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.

Development of melanoma clinical quality indicators for the Australian melanoma clinical outcomes registry (MelCOR): A modified Delphi study.

BACKGROUND: Clinical quality registries aim to identify significant variations in care and provide anonymised feedback to institutions to improve patient outcomes. Thirty-six Australian organisations with an interest in melanoma, raised funds through three consecutive Melanoma Marches, organised by Melanoma Institute Australia, to create a national Melanoma Clinical Outcomes Registry (MelCOR). This study aimed to formally develop valid clinical quality indicators for the diagnosis and early management of cutaneous melanoma as an important step in creating the registry. METHODS: Potential clinical quality indicators were identified by examining the literature, including Australian and international melanoma guidelines, and by consulting with key melanoma and registry opinion leaders. A modified two-round Delphi survey method was used, with participants invited from relevant health professions routinely managing melanoma as well as relevant consumer organisations. RESULTS: Nineteen participants completed at least one round of the Delphi process. 12 of 13 proposed clinical quality indictors met the validity criteria. The clinical quality indicators included acceptable biopsy method, appropriate excision margins, standardised pathology reporting, indications for sentinel lymph node biopsy, and involvement of multidisciplinary care and referrals. CONCLUSION: This study provides a multi-stakeholder consensus for important clinical quality indicators that define optimal practice that will now be used in the Australian Melanoma Clinical Outcomes Registry (MelCOR).

Methods of melanoma detection and of skin monitoring for individuals at high risk of melanoma: new Australian clinical practice.

INTRODUCTION: The evidence-based national clinical practice guidelines for the management of cutaneous melanoma published in 2008 are currently being updated. This article summarises the findings from multiple chapters of the guidelines on different methods of melanoma detection and of monitoring the skin for patients at high risk of melanoma. Early detection of melanoma is critical, as thinner tumours are associated with enhanced survival; therefore, strategies to improve early detection are important to reduce melanoma-related mortality. MAIN RECOMMENDATIONS: Clinicians who perform skin examinations for the purpose of detecting skin cancer should be trained in and use dermoscopy. The use of short term sequential digital dermoscopy imaging to detect melanomas that lack dermoscopic features of melanoma is recommended to assess individual melanocytic lesions of concern. The use of long term sequential digital dermoscopy imaging to detect melanomas that lack dermoscopic features of melanoma is recommended to assess individual or multiple melanocytic lesions for routine surveillance of high risk patients. The use of total body photography should be considered in managing patients at increased risk for melanoma, particularly those with high naevus counts and dysplastic naevi. There is insufficient evidence to recommend the routine use of automated instruments for the clinical diagnosis of primary melanoma. MANAGEMENT OVERVIEW: Determining the relative indications for each diagnostic method and how each method should be introduced into the surveillance of a patient requires careful consideration and an individualised approach.

Developing an Australian Melanoma Clinical Outcomes Registry (MelCOR): a protocol paper.

INTRODUCTION: Australia has the highest incidence of melanoma in the world with variable care provided by a diverse range of clinicians. Clinical quality registries aim to identify these variations in care and provide anonymised, benchmarked feedback to clinicians and institutions to improve patient outcomes. The Australian Melanoma Clinical Outcomes Registry (MelCOR) aims to collect population-wide, clinical-level data for the early management of cutaneous melanoma and provide anonymised feedback to healthcare providers. METHODS AND ANALYSIS: A modified Delphi process will be undertaken to identify key clinical quality indicators for inclusion in the MelCOR pilot. MelCOR will prospectively collect data relevant to these quality indicators, initially for all people over the age of 18 years living in Victoria and Queensland with a melanoma diagnosis confirmed by histopathology, via a two-stage recruitment and consent process. In stage 1, existing State-based cancer registries contact the treating clinician and provide an opportunity for them to opt themselves or their patients out of direct contact with MelCOR. After stage 1, re-identifiable clinical data are provided to the MelCOR under a waiver of consent. In stage 2, the State-based cancer registry will approach the patient directly and invite them to opt in to MelCOR and share identifiable data. If a patient elects to opt in, MelCOR will be able to contact patients directly to collect patient-reported outcome measures. Aggregated data will be used to provide benchmarked, comparative feedback to participating institutions/clinicians. ETHICS AND DISSEMINATION: Following the successful collection of pilot data, the feasibility of an Australia-wide roll out will be evaluated. Key quality indicator data will be the core of the MelCOR dataset, with additional data points added later. Annual reports will be issued, first to the relevant stakeholders followed by the public. MelCOR is approved by the Alfred Ethics Committee (58280/127/20).

BRAF mutation testing for patients diagnosed with stage III or stage IV melanoma: practical guidance for the Australian setting.

Targeted therapy (BRAF inhibitor plus MEK inhibitor) is now among the possible treatment options for patients with BRAF mutation-positive stage III or stage IV melanoma. This makes prompt BRAF mutation testing an important step in the management of patients diagnosed with stage III or IV melanoma; one that can help better ensure that the optimal choice of systemic treatment is initiated with minimal delay. This article offers guidance about when and how BRAF mutation testing should be conducted when patients are diagnosed with melanoma in Australia. Notably, it recommends that pathologists reflexively order BRAF mutation testing whenever a patient is found to have American Joint Committee on Cancer (AJCC)/Union for International Cancer Control (UICC) stage III or IV melanoma (i.e., any metastatic spread beyond the primary tumour) and that patient's BRAF mutation status is hitherto unknown, even if BRAF mutation testing has not been specifically requested by the treating clinician (in Australia, Medicare-subsidised BRAFV600 mutation testing does not need to be requested by the treating clinician). When performed in centres with appropriate expertise and experience, immunohistochemistry (IHC) using the anti-BRAF V600E monoclonal antibody (VE1) can be a highly sensitive and specific means of detecting BRAFV600E mutations, and may be used as a rapid and relatively inexpensive initial screening test. However, VE1 immunostaining can be technically challenging and difficult to interpret, particularly in heavily pigmented tumours; melanomas with weak, moderate or focal BRAFV600E immunostaining should be regarded as equivocal. It must also be remembered that other activating BRAFV600 mutations (including BRAFV600K), which account for ∼10-20% of BRAFV600 mutations, are not detected with currently available IHC antibodies. For these reasons, if available and practicable, we recommend that DNA-based BRAF mutation testing always be performed, regardless of whether IHC-based testing is also conducted. Advice about tissue/specimen selection for BRAF mutation testing of patients diagnosed with stage III or IV melanoma is also offered in this article; and potential pitfalls when interpreting BRAF mutation tests are highlighted.

Diagnosis and management of cutaneous melanoma.

BACKGROUND: In the field of melanoma, clinical trials evaluating the impact of sentinel node biopsy, completion lymph node dissection and adjuvant medical therapies on patient outcomes have provided evidence that has changed practice significantly over the past five years. OBJECTIVE: The aim of this article is to discuss key evidence that has informed new Cancer Council Australia melanoma management guidelines. DISCUSSION: General practitioners play a critical role in melanoma diagnosis and follow-up. Complete excisional biopsy to achieve accurate tumour microstaging is essential for obtaining reliable prognostic information, planning further management and accessing adjuvant medical therapies. The management of patients with Stage III disease has changed dramatically over the past few years. Less surgery is now recommended, and patients may be offered potentially life-prolonging systemic therapies. Multidisciplinary discussion of management is recommended. Rapid advances in therapeutic options for patients with advanced melanoma have placed new emphasis on the importance of accurate staging and early management. Accordingly, the Australian national melanoma management guidelines have recently been updated. These evidence-based guidelines are now readily available on Cancer Council Australia's electronic Wiki platform, which facilitates regular further updating.

Feasibility and Acceptability of Fear-Less: A Stepped-Care Program to Manage Fear of Cancer Recurrence in People with Metastatic Melanoma.

Immunotherapies and targeted therapies have revolutionised treatment of metastatic melanoma and improved survival rates. However, survivors treated with novel therapies are vulnerable to high levels of fear of cancer recurrence or progression (FCR). Existing FCR interventions have rarely been trialled in people with advanced cancer. The current study aimed to evaluate the acceptability and feasibility of Fear-Less: a stepped-care model to treat FCR in people with metastatic melanoma treated with immunotherapy or targeted therapy. Sixty-one outpatients with metastatic melanoma were screened using the Fear of Cancer Recurrence Inventory Short Form (FCRI-SF) and Fear of Progression Questionnaire Short Form (FoP-Q-SF). Survivors with subthreshold FCR were stratified to a self-management intervention while those with clinical levels of FCR were provided with an individual therapy, Conquer Fear. Survivor experience surveys and rescreening were administered post-intervention completion. Results indicated that Fear-Less was an acceptable and feasible FCR intervention. Results provided preliminary support for the potential impact of Fear-Less in reducing FCR. Fear-Less is a promising first step in providing an acceptable and feasible stepped-care model to treat FCR in survivors with metastatic disease.