Predicting Nurse Staffing Requirements From Routinely Collected Data

NCT06923943 | Active Not Recruiting

• 3 other identifiers: 100780NIHR166784346148
• Study Type: observational
• Target: 80
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to find out if the researchers can predict the number of nurses needed on hospital wards (units) from patient hospital data. The main question it aims to answer is: Is it possible to predict nurse staffing requirements from routinely recorded data in hospital systems? Researchers will ask nurses about their views of nurse staffing tools and what support they need for staffing decisions. They will analyse data from hospital IT systems.

Conditions

Nursing Workload

Keywords

nurse staffing; workload; prediction; workforce; safety

Outcome Measures

Primary Outcomes (1)

• Mean absolute error of prediction

  measured in whole-time-equivalents per patient. This is a measure of predictive accuracy, i.e. how well the algorithm's predictions match the target value for required nurse staffing on average across wards and shifts.

  For each 12-hour shift

Secondary Outcomes (5)

• mortality

  within 30 days of patient admission

• length of stay

  from hospital admission until discharge

• readmission

  within 30 days of hospital admission

• healthcare-associated conditions

  from hospital admission until discharge

• were the nursing staff on duty appropriate to meet patient care needs

  for each 8- or 12-hour shift

Study Arms (2)

National survey

We will survey staffing matrons and Chief Nursing Information Officers in England to find out how staffing tools are used and the availability/quality of patient data in IT systems.

Workshops

In workshops we will 1) ask nurses and managers what problems they have with current staffing systems and what would help, 2) discuss with nurses, NHS IT managers and IT system providers ideas for building our prediction algorithms into software products.

Eligibility Criteria

• Sex: all
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

English NHS acute hospital Trusts

You may qualify if:

• safe staffing lead/nurse with responsibility for safe staffing or CNIO/nurse with responsibility for IT/electronic records
• nursing manager with safe staffing remit/IT remit. OR
• clinical nurse with experience of completing Safer Nursing Care Tool ratings. OR
• NHS IT manager with familiarity of hospital Trust's systems for storing patient data. OR
• representative of company who provide rostering or patient information system services to hospitals.

Sponsors & Collaborators

• University of Southampton: lead
• Imperial College London: collaborator
• Imperial College Healthcare NHS Trust: collaborator
• Portsmouth Hospitals NHS Trust: collaborator
• NHS England: collaborator
• Guy's and St Thomas' NHS Foundation Trust: collaborator

Study Sites (1)

University of Southampton

Southampton, United Kingdom

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Dr.

Study Record Dates

• First Submitted: March 27, 2025
• First Posted: April 11, 2025
• Study Start: November 1, 2025
• Primary Completion (Estimated): July 31, 2026
• Study Completion (Estimated): July 31, 2026
• Last Updated: February 27, 2026

Record last verified: 2026-02

Data Sharing

• IPD Sharing: Will not share

Locations

GB (1)