Inteligência artificial como ferramenta de auxílio ao diagnóstico de câncer de pele

Abstract

Cancer is a chronic, serious, and degenerative disease considered an important and complex public health issue. Among the various types of cancer, skin cancer stands out, and detection in early stages is a determining factor for a favorable prognosis, enhancing treatment, resulting in greater possibilities of cure and reduction of more aggressive interventions. Knowing this, artificial intelligence can play a fundamental role in the diagnosis of this type of cancer, enhancing treatment, resulting in greater possibilities of cure and reduction of more aggressive interventions. In view of this, the objective of this systematic review was to investigate the potential impacts of the diagnosis of skin cancer, through the application of artificial intelligence. This is a systematic review carried out in the databases of the National Institutes of Health, Scientific Electronic Library, Library, Information Science & Technology Abstracts, Library and Information Science Abstracts, and Latin American and Caribbean Literature in Health Sciences, where observational case-control, cohort, and experimental studies published in the last 10 years were sought. Ten articles were selected and analyzed, and it was possible to see that the diagnosis, through artificial intelligence, presented different percentages of sensitivity and specificity, however equivalent or even many times superior to the results obtained by dermatologists. Therefore, the potential and diagnostic robustness of skin cancer, through artificial intelligence, was clearly demonstrated.