Related Experiment Video
Updated: Jul 10, 2026
Radiation Planning Assistant - A Streamlined, Fully Automated Radiotherapy Treatment Planning System
Published on: April 11, 2018
'You make the call': Improving radiology staff scheduling with AI-generated self-rostering in a medical imaging
K O'Callahan1, S Sitters1, M Petersen1
1Department of Medical Imaging, Unitec Institute of Technology, 5-7 Ratanui St, Henderson, Auckland, New Zealand.
Introduction:
New Zealand's shortage of medical imaging technicians has intensified due to factors like illness, the pandemic, and an ageing workforce. Addressing staff retention issues requires attention to intrinsic factors like workplace satisfaction and work-life balance. Self-rostering has proven effective in healthcare by enhancing work-life balance, job satisfaction, and retention, but it has not been implemented widely in radiology. This study aimed to explore the perceptions, benefits, and challenges of implementing AI-generated self-rostering in a radiology department through simulated trials.
Methods:
This study simulated an AI-generated roster in a regional New Zealand radiology department, engaging 23 staff members. A mixed-methods approach included surveys and discussion groups. Community-based participatory action methodology guided discussion groups and informed modifications.
Results:
The AI-generated self-rostering method demonstrated success by meeting a high percentage of shift preferences while fulfilling service demands. Participants perceived potential benefits in work-life balance and autonomy, though uncertainties persisted regarding implementation and fairness. Despite staff reservations, we found that an AI-generated self-rostering system may be fairer than manual self-rostering, while saving radiology staff time and cost.
Conclusion:
AI-generated self-rostering offers an innovative solution to an old problem. This self-rostering system provides a fair way for staff to have a say in the shifts they do, which increases feelings of work-life balance and autonomy. In this simulation, AI-generated self-rostering was well received, and most staff were receptive to moving to pilot the programme.
Implications For Practice:
Self-rostering could be a potential solution to staff retention issues in radiology; we recommend a pilot study is implemented. When switching to self-rostering, departments should consider implementing one-on-one support systems to assist staff with entering preferences. Education is essential to encourage staff understanding and cooperation.
More Related Videos
07:57Positron Emission Tomography-based Dose Painting Radiation Therapy in a Glioblastoma Rat Model using the Small Animal Radiation Research Platform
Published on: March 24, 2022
05:18Author Spotlight: Improving Radiation Therapy Access with Radiation Planning Assistant
Published on: October 6, 2023
