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

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.

Consumer views of melanoma early detection using 3D total-body photography: cross-sectional survey.

BACKGROUND: Three-dimensional (3D) total-body photography is a recent advance in melanoma early detection that can aid in monitoring and identifying new and changing skin lesions over time. METHODS: A cross-sectional survey of adults living in metropolitan and rural areas of Australia was conducted to assess perceptions of 3D total-body photography. Participants completed a survey detailing their previous use of skin cancer photography, personal skin checking history, perceptions of 3D total-body photography, and willingness to pay. Participants were also asked to describe the potential barriers and facilitators of 3D total-body photography in their own words. RESULTS: A total of 1056 participants completed the survey, with 739 (70%) from metropolitan areas of Australia and 317 (30%) from rural areas. Most participants (95%, n = 1004/1056) indicated they would consider using 3D total-body photography if it became commercially available at their regular medical practice. Most participants indicated 3D total-body photography would be effective to identify suspicious skin spots (94%, n = 995/1056), monitor lesion changes (94%, n = 997/1056), and reduce skin cancer related anxiety (90%, n = 950/1055). In open-ended feedback, participants (87%, n = 918/1056) identified perceived benefits, including more comprehensive screenings, earlier detection, and less human error. Participants (84%, n = 889/1056) also identified potential barriers to 3D total-body photography, including cost, accessibility and availability, trust in the technology, and digital security concerns. CONCLUSIONS: Participant feedback indicated a high level of acceptance and confidence in the technology. To facilitate clinical translation, addressing consumer-identified barriers to 3D total-body photography will be vital.

Embedding electronic patient-reported outcome measures into routine care for patients with stage III MELanoma (ePROMs-MEL): protocol for a prospective, longitudinal, mixed-methods pilot study.

INTRODUCTION: The benefits of patient-reported feedback, using questionnaires that allow patients to report how they feel and function without any interpretation from healthcare professionals, are well established. However, patient-reported outcomes measures (PROMs) are not routinely collected in patients with melanoma in Australia. The aim of this study is to evaluate the feasibility and acceptability of implementing electronic PROMs (ePROMs) into routine care from the perspectives of patients with stage III melanoma and their treating clinical team. METHODS AND ANALYSIS: A minimum of 50 patients and 5 clinicians will be recruited to this prospective, longitudinal pilot study (ePROMs-MELanoma). The study uses a mixed-methods approach (quantitative PROMs questionnaires and end-of-study surveys with qualitative interviews) and commenced in May 2021 in surgical and medical melanoma clinics at two sites in metropolitan Sydney, Australia. The primary outcomes are measures of feasibility and acceptability, comprising descriptive questionnaire completion statistics, and proportion of patients who reported that these PROMs were easy to complete and measured items they considered important. Clinician and clinic staff views will be canvassed on the appropriateness of these PROMs for their patients, change in referral practice and uptake and incorporation into routine practice. Secondary aims include measurement of improvements in patients' emotional and physical health and well-being, and utility of real-time data capture and clinician feedback. All participants will complete the Distress Thermometer and EQ-5D-5L questionnaires in the clinic using a tablet computer at baseline and two to three subsequent follow-up appointments. Participants who report a score of 4 or higher on the Distress Thermometer will be triaged to complete an additional three questionnaires: the QLQ-C30, Depression, Anxiety and Stress Scale and Melanoma Concerns Questionnaire-28. Results will be generated in real time; patients with psychosocial distress or poor quality of life will discuss possible referral to appropriate allied health services with their clinician. Thematic analysis of interviews will be conducted. ETHICS AND DISSEMINATION: Ethics approval obtained from St Vincent's Hospital Human Research Ethics Committee on 19 September 2019 (2019/ETH10558), with amendments approved on 8 June 2022. Patient consent is obtained electronically prior to questionnaire commencement. Dissemination strategies will include publication in peer-reviewed journals and presentation at international conferences, tailored presentations for clinical societies and government bodies, organisational reporting through multidisciplinary meetings and research symposia for local clinicians and clinic staff, and more informal, lay reports and presentations for consumer melanoma representative bodies and patient participants and their families. TRIAL REGISTRATION NUMBER: ACTRN12620001149954.