Visualizing and Optimizing Operating Room Nurses’ Workload Using Generative AI: A Cross-Sectional Study

Description:
This dataset contains raw data collected for a cross-sectional study on the workload of operating room nurses at a tertiary care hospital in Japan (Nagasaki Medical Center). The survey quantified the time allocation of perioperative nurses during different shifts (weekday daytime, weekday nighttime, weekend/holiday shifts), covering both nursing tasks (e.g., direct patient care, preparation, intraoperative support) and non-nursing tasks (e.g., documentation, supply management, administrative work).

The dataset was obtained through a structured workload survey and time-motion style observational records between 2023 and 2024. It includes aggregated time distribution across task categories, shift type, and nurse demographics. The data were used for analysis in the manuscript “Visualizing and Optimizing Operating Room Nurses’ Workload Using Generative AI: A Cross-Sectional Study”.

File contents:

Excel spreadsheets summarizing observed task times by category and shift.

Supplementary tables for task classification (nursing vs. non-nursing).

Anonymized records ensuring no individual nurse identifiers are present.

Ethics:
The study was approved by the Ethics Committee of Kumamoto University (Approval No. 2024015). Participation was voluntary, and all participants provided informed consent.

Potential use:
The dataset can support further research in:

Nursing workload measurement and benchmarking.

Workforce planning and staffing optimization in perioperative settings.

Application of AI and digital tools for task visualization and efficiency improvement.

Limitations:
The dataset is from a single institution and may not be generalizable to all healthcare contexts. Task classification reflects the local practice environment.