JMIR Publications

ABSTRACT

Background:

Nursing care is a critical determinant of patient outcomes in the intensive care unit (ICU). Most studies of nursing care have focused on nursing characteristics averaged across the ICU (e.g., unit-wide nurse-to-patient ratios, education, and working environment). In contrast, relatively little work has focused on the influence of individual nurses on patient outcomes. Such research could provide granular insight into how nurse staffing patterns affect the quality of care, opening new avenues for performance improvement. Research in this area is hindered by an inability to link individual nurses to specific patients retrospectively and at scale.

Objective:

This study aimed to use electronic signatures in the electronic health record (EHR) as nurses perform their daily activities to retrospectively link individual nurses to specific patients during a shift.

Methods:

We used EHR data from 38 ICUs in 18 hospitals from 2018 to 2020. We abstracted data on the time and frequency of nurse charting of clinical assessments and medication administration, and then used those data to iteratively develop an algorithm to identify a single ICU nurse for each patient-shift. We examined the accuracy and precision of the algorithm by performing manual chart review on a randomly selected subset of patient-shifts.

Results:

The analytic data set contained 5,479,034 unique nurse-patient charting times, 748,771 patient-shifts, 87,466 hospitalizations, 70,002 patients, and 8,134 individual nurses. The final algorithm identified a single nurse for 97.3% of patient-shifts. In the remaining 2.7% of patient-shifts, the algorithm either identified multiple nurses (0.6%), no nurse (2.0%), or the same nurse as the prior shift (0.1%). In 200 patient-shifts selected for chart review, the algorithm had an accuracy (correctly identifying the primary nurse or correctly identifying that there was no primary nurse) of 93.0% and a precision (correctly identifying the primary nurse when a primary nurse was identified) of 94.4%. Misclassification was most frequently due to patient transitions in care location such as ICU transfers, discharges, and admissions.

Conclusions:

Meta-data from the EHR can accurately identify individual nurse-patient assignments in the ICU. This approach could form the basis of granular studies of ICU nurse staffing, leading to improved understanding of the relationship between nurse staffing and patient outcomes.