Focus areas

The Applied Operations Research Program primarily focuses on redesigning outpatient scheduling and optimizing the use of staff and space to improve patient access, treatment quality and financial performance.

The program's responsibilities and areas of expertise include:

  • Applying operations research and data science theories and techniques.
  • Discovering innovations to advance science into practice.
  • Assisting the practice with defining operational issues and concerns.
  • Defining project elements and resource needs.
  • Extracting and manipulating data to report outcomes.
  • Developing evidence-driven, optimal solutions and executing them.
  • Creating automated tools, interfaces and software.
  • Monitoring outcomes and adjusting accordingly.

Projects

Outpatient scheduling systems

The research team is redesigning outpatient scheduling systems by developing optimal scheduling templates and policies tailored to the needs of individual medical departments at Mayo Clinic. Through this work, the team aims to reduce patient wait times, minimize staff overtime and idle time, and ultimately, increase resource stewardship and optimize space utilization.

The team also is building tools that incorporate patient characteristics and clinical conditions to account for uncertainty. For example, the team is improving chemotherapy scheduling, through template design, implementation strategies, override policies and tools to improve patient treatment allocation.

Related publications:

Real-time scheduling decision tool

The program team is developing real-time scheduling algorithms that work in tandem with existing templates to enhance scheduling efficiency and care delivery. This effort includes building infrastructure to connect algorithms with real-time data feed. These decision-support tools help schedulers find the best appointment times and locations, reducing the need for manual processes and back-and-forth communication.

Example applications of real-time scheduling decision tools include:

  • A search algorithm that pairs cardiovascular interventionalists with surgeons for transcatheter aortic valve replacement procedures.
  • A gatekeeping system for proton therapy to reduce how long patients wait for beam treatment.

Related publications:

Predictive modeling for artificial intelligence (AI)

Program researchers are applying predictive analytics — including statistical methods, machine learning and natural language processing — to support decision-making using AI in staffing, schedule planning and triage. The goal is to ensure the right patient is matched with the right healthcare professional at the right time. This work often supports scheduling and staffing optimization, either during the planning phase or in real-time decision-making.

Example applications of this work involve enhancing real-time referral triage decision for pain management services and predicting patient workload using social determinants of health.

Related publications:

Staffing assignment decisions and policy

The Applied Operations Research Program uses predictive analytics to develop algorithms that optimize staffing based on patient volume and scheduling trends. These efforts are designed to enhance both staff and patient satisfaction while improving resource utilization. Practical applications include determining ideal staffing levels for appointment call centers to improve call quality as well as designing optimal panel sizes and care team structures in primary care. These tools help balance workloads, reduce staff burnout and promote continuity of patient care.

Related publications:

Contact