Estimating nurse workload: a predictive model from routine hospital data
Estimating nurse workload: a predictive model from routine hospital data
Background: managing nurse staffing is complex due to fluctuating demand based on ward occupancy, patient acuity and
dependency. Monitoring staffing adequacy in real-time has the potential to inform safe and efficient deployment of staff. Patient
classification systems are being used for per shift workload measurement, but they add a frequent administrative task for ward nursing staff.
Objective: to explore whether an algorithm could estimate ward workload using existing routinely recorded data.
Methods: anonymised admission records and assessments from a patient classification system (PCS) supporting the Safer
Nursing Care Tool (SNCT) were used to determine nursing care demand in medical and surgical wards in a single UK hospital
between Feb 2017 and Feb 2020. Records were linked by ward and time. The data was split into a training set (75%) and a test
set (25%). We built a predictive model of ward workload (as measured by the PCS) using routinely recorded administrative data and admission National Early Warning Score (NEWS). The outcome variable was ward workload derived from the patient
classifications, measured as the number of whole-time equivalent (WTE) nursing staff per patient.
Results: in a test set of 11,592 ward assessments from 42 wards with a mean WTE per patient of 1.64, the model’s mean absolute
error was 0.078, a mean percentage error of 4.9%. A Bland-Altman plot of the differences between the predicted values and the
assessment values showed 95% of them within 0.21 WTE per patient.
Conclusions: predictions of nursing workload from a relatively small number of routinely collected variables showed moderate
accuracy for general wards in one English hospital. This demonstrates the potential for automating assessments of nurse staffing requirements from routine data, reducing time spent on this non-clinical overhead and improving monitoring of real-time staffing pressures.
Workload, Staffing, Nursing Staff, Hospital, Safer Nursing Care Tool, predictive model, safer nursing care tool, nursing staff, workload, staffing
Meredith, Paul
652fc110-7cba-48c3-bfba-264c43324626
Saville, Christina
2c726abd-1604-458c-bc0b-daeef1b084bd
Dall'ora, Chiara
4501b172-005c-4fad-86da-2d63978ffdfd
Weeks, Tom
ff0a098a-d04a-40e9-9703-78b9d0f7c375
Wierzbicki, Sue
8bd073b5-3a1c-47df-93c4-f780ffae1cd3
Griffiths, Peter
ac7afec1-7d72-4b83-b016-3a43e245265b
31 July 2025
Meredith, Paul
652fc110-7cba-48c3-bfba-264c43324626
Saville, Christina
2c726abd-1604-458c-bc0b-daeef1b084bd
Dall'ora, Chiara
4501b172-005c-4fad-86da-2d63978ffdfd
Weeks, Tom
ff0a098a-d04a-40e9-9703-78b9d0f7c375
Wierzbicki, Sue
8bd073b5-3a1c-47df-93c4-f780ffae1cd3
Griffiths, Peter
ac7afec1-7d72-4b83-b016-3a43e245265b
Meredith, Paul, Saville, Christina, Dall'ora, Chiara, Weeks, Tom, Wierzbicki, Sue and Griffiths, Peter
(2025)
Estimating nurse workload: a predictive model from routine hospital data.
JMIR Medical Informatics, 13, [e71666].
(doi:10.2196/71666).
Abstract
Background: managing nurse staffing is complex due to fluctuating demand based on ward occupancy, patient acuity and
dependency. Monitoring staffing adequacy in real-time has the potential to inform safe and efficient deployment of staff. Patient
classification systems are being used for per shift workload measurement, but they add a frequent administrative task for ward nursing staff.
Objective: to explore whether an algorithm could estimate ward workload using existing routinely recorded data.
Methods: anonymised admission records and assessments from a patient classification system (PCS) supporting the Safer
Nursing Care Tool (SNCT) were used to determine nursing care demand in medical and surgical wards in a single UK hospital
between Feb 2017 and Feb 2020. Records were linked by ward and time. The data was split into a training set (75%) and a test
set (25%). We built a predictive model of ward workload (as measured by the PCS) using routinely recorded administrative data and admission National Early Warning Score (NEWS). The outcome variable was ward workload derived from the patient
classifications, measured as the number of whole-time equivalent (WTE) nursing staff per patient.
Results: in a test set of 11,592 ward assessments from 42 wards with a mean WTE per patient of 1.64, the model’s mean absolute
error was 0.078, a mean percentage error of 4.9%. A Bland-Altman plot of the differences between the predicted values and the
assessment values showed 95% of them within 0.21 WTE per patient.
Conclusions: predictions of nursing workload from a relatively small number of routinely collected variables showed moderate
accuracy for general wards in one English hospital. This demonstrates the potential for automating assessments of nurse staffing requirements from routine data, reducing time spent on this non-clinical overhead and improving monitoring of real-time staffing pressures.
Text
Predicting Nurse Workload from routine Hospital DataV10 accepted changes
- Accepted Manuscript
Text
medinform-2025-1-e71666
- Version of Record
More information
Accepted/In Press date: 17 June 2025
e-pub ahead of print date: 24 June 2025
Published date: 31 July 2025
Additional Information:
For the purpose of open access, the author has applied a CC BY public copyright license to any author accepted manuscript version
arising from this submission.
Keywords:
Workload, Staffing, Nursing Staff, Hospital, Safer Nursing Care Tool, predictive model, safer nursing care tool, nursing staff, workload, staffing
Identifiers
Local EPrints ID: 503454
URI: http://eprints.soton.ac.uk/id/eprint/503454
ISSN: 2291-9694
PURE UUID: 12ea9cf7-bb36-4a9e-89a3-4bd23bf243c8
Catalogue record
Date deposited: 01 Aug 2025 16:34
Last modified: 26 Sep 2025 02:08
Export record
Altmetrics
Contributors
Author:
Paul Meredith
Author:
Tom Weeks
Author:
Sue Wierzbicki
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics