New international reporting guidelines for clinical trials evaluating effectiveness of artificial intelligence interventions in dermatology: strengthening the SPIRIT of robust trial reporting
Maria Charalambides, Carsten Flohr, Philippe Bahadoran, Rubeta Matin
Abstract
Conflicts of interest: The authors declare they have no conflicts of interest. Artificial intelligence (AI) can be defined simply as the ability of computers to simulate intelligent human behaviour. Machine learning is a branch of AI that uses algorithms and statistical models that are able to learn from data. Deep learning is a specific form of machine learning. AI can refer to either machine learning or deep learning.1 The potential for AI and machine learning to improve the management of skin diseases is immense. For instance smartphone applications (‘apps’) can detect or monitor skin disease, and apps can send images to a central server for evaluation. Assessing the impact of such devices through robustly developed, rigorously conducted and accurately reported intervention studies may lead to significant changes in healthcare delivery. This could be through enhanced diagnostic accuracy and disease flare prediction, which allow pre‐emptive treatment adjustments and ultimately better disease control. The coronavirus disease 2019 (COVID‐19) pandemic has accelerated adoption of digital technologies to reduce the need for face‐to‐face contact with patients and created a sense of urgency to implement AI in healthcare, with dermatology as a priority.