Managing magnetic resonance imaging machines: support tools for scheduling and planning

Area of Science:

• Radiology and Medical Imaging
• Operations Research
• Healthcare Management

Background:

• Hospitals face challenges in managing patient demand for Magnetic Resonance Imaging (MRI) services.
• Efficient scheduling and resource allocation are crucial for optimizing MRI machine throughput and patient utilization.

Purpose of the Study:

• To develop models and algorithms for estimating current and future patient demand for MRI examinations.
• To improve MRI scheduling decisions and support personnel and equipment planning.
• To address the competing objectives of maximizing examination throughput and patient-magnet utilization.

Main Methods:

• Development of novel scheduling algorithms to balance competing objectives.
• Construction of a simulation model using historical patient and MRI utilization data.
• Retrospective analysis of scheduling decisions and identification of efficiency improvements.

Main Results:

• The developed algorithms can assess past scheduling, identify efficiency gains, and pinpoint challenging examination types.
• The simulation model forecasts MRI demand under various scenarios.
• Algorithm-calculated throughput estimates MRI overtime needs, informing staffing and equipment planning.

Conclusions:

• The proposed models and algorithms provide a robust framework for optimizing MRI operations.
• This approach supports data-driven decision-making for radiology departments.
• Effective MRI resource management can be achieved through advanced scheduling and demand forecasting.