Improving hospital bed occupancy and resource utilization through queuing modeling and evolutionary computation.

Area of Science:

• Healthcare Management
• Operations Research
• Health Informatics

Background:

• Healthcare resources are limited, necessitating efficient policies for bed allocation, service quality, and financial support.
• Optimizing hospital resource allocation is crucial for maintaining quality care and operational efficiency.

Purpose of the Study:

• To propose and validate a complex analytical framework for hospital resource allocation.
• To integrate queuing systems, compartmental models, and evolutionary optimization for enhanced bed management and resource utilization.

Main Methods:

• Utilized a queuing system to model patient flow within a hospital setting.
• Employed a compartmental model to structure hospital departments based on queuing characteristics.
• Applied an evolutionary-based optimization, specifically a genetic algorithm, for optimizing bed occupancy and resource utilization.
• Incorporated a 'What-if analysis' for exploring parameter changes' effects on outcomes.

Main Results:

• Demonstrated the methodology's application using real data from a geriatric department in London, UK.
• Validated the model's adaptability to various medical departments, including surgery, stroke, and mental illness.
• Presented a simulated application highlighting the model's practical utility for healthcare decision-making.

Conclusions:

• The integrated framework provides a robust tool for optimizing hospital resource allocation and bed management.
• The methodology offers flexibility for 'What-if analysis' and adaptation across diverse medical departments.
• This approach supports evidence-based policymaking for efficient healthcare resource utilization.