JMIR Publications

ABSTRACT

Background:

Recently Deep CNNs (DCNNs) became of interest as decision support systems for dermoscopic and clinical analysis skin diseases. AI application in TD has been recently reported in several studies as a tool for augmented intelligence.

Objective:

In this session, a critical discussion of the opportunities, limitations, and risks of AI in TD will be presented with special attention to recent studies published.

Methods:

Review of the literature in Pubmed, EMBASE in the period of January 2018 to November 2021 with the search terms of dermatology, skin cancer, deep learning, artificial intelligence. Review of the Regulation of Medical Devices in the EU 2017/745.

Results:

A clear definition of the clinical use of AI in TD has to be considered: primary TD from patients to nurses, primary care physicians (PCP) or general dermatologists; secondary TD from PCP or nurses to dermatologists or tertiary TD from dermatologists to Hospital dermatologists. In some health models TD for nurses or PCPs, AI assistance can lower the rates of recommending a biopsy or specialist referral, increase self-reported diagnostic confidence, and help to achieve higher diagnostic agreement rates (with dermatologists) in non-referred cases. The main limitations of the use of AI in TD are lack of large longitudinal studies, lack of interpretability of the CNN, biases in the databases and unrepresented dermatological conditions for training, limited representation of different ethnicities, standardization of clinical information and of the images, liability, and privacy issues. How to implement the concept of Augmented intelligence in clinical practice with referral TD consultations including structured clinical information and good quality images will need further research and education of the end-users. Even if the interface is used either for store-and-forward teledermatology or to live, interactive teledermatology is in principle straightforward for AI systems, different TD modalities have particular technological requirements that can reduce the efficacy. Finally, AI systems in TD are under the umbrella of medical device regulatory frames, and specific certification is compulsory. This regulation has the benefit of assuring the quality of the new AI systems and diminishing their risks but at the same time, it can delay the incorporation of AI tools in clinical practice.

Conclusions:

AI has the potential to improve the results of the technology in different aspects in multiple modalities of TD. However, the evidence is weak and several barriers and limitations have to be solved for their integration into clinical practice.