Abstract:

The ongoing healthcare workforce crisis, exacerbated by the Great Resignation, led to a substantial reduction in available personnel, including a 30% decline in nursing staff. This shortage can lead to longer patient wait times and compromised patient safety, contributing to more medical errors and higher mortality rates. A key factor contributing to nurse attrition is burnout, often driven by excessive administrative burdens. One effective strategy to mitigate burnout and reduce turnover is improving job satisfaction by minimizing administrative workload, thereby enabling nurses to dedicate more time to direct patient care. Additionally, high-quality patient rounding is essential for enhancing Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) scores, which assesses patient perceptions of hospital experiences. These scores inform quality improvement initiatives, promote transparency, and influence reimbursement under value-based purchasing programs.

Real-Time Location Systems (RTLS) have emerged as a transformative technology in healthcare, providing enhanced visibility and operational efficiency for both clinical and administrative workflows. By leveraging real-time location data, RTLS enables continuous monitoring of nursing staff movements, reduced response times to patient needs, and efficient personnel management.

This study examines the implementation of RTLS in a large community hospital, integrating RFID-enabled badges into nurse rounding protocols. To establish a data-driven correlation between rounding practices and patient satisfaction, a decision tree machine learning model was developed. This model generates interpretable, rule-based insights that quantify the impact of rounding on HCAHPS scores. By leveraging these insights, nursing teams enhanced the consistency and effectiveness of patient interactions, leading to measurable improvements in patient satisfaction.

This research underscores the potential of RTLS to model hospital system efficiency, automating insights to optimize resource allocation and improve patient care outcomes. By integrating real-time monitoring with predictive analytics, hospitals can enhance operational efficiency while pushing a more positive healthcare experience for both patients and staff.

Keywords: HEALTH CARE;HUMAN PERFORMANCE;MACHINE LEARNING

Menu

Shuxin Li