The incidence of skin cancer in Europe is increasing, and is expected to continue rising over the coming decade.¹˒² The World Health Organization (WHO) recognizes the importance of early detection, which requires accessible healthcare services and health professionals with adequate expertise.³˒⁴

Artificial intelligence (AI)-based systems could facilitate early skin cancer detection in several ways:

• by assisting the general population in identifying skin lesions requiring urgent medical evaluation,
• by supporting physicians in risk assessment and diagnosis.

There is a need for studies evaluating accuracy and safety of these tools in real-world settings ^5,6, and identifying at which points in the diagnostic process they can provide public health benefit.^5,7

This PhD focuses on two levels:

• Consumer level: Many apps are available, but concerns remain about their accuracy in real-world conditions. ^8,9 The first study evaluates the diagnostic accuracy, influencing factors, and user acceptance of a widely used smartphone app, evaluated in a prospective study involving actual end-users (manuscript submitted).

• Physician level: In experimental settings, neural networks have shown diagnostic performance comparable to expert dermatologists using dermoscopic images.¹⁰ Evidence suggests that combining AI support with physician input yields better outcomes than either alone, and that less experienced clinicians benefit most. ¹¹ This study investigates the impact of AI-based decision support on clinical decision-making by GPs and dermatologists (study ongoing).

The goal of the PhD is 

1. To evaluate diagnostic accuracy, reproducibility, user acceptance of a widely used smartphone app¹² through a large-scale clinical trial in a cohort resembling end-users.

1. To assess the Impact of AI decision support on diagnostic and management decisions and confidence among general practitioners (GPs) and dermatologists of varying experience, in an online reader study. To explore physicians’ perspectives on AI decision support.

These studies may provide insights into the responsible integration of AI for early skin cancer detection within the current regulatory framework.

1. International Agency for Research on Cancer (IARC). Cancer Today. Population fact sheets. 2022; Available from: https://gco.iarc.fr/today/fact-sheets-populations Accessed on: 20 April 2025.
2. Brochez L, Volkmer B, Hoorens I, Garbe C, Röcken M, Schüz J, et al. Skin cancer in Europe today and challenges for tomorrow. J Eur Acad Dermatol Venereol. 2024.
3. WHO Cancer screening and early detection of cancer. Preprints with The Lancet; 2010; Available from: https://www.who.int/europe/news-room/fact-sheets/item/cancer-screening-and-early-detection-of-cancer. Accessed on: 20 April 2025.
4. Adamson AS. The USPSTF I Statement on Skin Cancer Screening-Not a Disappointment but an Opportunity. JAMA Dermatol. 2023;159(6):579-81.
5. Brancaccio G, Balato A, Malvehy J, Puig S, Argenziano G, Kittler H. Artificial Intelligence in Skin Cancer Diagnosis: A Reality Check. J Invest Dermatol. 2024;144(3):492-9.
6. Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019;1(6):e271-e97.
7. Jones OT, Matin RN, Walter FM. Using artificial intelligence technologies to improve skin cancer detection in primary care. Lancet Digit Health. 2025;7(1):e8-e10.
8. Freeman K, Dinnes J, Chuchu N, et al. Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies. 2020;368:m127.
9. Matin RN, Dinnes J. AI-based smartphone apps for risk assessment of skin cancer need more evaluation and better regulation. Br J Cancer. 2021;124(11):1749-50.
10. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115-8.Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019;1(6):e271-e97.
11. Tschandl P, Rinner C, Apalla Z, et al. Human-computer collaboration for skin cancer recognition. Nat Med. 2020;26(8):1229-34.
12. SkinVision | Huidkanker Detectie App