Kränke Teresa, Efferl Philipp, Tripolt-Droschl Katharina, Hofmann-Wellenhof Rainer
Department of Dermatology and Venereology, Medical University of Graz, Austria.
Dermatol Pract Concept. 2025 Jul 31;15(3):5110. doi: 10.5826/dpc.1503a5110.
The diagnostic performance of convolutional neural networks (CNNs) in diagnosing different types of skin cancer has been quite promising. Mobile phone applications with integrated artificial intelligence (AI) are an understudied area.
We evaluated the risk assessment of the SkinScreener (Medaia GmbH, Graz, Austria) AI-based algorithm in comparison with an expert panel of three dermatologists.
In this retrospective single-center study at the Department of Dermatology and Venereology in Graz, Austria. Photographs of lesions were taken by the users' mobile phone cameras. The algorithm allocated them to three risk classes. Blinded to AI's results, the images were evaluated by three dermatologists-our reference standard. A consensus was defined as at least a two-thirds majority.
A total of 1,428 skin lesions were included. In 902 lesions (63.16%), there was full agreement, and in 441 lesions (30.88%) a two-thirds majority was reached. Eighty-five lesions (5.69%) had to be discussed in a joint review process. The tested algorithm reached a sensitivity of 76.9% (95% CI: 71.7%-81.5%) and a specificity of 80.9% (95% CI: 78.5%-83.2%). Overall accuracy results were 77.2%.
Our results indicate that the tested mobile phone algorithm is a valuable tool for the correct risk classification of various skin lesions. As expected, its performance is worse than in a professional setting. Nonetheless, the use of these applications on mobile phones should raise awareness of skin cancer and encourage users to deal more intensively with preventive measures. In light of our results, these applications are also reliable for use by non-professionals.
卷积神经网络（CNN）在诊断不同类型皮肤癌方面的诊断性能颇具前景。集成人工智能（AI）的手机应用是一个研究较少的领域。
我们将基于人工智能算法的SkinScreener（奥地利格拉茨的Medaia GmbH公司）与由三位皮肤科医生组成的专家小组进行比较，评估其风险评估能力。
在奥地利格拉茨皮肤病与性病科进行的这项回顾性单中心研究中，用户使用手机摄像头拍摄病变照片。该算法将病变分为三个风险等级。在不了解人工智能结果的情况下，由三位皮肤科医生对图像进行评估——这是我们的参考标准。若至少三分之二的人达成一致，则定义为达成共识。
共纳入1428例皮肤病变。902例病变（63.16%）完全达成一致，441例病变（30.88%）达成了三分之二多数的意见。85例病变（5.69%）需在联合审查过程中进行讨论。测试算法的灵敏度为76.9%（95%置信区间：71.7% - 81.5%），特异度为80.9%（95%置信区间：78.5% - 83.2%）。总体准确率为77.2%。
我们的结果表明，测试的手机算法是对各种皮肤病变进行正确风险分类的有价值工具。正如预期的那样，其性能在专业环境中要差一些。尽管如此，在手机上使用这些应用应该会提高对皮肤癌的认识，并鼓励用户更深入地采取预防措施。根据我们的结果，这些应用对非专业人员来说也是可靠的。
