Clinicians must participate in the development of multimodal AI

Summary: Multimodal artificial intelligence (AI) is a powerful new technological advance, capable of simultaneously learning from diverse data types, such as text, images, video, and audio. Because clinical decisions are usually based on information from multiple sources, multimodal AI has the poten...

Full description

Saved in:
Bibliographic Details
Main Authors: Christopher R.S. Banerji, Aroon Bhardwaj Shah, Ben Dabson, Tapabrata Chakraborti, Vicky Hellon, Chris Harbron, Ben D. MacArthur
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:EClinicalMedicine
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589537025001841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850270961892327424
author Christopher R.S. Banerji
Aroon Bhardwaj Shah
Ben Dabson
Tapabrata Chakraborti
Vicky Hellon
Chris Harbron
Ben D. MacArthur
author_facet Christopher R.S. Banerji
Aroon Bhardwaj Shah
Ben Dabson
Tapabrata Chakraborti
Vicky Hellon
Chris Harbron
Ben D. MacArthur
author_sort Christopher R.S. Banerji
collection DOAJ
description Summary: Multimodal artificial intelligence (AI) is a powerful new technological advance, capable of simultaneously learning from diverse data types, such as text, images, video, and audio. Because clinical decisions are usually based on information from multiple sources, multimodal AI has the potential to significantly improve clinical practice. However, unlike most developed multimodal AI workflows, clinical medicine is both a dynamic and interventional process in which the clinician continually learns about the patient's health and acts accordingly as data is collected. In this article we argue that multimodal clinical AI must be fully attuned to the particular challenges and constraints of the clinic, and clinician involvement is needed throughout development—not just at clinical deployment. We propose ways that clinician involvement can add value at each stage of the multimodal AI development pipeline, and argue for the establishment of actively managed multidisciplinary communities to work collaboratively towards the shared goal of improving the health of all.
format Article
id doaj-art-2b4ee7714a044f83b9917d99d0e4da16
institution OA Journals
issn 2589-5370
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series EClinicalMedicine
spelling doaj-art-2b4ee7714a044f83b9917d99d0e4da162025-08-20T01:52:23ZengElsevierEClinicalMedicine2589-53702025-06-018410325210.1016/j.eclinm.2025.103252Clinicians must participate in the development of multimodal AIChristopher R.S. Banerji0Aroon Bhardwaj Shah1Ben Dabson2Tapabrata Chakraborti3Vicky Hellon4Chris Harbron5Ben D. MacArthur6The Alan Turing Institute, London, UK; University College London Hospital, University College London Hospitals NHS Trust, London, UK; UCL Cancer Institute, Faculty of Medical Sciences, University College London, London, UK; King's Comprehensive Cancer Centre, King's College London, London, UK; Corresponding author. The Alan Turing Institute, London, UK.Whittington Hospital, Whittington Health NHS Trust, London, UKHammersmith Hospital, Imperial College London NHS Trust, London, UKThe Alan Turing Institute, London, UK; UCL Cancer Institute, Faculty of Medical Sciences, University College London, London, UKThe Alan Turing Institute, London, UKRoche Pharmaceuticals, Welwyn Garden City, UKThe Alan Turing Institute, London, UK; Faculty of Medicine, University of Southampton, Southampton, UK; Mathematical Sciences, University of Southampton, Southampton, UK; Corresponding author. The Alan Turing Institute, London, UK.Summary: Multimodal artificial intelligence (AI) is a powerful new technological advance, capable of simultaneously learning from diverse data types, such as text, images, video, and audio. Because clinical decisions are usually based on information from multiple sources, multimodal AI has the potential to significantly improve clinical practice. However, unlike most developed multimodal AI workflows, clinical medicine is both a dynamic and interventional process in which the clinician continually learns about the patient's health and acts accordingly as data is collected. In this article we argue that multimodal clinical AI must be fully attuned to the particular challenges and constraints of the clinic, and clinician involvement is needed throughout development—not just at clinical deployment. We propose ways that clinician involvement can add value at each stage of the multimodal AI development pipeline, and argue for the establishment of actively managed multidisciplinary communities to work collaboratively towards the shared goal of improving the health of all.http://www.sciencedirect.com/science/article/pii/S2589537025001841Multimodal AIHuman-in-the-loop AIHealth policyCommunity managementClinical AI
spellingShingle Christopher R.S. Banerji
Aroon Bhardwaj Shah
Ben Dabson
Tapabrata Chakraborti
Vicky Hellon
Chris Harbron
Ben D. MacArthur
Clinicians must participate in the development of multimodal AI
EClinicalMedicine
Multimodal AI
Human-in-the-loop AI
Health policy
Community management
Clinical AI
title Clinicians must participate in the development of multimodal AI
title_full Clinicians must participate in the development of multimodal AI
title_fullStr Clinicians must participate in the development of multimodal AI
title_full_unstemmed Clinicians must participate in the development of multimodal AI
title_short Clinicians must participate in the development of multimodal AI
title_sort clinicians must participate in the development of multimodal ai
topic Multimodal AI
Human-in-the-loop AI
Health policy
Community management
Clinical AI
url http://www.sciencedirect.com/science/article/pii/S2589537025001841
work_keys_str_mv AT christopherrsbanerji cliniciansmustparticipateinthedevelopmentofmultimodalai
AT aroonbhardwajshah cliniciansmustparticipateinthedevelopmentofmultimodalai
AT bendabson cliniciansmustparticipateinthedevelopmentofmultimodalai
AT tapabratachakraborti cliniciansmustparticipateinthedevelopmentofmultimodalai
AT vickyhellon cliniciansmustparticipateinthedevelopmentofmultimodalai
AT chrisharbron cliniciansmustparticipateinthedevelopmentofmultimodalai
AT bendmacarthur cliniciansmustparticipateinthedevelopmentofmultimodalai