Quantitative Insights From Nursing Workload Measurement: An Artificial Intelligence-Driven Approach

Area of Science:

• Health Informatics
• Nursing Informatics
• Data Science in Healthcare

Background:

• Military nurses experience unique challenges, including high workloads due to staffing shortages.
• Quantifying nurse workload objectively is difficult.
• Electronic health record (EHR) audit logs offer a promising method for unobtrusive measurement of clinician work.

Purpose of the Study:

• To explore the utility of EHR audit log data for understanding nursing activities and workload.
• To develop a framework for automated, AI-driven workload monitoring in nursing.
• To assess the potential for predictive modeling in forecasting nurse burnout.

Main Methods:

• Extracted five years of EHR audit log data from an academic medical center for nurse users.
• Applied temporal mining techniques to analyze nursing workflows and EHR interaction patterns.
• Explored predictive modeling for workload variation assessment and burnout risk forecasting.

Main Results:

• Analyzed data from 8,149 unique nurse users logging 1,461 distinct EHR activities.
• Identified that many tasks involved viewing or searching EHR data.
• Developed the Predictive Optimization of Workload and Efficiency for RNs (POWER) framework for automated AI-driven workload monitoring.

Conclusions:

• EHR audit log data provides a scalable and objective method for nursing workload analysis.
• The methodology demonstrates a generalizable approach for leveraging audit logs.
• Future work includes validation in military settings and developing AI-driven decision support for workforce management.