Experiences regarding use and implementation of AI-supported follow-up of atypical moles at a Dermatological out-patient clinic: a qualitative study (Preprint)

Abstract

Artificial intelligence (AI) is increasingly employed in numerous medical fields. In dermatology, AI can be used when assessing and diagnosing suspicious skin lesions. ATBM master from FotoFinder Systems GmbH is an AI-powered imaging device which can aid the doctor in the diagnosis of melanoma, a potential lethal skin cancer with rising incidence all over the world. ATBM master includes a Total Body Dermoscopy (TBD)-module which can photograph a patient’s entire body, and afterwards display moles onto a screen, grouped according to their clinical relevance. An optional software, Moleanalyzer Pro, can provide additional information about the moles. The creation of many AI-supported devices often centers around technicalities, rather than practical application in clinical settings. As a consequence, the implementation and realization of such systems may face suboptimal use.

Few qualitative studies have been conducted on the implementation of AI-supported procedures in dermatology. Therefore, the purpose of this study was to investigate how healthcare providers experience the use and implementation of an AI-powered skin imaging devices like FotoFinder’s ATBM master, in particular its TBD-module. In this way, the study aimed to elucidate potential barriers to the application of such new technology.

Two focus-group interviews with 14 doctors and nurses regularly working in an out-patient pigmented lesions clinic, was conducted. The Consolidated Framework for Implementation Research (CFIR) served as framework for the study. Analysis and interpretation of the interviews were based on the thematic analysis of Braun and Clark.

First, several organizational matters were revealed to be a barrier to consistent usage of the ATBM master’s AI-powered TBD-module, namely lack of guidance, time pressure and insufficient training. Second, the study found the perceived benefits of TBD to be the ability to better discover and monitor subtle lesion changes, as well as being an unbiased procedure. Imprecise identification of moles, inability to photograph certain areas, and substandard technical aspects, were among the perceived weaknesses. Lastly, the study found that clinicians were open to utilize AI-powered technology and that the TBD module was considered a supplementary tool to aid the medical staff, rather than a replacement of the clinician.

AI-powered imaging device may aid the doctor in the diagnosis of skin cancer. To ensure optimized application of AI-supported diagnostic tools, a strategy for implementation should exist.