The Role of Smartphone-Based Applications and Artificial Intelligence Aiding in Screening, Faster Diagnosis and Prevention in Skin Cancer: A Systematic Mini-Review

Abstract

Background: Skin cancer, especially melanoma, is one of the most common cancers in humans. According to the WHO, it causes a significant burden on modern health services. Currently, diagnostics are painful and invasive for patients and healthcare providers, heralding novel techniques. In the age of mobile health, computer-aided applications could be an ideal solution. However, their relevance in clinical practice remains to be determined. This systematic review assessed detection rates and clinical implementation of computer-aided applications in patients with suspicious skin lesions. Methods and Results: We systematically searched the following databases: PubMed, Medline, Embase (OVID), Web of Science, and the Cochrane Library for articles. Of 819 identified articles, eight remained for primary outcome analysis. Diagnostic sensitivity was reported in three out of eight studies, while accuracy and concordance were reported in three and four, respectively. The quality of the included studies was primarily moderate. Conclusion: Although promising, computer-aided applications remain below standard detection rates of the current standard of care. Further improvement in accuracy and detection rates should be achieved while primary care providers and patients alike should be aware of the current limitations of these new diagnostic tools.