A Hybrid Genetic Algorithm for Nurse Scheduling Problem considering the Fatigue Factor

Area of Science:

• Operations Research
• Healthcare Management
• Nursing Informatics

Background:

• The COVID-19 pandemic has significantly increased pressure on nurses globally.
• Sustained high workloads contribute to nurse fatigue, impacting patient care and well-being.
• Existing nurse scheduling models often do not adequately address fatigue factors.

Purpose of the Study:

• To develop a novel mathematical model for the Nurse Scheduling Problem (NSP) that incorporates nurse fatigue.
• To create an efficient algorithm for solving the proposed NSP model.
• To validate the model's effectiveness in both simulated and real-world hospital settings.

Main Methods:

• Formulation of a new mathematical model for NSP with a fatigue consideration.
• Development of a hybrid Genetic Algorithm (GA) to solve the optimization problem.
• Testing and validation using a randomly generated problem and a case study from a COVID-19 ward.

Main Results:

• The hybrid GA effectively generated optimal nurse schedules for all three daily shifts.
• The proposed model produced schedules superior to traditional manual scheduling in a real hospital case study.
• The model demonstrated practical applicability in a high-pressure healthcare environment.

Conclusions:

• Incorporating nurse fatigue into scheduling models is crucial for optimizing workforce management.
• The developed mathematical model and GA offer an effective solution for fatigue-aware nurse scheduling.
• This approach can enhance nurse well-being and potentially improve patient care quality, particularly during crises.