Back to search

University of Southampton

Using data science to optimise nurses’ shift patterns in acute hospitals

Abstract

dc:description.abstract

In inpatient hospital wards, registered nurses are often required to work in shifts that cover the 24-hour day. While shift work has previously been linked with increased fatigue, burnout, sickness, and work-life imbalance, consensus is lacking on how to reconcile these risks with competing scheduling priorities, e.g., meeting ward demands and accommodating nurses’ working time preferences. This thesis aimed to address this gap through three interconnected studies. Study 1 involved a thematic analysis of national survey data to identify the factors nurses prioritise when choosing their working hours. Findings stressed the importance of scheduling practices that support a good work-life balance, such as ergonomic shift planning, consistent/predictable patterns, and increased control over working hours. Study 2 involved the analysis of 1.4 million historical roster records from two NHS hospital Trusts via logistic mixed regression models. Several adverse shift work variables, including long working hours, spells of consecutive working days, excessive night work, and insufficient rest periods were found to significantly increase the odds of sickness absence in both weekly and monthly exposure windows. Study 3 integrated the findings of the first two studies to develop a novel mathematical optimisation model for nurse scheduling. Across a series of experimental scenarios, the model successfully generated rosters that minimised adverse shift configurations, incorporated nurses’ general scheduling preferences, and satisfied minimum nurse staffing requirements. This research makes significant contributions to both practice and policy, providing novel insights into nurses’ working time preferences, the longitudinal effects of shift work on well-being, and innovative methods for automated rostering. This programme of work also offers a practical and adaptable methodology for prioritising nurse-centred outcomes in ward scheduling - a critical consideration given national challenges in nurse recruitment and retention.

Degree

thesis:*
Name dc:type.qualificationname
Ph.D.
Level dc:type.qualificationlevel
doctoral
Grantor dc:publisher.institution
University of Southampton
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Emmanuel, Talia
Advisors dc:contributor.advisor
  • Dall'ora, Chiara
  • Griffiths, Peter
  • Lamas Fernandez, Carlos

Rights

Language dc:language
English, eng

Chain of custody

source
Harvested from
University of Southampton
Base URL
eprints.soton.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Emmanuel, Talia. Using data science to optimise nurses’ shift patterns in acute hospitals. doctoral thesis, University of Southampton, 2025.