Minimum labelling requirements for dermatology artificial intelligence-based Software as Medical Device (SaMD): A consensus statement

Åsa Ingvar; Ayooluwatomiwa Oloruntoba; Maithili Sashindranath; Robert Miller; H Peter Soyer; Pascale Guitera; Tony Caccetta; Stephen Shumack; Lisa Abbott; Chris Arnold; Craig Lawn; Alison Button-Sloan; Monika Janda; Victoria Mar

doi:10.1111/ajd.14222

Minimum labelling requirements for dermatology artificial intelligence-based Software as Medical Device (SaMD): A consensus statement

Australas J Dermatol. 2024 May;65(3):e21-e29. doi: 10.1111/ajd.14222. Epub 2024 Feb 28.

Authors

Åsa Ingvar^{1

2

3

4}, Ayooluwatomiwa Oloruntoba², Maithili Sashindranath², Robert Miller⁵, H Peter Soyer^{5

6}, Pascale Guitera^{5

7

8

9}, Tony Caccetta^{5

10}, Stephen Shumack^{5

11}, Lisa Abbott^{5

7

12}, Chris Arnold^{13

14

15}, Craig Lawn^{9

16}, Alison Button-Sloan¹⁷, Monika Janda^{5

6

18}, Victoria Mar^{1

2

5}

Affiliations

¹ Victorian Melanoma Service, Alfred Health, Melbourne, Victoria, Australia.
² School of Public Health and Preventive Medicine, Monash University, Melbourne, Victoria, Australia.
³ Department of Dermatology, Skåne University Hospital, Lund, Sweden.
⁴ Department of Clinical Sciences, Lund University, Lund, Sweden.
⁵ Australasian College of Dermatologists, Sydney, Australia.
⁶ Dermatology Research Centre, Frazer Institute, The University of Queensland, Brisbane, Queensland, Australia.
⁷ Faculty of Medicine and Health, The University of Sydney, Sydney, New South Wales, Australia.
⁸ Sydney Melanoma Diagnostic Centre, Royal Prince Alfred Hospital, Camperdown, Victoria, Australia.
⁹ Melanoma Institute Australia, The University of Sydney, Sydney, New South Wales, Australia.
¹⁰ Perth Dermatology Clinic, Perth, Western Australia, Australia.
¹¹ Royal North Shore Hospital of Sydney, Sydney, New South Wales, Australia.
¹² The Skin Hospital, Sydney, New South Wales, Australia.
¹³ BioGrid Australia Ltd, Melbourne, Australia.
¹⁴ Hodgson Associates, Melbourne, Australia.
¹⁵ Australasian Society of Cosmetic Dermatologists, Melbourne, Australia.
¹⁶ Centre of Excellence in Melanoma Imaging, Brisbane, Queensland, Australia.
¹⁷ Australian Melanoma Consumer Alliance, Melbourne, Victoria, Australia.
¹⁸ Centre for Health Services Research, The University of Queensland, Brisbane, Queensland, Australia.

PMID: 38419186
DOI: 10.1111/ajd.14222

Abstract

Background/objectives: Artificial intelligence (AI) holds remarkable potential to improve care delivery in dermatology. End users (health professionals and general public) of AI-based Software as Medical Devices (SaMD) require relevant labelling information to ensure that these devices can be used appropriately. Currently, there are no clear minimum labelling requirements for dermatology AI-based SaMDs.

Methods: Common labelling recommendations for AI-based SaMD identified in a recent literature review were evaluated by an Australian expert panel in digital health and dermatology via a modified Delphi consensus process. A nine-point Likert scale was used to indicate importance of 10 items, and voting was conducted to determine the specific characteristics to include for some items. Consensus was achieved when more than 75% of the experts agreed that inclusion of information was necessary.

Results: There was robust consensus supporting inclusion of all proposed items as minimum labelling requirements; indication for use, intended user, training and test data sets, algorithm design, image processing techniques, clinical validation, performance metrics, limitations, updates and adverse events. Nearly all suggested characteristics of the labelling items received endorsement, except for some characteristics related to performance metrics. Moreover, there was consensus that uniform labelling criteria should apply across all AI categories and risk classes set out by the Therapeutic Goods Administration.

Conclusions: This study provides critical evidence for setting labelling standards by the Therapeutic Goods Administration to safeguard patients, health professionals, consumers, industry, and regulatory bodies from AI-based dermatology SaMDs that do not currently provide adequate information about how they were developed and tested.

Keywords: Delphi consensus; artificial intelligence; dermatology; labelling; medical device.

MeSH terms

Artificial Intelligence*
Australia
Consensus*
Delphi Technique
Dermatology* / standards
Humans
Product Labeling* / standards
Software*

Abstract

MeSH terms

Grants and funding