Enhancing hospital workforce planning, scheduling, and performance evaluation through an AI-driven human resource...

Area of Science:

• Healthcare Management
• Artificial Intelligence in Healthcare
• Operations Research

Background:

• Traditional human resource management (HRM) in hospitals faces challenges with manual processes, errors, and balancing staff needs with patient care.
• Inefficient workforce management impacts hospital operational quality, safety, and sustainability.

Purpose of the Study:

• To develop and evaluate an AI-driven HRM framework for hospitals to optimize workforce planning, staff scheduling, and performance assessment.
• To enhance hospital operational efficiency, staff fairness, and patient care quality through intelligent automation.

Main Methods:

• Developed a three-module AI framework: workforce demand forecasting (LSTM, XGBoost, Random Forest), intelligent staff scheduling (optimization models with constraints), and performance evaluation (metrics and NLP analysis of feedback).
• Validated the framework using synthetic and real hospital datasets, including stress tests for scalability and pilot deployments.

Main Results:

• The AI framework significantly outperformed conventional methods. LSTM achieved high forecasting accuracy (MAE=6.1, R2=0.91).
• Intelligent scheduling reduced conflicts by 41% and improved fairness (Gini=0.08). Performance evaluation showed 74% positive patient feedback.
• Pilot studies indicated an 18% reduction in patient waiting times and a 14% increase in satisfaction.

Conclusions:

• The AI-driven HRM framework offers a robust solution for improving hospital workforce management.
• The proposed system enhances operational efficiency, staff satisfaction, and the overall quality of patient care.