Review
. 2024 Feb;6(2):e131-e144.
doi: 10.1016/S2589-7500(23)00241-8.
Affiliations
Item in Clipboard
Review
Lancet Digit Health.
2024 Feb.
Abstract
Machine learning (ML)-based risk prediction models hold the potential to support the health-care setting in several ways; however, use of such models is scarce. We aimed to review health-care professional (HCP) and patient perceptions of ML risk prediction models in published literature, to inform future risk prediction model development. Following database and citation searches, we identified 41 articles suitable for inclusion. Article quality varied with qualitative studies performing strongest. Overall, perceptions of ML risk prediction models were positive. HCPs and patients considered that models have the potential to add benefit in the health-care setting. However, reservations remain; for example, concerns regarding data quality for model development and fears of unintended consequences following ML model use. We identified that public views regarding these models might be more negative than HCPs and that concerns (eg, extra demands on workload) were not always borne out in practice. Conclusions are tempered by the low number of patient and public studies, the absence of participant ethnic diversity, and variation in article quality. We identified gaps in knowledge (particularly views from under-represented groups) and optimum methods for model explanation and alerts, which require future research.
Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.
Conflict of interest statement
Declaration of interests RG is funded by the National Institute for Health and Care Research (NIHR) for this study (NIHR302604). TC is a co-founder of and owns stock in Mortimer Health and is supported by the Wellcome Trust via a Wellcome Clinical PhD Training Fellowship (REF 22890/Z/21/Z). SMJ is supported by Cancer Research UK (CRUK; EDDCPGM\100002) and Medical Research Council (MRC; MR/W025051/1) programme grants; received fees for advisory board membership in the last three years from Bard1 Lifescience; received grant income from Owlstone and GRAIL; is an unpaid member of a GRAIL advisory board; has received lecture fees for academic meetings from Cheisi and AstraZeneca; and receives support from the CRUK Lung Cancer Centre and the CRUK City of London Centre, the Rosetrees Trust, the Roy Castle Lung Cancer foundation, the Longfonds BREATH Consortia, MRC UKRMP2 Consortia, the Garfield Weston Trust, and University College London (UCL) Hospitals Charitable Foundation where this work was partly undertaken and who also received a proportion of funding from the Department of Health’s NIHR Biomedical Research Centre’s funding scheme. SMJ’s wife works for AstraZeneca. MvdS is a Director at the Cambridge Centre for AI in Medicine, which receives funding from AstraZeneca and GSK. JS is funded by NIHR Applied Research Collaboration North Thames, NIHR (policy research programme, programme grant, health service and delivery grant, and capacity building funding), and the UK Prevention Research Partnership. NN is supported by an MRC Clinical Academic Research Partnership (MR/T02481X/1); received a grant from the CRUK early diagnosis grant for the Real-time cancer analytics (REACT) study (EICEDAAP\100012); reports honoraria for non-promotional educational talks or advisory boards from Amgen, AstraZeneca, Boehringer ingelheim, Bristol Myers Squibb, EQRx, Fujifilm, Guardant Health, Intuitive, Janssen, Lilly, MSD, Olympus, OncLive, PeerVoice, Pfizer, Roche, and Takeda outside of the current work; holds positions as the Director of UK Lung cancer coalition, member of the Steering Committee of British Thoracic Oncology Group, and Clinical Director of National Lung Cancer Audit; and reports stock and stock options in OneWelbeck, The Physicians’ Clinic (HCA), and Pharmacierge. AJ declares no competing interests. The views expressed in this publication are those of the authors and not necessarily those of the NIHR, National Health Service, or the UK Department of Health and Social Care.
