The University of Southampton
University of Southampton Institutional Repository

Health care professionals' perceptions of machine learning based clinical decision support systems for oesophageal cancer management

Health care professionals' perceptions of machine learning based clinical decision support systems for oesophageal cancer management
Health care professionals' perceptions of machine learning based clinical decision support systems for oesophageal cancer management
Oesophageal cancer (OC) causes significant morbidity and mortality. Multiple treatment regimens are available, and multidisciplinary team (MDT) decisions over which to offer are complex, multi-faceted and subject to logistical constraints and human factors. A machine learning (ML) model-based clinical decision support system (CDSS) for OC has been developed, trained on historical treatment decisions. However, clinician trust in such systems is not yet established. This study surveyed clinicians in OC MDTs in the UK and Ireland to investigate which clinical and sociodemographic factors influence conscious decision-making in OC, comparing their relative subjective importance to those derived from the ML model (reflecting previous real-world practice). It also sought to explore clinicians' views on the potential use of artificial intelligence-based CDSSs in OC. There was agreement between clinicians and the model in many of the most influential factors in decision making, although age and gender had greater influence on the model than their conscious importance to clinicians would support. Clinicians identified a wide range of additional clinical and holistic factors outside the current model which factor into their decision-making, including further investigations, symptoms, nutrition and social factors. The prospect of utilising an ML CDSS in future received generally positive feedback, although opinions varied widely. However, barriers to implementation were identified, including concerns around perceived clinician superiority over ML CDSSs, patient individuality, transparency and safeguarding, the need for evidence, and additional input requirements. As ML CDSSs are increasingly offered in practice, clinicians' reservations must be addressed and their need for transparency and evidence met.
“Artificial intelligence”, “Clinical decision support system”, “Machine learning”, “Multidisciplinary team”, “Oesophageal cancer”
0010-4825
Webb, Catherine
Thavanesan, Navamayooran
94f0a216-9131-431b-809c-f5a83146343d
Naiseh, Mohammad
Dewar-Haggart, Rachel
Underwood, Tim
8e81bf60-edd2-4b0e-8324-3068c95ea1c6
Vigneswaran, Ganesh
4e3865ad-1a15-4a27-b810-55348e7baceb
Webb, Catherine
Thavanesan, Navamayooran
94f0a216-9131-431b-809c-f5a83146343d
Naiseh, Mohammad
Dewar-Haggart, Rachel
Underwood, Tim
8e81bf60-edd2-4b0e-8324-3068c95ea1c6
Vigneswaran, Ganesh
4e3865ad-1a15-4a27-b810-55348e7baceb

Webb, Catherine, Thavanesan, Navamayooran, Naiseh, Mohammad, Dewar-Haggart, Rachel, Underwood, Tim and Vigneswaran, Ganesh (2026) Health care professionals' perceptions of machine learning based clinical decision support systems for oesophageal cancer management. Computers in Biology and Medicine, 200, [111373]. (doi:10.1016/j.compbiomed.2025.111373).

Record type: Article

Abstract

Oesophageal cancer (OC) causes significant morbidity and mortality. Multiple treatment regimens are available, and multidisciplinary team (MDT) decisions over which to offer are complex, multi-faceted and subject to logistical constraints and human factors. A machine learning (ML) model-based clinical decision support system (CDSS) for OC has been developed, trained on historical treatment decisions. However, clinician trust in such systems is not yet established. This study surveyed clinicians in OC MDTs in the UK and Ireland to investigate which clinical and sociodemographic factors influence conscious decision-making in OC, comparing their relative subjective importance to those derived from the ML model (reflecting previous real-world practice). It also sought to explore clinicians' views on the potential use of artificial intelligence-based CDSSs in OC. There was agreement between clinicians and the model in many of the most influential factors in decision making, although age and gender had greater influence on the model than their conscious importance to clinicians would support. Clinicians identified a wide range of additional clinical and holistic factors outside the current model which factor into their decision-making, including further investigations, symptoms, nutrition and social factors. The prospect of utilising an ML CDSS in future received generally positive feedback, although opinions varied widely. However, barriers to implementation were identified, including concerns around perceived clinician superiority over ML CDSSs, patient individuality, transparency and safeguarding, the need for evidence, and additional input requirements. As ML CDSSs are increasingly offered in practice, clinicians' reservations must be addressed and their need for transparency and evidence met.

Text
1-s2.0-S0010482525017275-main - Version of Record
Available under License Creative Commons Attribution.
Download (4MB)

More information

Accepted/In Press date: 3 December 2025
e-pub ahead of print date: 10 December 2025
Published date: 1 January 2026
Keywords: “Artificial intelligence”, “Clinical decision support system”, “Machine learning”, “Multidisciplinary team”, “Oesophageal cancer”

Identifiers

Local EPrints ID: 508987
URI: http://eprints.soton.ac.uk/id/eprint/508987
ISSN: 0010-4825
PURE UUID: 4949d052-3adf-4d4f-9146-4cd7685a6c11
ORCID for Navamayooran Thavanesan: ORCID iD orcid.org/0000-0002-7127-9606
ORCID for Tim Underwood: ORCID iD orcid.org/0000-0001-9455-2188
ORCID for Ganesh Vigneswaran: ORCID iD orcid.org/0000-0002-4115-428X

Catalogue record

Date deposited: 09 Feb 2026 17:56
Last modified: 10 Feb 2026 03:13

Export record

Altmetrics

Contributors

Author: Catherine Webb
Author: Navamayooran Thavanesan ORCID iD
Author: Mohammad Naiseh
Author: Rachel Dewar-Haggart
Author: Tim Underwood ORCID iD

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

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×