Real-time healthcare staffing optimization using fuzzy logic and genetic algorithm

Area of Science:

• Healthcare Management
• Operations Research
• Artificial Intelligence in Healthcare

Background:

• Healthcare systems face challenges like rising costs, increased demand, and resource constraints.
• Effective management and efficient resource utilization are crucial for healthcare delivery.
• Optimized systems improve service delivery and reduce patient waiting times.

Purpose of the Study:

• To introduce a novel model for optimizing healthcare staffing in real-time.
• To address the limitations of traditional fixed-staffing models in dynamic healthcare environments.
• To improve the efficiency and responsiveness of healthcare services.

Main Methods:

• Development of the Fuzzy-Based Time-Dependent Multi-Server, Multi-Queueing (FB-TDMS-MQ) System.
• Integration of fuzzy logic and a genetic algorithm (GA) for dynamic staff optimization.
• Validation through a case study at Dhanwantri Hospital and Research Centre (DHRC) using simulation studies.

Main Results:

• A 72.73% reduction in average peak-hour waiting time was achieved with fuzzy logic modifications.
• The genetic algorithm optimization led to a 50.2% decrease in average waiting time.
• The model demonstrated superior performance compared to static staffing models and proved useful for handling unexpected events.

Conclusions:

• The FB-TDMS-MQ model offers an adaptable and effective solution for real-time healthcare staffing optimization.
• Dynamic staff allocation using this model can significantly reduce patient waiting times and improve hospital management.
• The model's ability to handle unexpected events highlights its potential for enhancing healthcare system resilience.