Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance
dc.contributor.author | Thomas, L | |
dc.contributor.author | Hyde, C | |
dc.contributor.author | Mullarkey, D | |
dc.contributor.author | Greenhalgh, J | |
dc.contributor.author | Kalsi, D | |
dc.contributor.author | Ko, J | |
dc.date.accessioned | 2024-02-05T12:01:21Z | |
dc.date.issued | 2023-10-31 | |
dc.date.updated | 2024-02-05T09:57:19Z | |
dc.description.abstract | INTRODUCTION: Deep Ensemble for Recognition of Malignancy (DERM) is an artificial intelligence as a medical device (AIaMD) tool for skin lesion assessment. METHODS: We report prospective real-world performance from its deployment within skin cancer pathways at two National Health Service hospitals (UK) between July 2021 and October 2022. RESULTS: A total of 14,500 cases were seen, including patients 18-100 years old with Fitzpatrick skin types I-VI represented. Based on 8,571 lesions assessed by DERM with confirmed outcomes, versions A and B demonstrated very high sensitivity for detecting melanoma (95.0-100.0%) or malignancy (96.0-100.0%). Benign lesion specificity was 40.7-49.4% (DERM-vA) and 70.1-73.4% (DERM-vB). DERM identified 15.0-31.0% of cases as eligible for discharge. DISCUSSION: We show DERM performance in-line with sensitivity targets and pre-marketing authorisation research, and it reduced the caseload for hospital specialists in two pathways. Based on our experience we offer suggestions on key elements of post-market surveillance for AIaMDs. | en_GB |
dc.format.extent | 1264846- | |
dc.format.medium | Electronic-eCollection | |
dc.identifier.citation | Vol. 10, article 1264846 | en_GB |
dc.identifier.doi | https://doi.org/10.3389/fmed.2023.1264846 | |
dc.identifier.uri | http://hdl.handle.net/10871/135243 | |
dc.identifier | ORCID: 0000-0002-7349-0616 (Hyde, Chris) | |
dc.identifier | ScopusID: 57055205300 | 7005161276 (Hyde, Chris) | |
dc.language.iso | en | en_GB |
dc.publisher | Frontiers Media | en_GB |
dc.relation.url | https://www.ncbi.nlm.nih.gov/pubmed/38020164 | en_GB |
dc.rights | © 2023 Thomas, Hyde, Mullarkey, Greenhalgh, Kalsi and Ko. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. | en_GB |
dc.subject | AI as a medical device | en_GB |
dc.subject | AI for skin cancer | en_GB |
dc.subject | DERM | en_GB |
dc.subject | Skin Analytics | en_GB |
dc.subject | artificial intelligence | en_GB |
dc.subject | deep ensemble for the recognition of malignancy | en_GB |
dc.subject | skin cancer | en_GB |
dc.title | Real-world post-deployment performance of a novel machine learning-based digital health technology for skin lesion assessment and suggestions for post-market surveillance | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2024-02-05T12:01:21Z | |
dc.identifier.issn | 2296-858X | |
exeter.place-of-publication | Switzerland | |
dc.description | This is the final version. Available on open access from Frontiers Media via the DOI in this record | en_GB |
dc.description | Data availability statement: The datasets presented in this article are not readily available because the data included in this manuscript have been collected as part of the routine post-market surveillance programme for DERM, conducted by Skin Analytics, London. Requests to access the datasets should be directed to DK, dilraj@skinanalytics.co.uk and DM, dan@skinanalytics.co.uk. | en_GB |
dc.identifier.eissn | 2296-858X | |
dc.identifier.journal | Frontiers in Medicine | en_GB |
dc.relation.ispartof | Front Med (Lausanne), 10 | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_GB |
dcterms.dateAccepted | 2023-10-10 | |
dc.rights.license | CC BY | |
rioxxterms.version | VoR | en_GB |
rioxxterms.licenseref.startdate | 2023-10-31 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2024-02-05T11:59:27Z | |
refterms.versionFCD | VoR | |
refterms.dateFOA | 2024-02-05T12:01:37Z | |
refterms.panel | A | en_GB |
refterms.dateFirstOnline | 2023-10-31 |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © 2023 Thomas, Hyde, Mullarkey, Greenhalgh, Kalsi and Ko. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.