Position statement of the EADV Artificial Intelligence (AI) Task Force on AI-assisted smartphone apps and web-based services for skin disease

BACKGROUND

As the use of smartphones continues to surge globally, mobile applications (apps) have become a powerful tool for healthcare engagement. Prominent among these are dermatology apps powered by Artificial Intelligence (AI), which provide immediate diagnostic guidance and educational resources for skin diseases, including skin cancer.

OBJECTIVE

This article, authored by the EADV AI Task Force, seeks to offer insights and recommendations for the present and future deployment of AI-assisted smartphone applications (apps) and web-based services for skin diseases with emphasis on skin cancer detection.

METHODS

An initial position statement was drafted on a comprehensive literature review, which was subsequently refined through two rounds of digital discussions and meticulous feedback by the EADV AI Task Force, ensuring its accuracy, clarity and relevance.

RESULTS

Eight key considerations were identified, including risks associated with inaccuracy and improper user education, a decline in professional skills, the influence of non-medical commercial interests, data security, direct and indirect costs, regulatory approval and the necessity of multidisciplinary implementation. Following these considerations, three main recommendations were formulated: (1) to ensure user trust, app developers should prioritize transparency in data quality, accuracy, intended use, privacy and costs; (2) Apps and web-based services should ensure a uniform user experience for diverse groups of patients; (3) European authorities should adopt a rigorous and consistent regulatory framework for dermatology apps to ensure their safety and accuracy for users.

CONCLUSIONS

The utilisation of AI-assisted smartphone apps and web-based services in diagnosing and treating skin diseases has the potential to greatly benefit patients in their dermatology journeys. By prioritising innovation, fostering collaboration and implementing effective regulations, we can ensure the successful integration of these apps into clinical practice.

Artificial intelligence in mobile health for skin cancer diagnostics at home (AIM HIGH): a pilot feasibility study

Background

Artificial intelligence (AI)-based mobile phone apps (mHealth) have the potential to streamline care for suspicious skin lesions in primary care. This study aims to investigate the conditions and feasibility of a study that incorporates an AI-based app in primary care and evaluates its potential impact.

Methods

We conducted a pilot feasibility study from November 22nd, 2021 to June 9th, 2022 with a mixed-methods design on implementation of an AI-based mHealth app for skin cancer detection in three primary care practices in the Netherlands (Rotterdam, Leiden and Katwijk). The primary outcome was the inclusion and successful participation rate of patients and general practitioners (GPs). Secondary outcomes were the reasons, facilitators and barriers for successful participation and the potential impact in both pathways for future sample size calculations. Patients were offered use of an AI-based mHealth app before consulting their GP. GPs assessed the patients blinded and then unblinded to the app. Qualitative data included observations and audio-diaries from patients and GPs and focus-groups and interviews with GPs and GP assistants.

Findings

Fifty patients were included with a median age of 52 years (IQR 33.5-60.3), 64% were female, and 90% had a light skin type. The average patient inclusion rate was 4-6 per GP practice per month and 84% (n = 42) successfully participated. Similarly, in 90% (n = 45 patients) the GPs also successfully completed the study. GPs never changed their working diagnosis, but did change their treatment plan (n = 5) based on the app's assessments. Notably, 54% of patients with a benign skin lesion and low risk rating, indicated that they would be reassured and cancel their GP visit with these results (p < 0.001).

Interpretation

Our findings suggest that studying implementation of an AI-based mHealth app for detection of skin cancer in the hands of patients or as a diagnostic tool used by GPs in primary care appears feasible. Preliminary results indicate potential to further investigate both intended use settings.

Funding

SkinVision B.V.

An artificial intelligence based app for skin cancer detection evaluated in a population based setting

Artificial intelligence (AI) based algorithms for classification of suspicious skin lesions have been implemented in mobile phone apps (mHealth), but their effect on healthcare systems is undocumented. In 2019, a large Dutch health insurance company offered 2.2 million adults free access to an mHealth app for skin cancer detection. To study the impact on dermatological healthcare consumption, we conducted a retrospective population-based pragmatic study. We matched 18,960 mHealth-users who completed at least one successful assessment with the app to 56,880 controls who did not use the app and calculated odds ratios (OR) to compare dermatological claims between both groups in the first year after granting free access. A short-term cost-effectiveness analysis was performed to determine the cost per additional detected (pre)malignancy. Here we report that mHealth-users had more claims for (pre)malignant skin lesions than controls (6.0% vs 4.6%, OR 1.3 (95% CI 1.2-1.4)) and also a more than threefold higher risk of claims for benign skin tumors and nevi (5.9% vs 1.7%, OR 3.7 (95% CI 3.4-4.1)). The costs of detecting one additional (pre)malignant skin lesion with the app compared to the current standard of care were €2567. Based on these results, AI in mHealth appears to have a positive impact on detecting more cutaneous (pre)malignancies, but this should be balanced against the for now stronger increase in care consumption for benign skin tumors and nevi.

Towards successful implementation of artificial intelligence in skin cancer care: a qualitative study exploring the views of dermatologists and general practitioners

Recent studies show promising potential for artificial intelligence (AI) to assist healthcare providers (HCPs) in skin cancer care. The aim of this study is to explore the views of dermatologists and general practitioners (GPs) regarding the successful implementation of AI when assisting HCPs in skin cancer care. We performed a qualitative focus group study, consisting of six focus groups with 16 dermatologists and 17 GPs, varying in prior knowledge and experience with AI, gender, and age. An in-depth inductive thematic content analysis was deployed. Perceived benefits, barriers, and preconditions were identified as main themes. Dermatologists and GPs perceive substantial benefits of AI, particularly an improved health outcome and care pathway between primary and secondary care. Doubts about accuracy, risk of health inequalities, and fear of replacement were among the most stressed barriers. Essential preconditions included adequate algorithm content, sufficient usability, and accessibility of AI. In conclusion, dermatologists and GPs perceive significant benefits from implementing AI in skin cancer care. However, to successfully implement AI, key barriers need to be addressed. Efforts should focus on ensuring algorithm transparency, validation, accessibility for all skin types, and adequate regulation of algorithms. Simultaneously, improving knowledge about AI could reduce the fear of replacement.

Limited impact of COVID-19-related diagnostic delay on cutaneous melanoma and squamous cell carcinoma tumour characteristics: a nationwide pathology registry analysis

BACKGROUND

The COVID-19 pandemic reduced the number of skin cancer diagnoses, potentially causing a progression to unfavourable tumour stages.

OBJECTIVES

To identify the impact of delayed diagnostics on primary invasive melanoma and cutaneous squamous cell carcinoma (cSCC) by comparing tumour (pT) stage, Breslow thickness and invasion depth from before to after the first and second lockdown periods.

METHODS

In this population-based cohort study, histopathology reports registered between 1 January 2018 and 22 July 2021 were obtained from the nationwide histopathology registry in the Netherlands. The Breslow thickness of melanomas, invasion depth of cSCCs, and pT stage for both tumour types were compared across five time periods: (i) pre-COVID, (ii) first lockdown, (iii) between first and second lockdowns, (iv) second lockdown and (v) after second lockdown. Breslow thickness was compared using an independent t-test. pT-stage groups were compared using a χ2 -test. Outcomes were corrected for multiple testing using the false discovery rate.

RESULTS

In total, 20 434 primary invasive melanomas and 68 832 cSCCs were included in this study. The mean primary melanoma Breslow thickness of the prepandemic era (period i) and the following time periods (ii-v) showed no significant difference. A small shift was found towards unfavourable pT stages during the first lockdown compared with the pre-COVID period: pT1 52·3% vs. 58·6%, pT2 18·9% vs. 17·8%, pT3 13·2% vs. 11·0%, pT4 9·1% vs. 7·3% (P = 0·001). No relevant changes were seen in subsequent periods. No significant change in pT stage distribution was observed between the pre-COVID (i) and COVID-affected periods (ii-v) for cSCCs.

CONCLUSIONS

To date, the diagnostic delay caused by COVID-19 has not resulted in relatively more unfavourable primary tumour characteristics of melanoma or cSCC. Follow-up studies in the coming years are needed to identify a potential impact on staging distribution and survival in the long term.

Views on mobile health apps for skin cancer screening in the general population: an in-depth qualitative exploration of perceived barriers and facilitators

Background

Mobile health (mHealth) applications (apps) incorporating artificial intelligence for skin cancer screening are increasingly reimbursed by health insurers. However, an in‐depth exploration of the general public’s views towards these apps is lacking.

Objectives

To explore the perceived barriers and facilitators towards mHealth apps for skin cancer screening among the Dutch general population.

Methods

A qualitative study consisting of four focus groups with 27 participants was conducted. A two‐stage purposive sampling method was used to include information‐rich participants from the Dutch general population with varying experience of mHealth. A topic guide was used to structure the sessions. All focus group meetings were transcribed verbatim and analysed in thematic content analysis by two researchers using several coding phases, resulting in an overview of themes and subthemes, categorized as (sub‐)barriers and (sub)facilitators.

Results

Main barriers to using mHealth apps included a perceived lack of value, perception of untrustworthiness, preference for a doctor, privacy concerns, a complex user interface, and high costs. The main factors facilitating the use of mHealth among the general population were a high perceived value, a transparent and trustworthy identity of app developers, endorsement by healthcare providers and government regulating bodies, and ease and low costs of use.

Conclusions

To increase successful adoption in skin cancer screening apps, developers should create a transparent identity and build trustworthy apps. Collaboration between app developers, general practitioners and dermatologists is advocated to improve mHealth integration with skin cancer care. Special attention should be given to the development of low‐cost, privacy‐friendly, easy‐to‐use apps.

What is already known about this topic?

Mobile health (mHealth) smartphone apps, which provide users with a risk indication of skin cancer using artificial intelligence, are increasingly reimbursed by health insurers.

An in‐depth understanding of the views of the general public towards these apps is currently lacking.

To increase the functionality and successful adoption and integration of mHealth with skin cancer care, insight into perceived barriers and facilitators towards the use of this technology is advocated.

What does this study add?

Our qualitative exploration shows that perceived value, trustworthiness, privacy, app design and costs act as important barriers or facilitators towards the use of mHealth apps for skin cancer screening among the Dutch general population.

The preference for a human doctor acted as an additional important barrier towards using mHealth apps.

Additional main facilitators were a transparent identity of the app developer, and endorsement from healthcare providers and government regulating bodies.

What are the clinical implications of this work?

Adoption of mHealth for skin cancer can be improved by clear communication regarding the reliability of the provided screening, its associated benefits and drawbacks, and by ensuring low cost of use.

Design and functionality can be improved by developing privacy‐friendly, easy‐to‐use apps that are usable by all ages.

Integration with existing healthcare systems can be improved by collaboration with and endorsement from healthcare professionals and government regulating bodies.

Linked Comment: R.M. Hewitt and C. Bundy. Br J Dermatol 2021; 185:880–881.

Plain language summary available online