Aplicações da inteligência artificial no câncer oral: uma revisão sistemática

Introduction. Accurate and early diagnosis of oral cancer allows not only the correct choice and application of treatment, but also intervention in the early stages of the disease, which directly contributes to a good prognosis for the patient. Therefore, technologies are presented as important allies for improving the diagnosis and treatment of this condition. Objectives. To identify the applications of Artificial Intelligence in the process of diagnosis and treatment of malignant oral lesions. Method. This research is a systematic review that followed the guidelines of the PRISMA protocol. The search was carried out in the PubMed, BVS, Science Direct and Scopus databases and the initial screening was based on reading the title and abstract of the articles found. The remaining studies from this stage were selected for full reading in order to verify their adequacy with the inclusion criteria of this review. Finally, the studies selected for inclusion underwent an analysis of the risk of bias. Results. A total of 19 studies were included, in which the most analyzed fields were machine learning, artificial neural network and deep-learning, and the most analyzed applications were histopathological diagnosis and diagnostic prediction. Conclusions. Although it was possible to identify the applications of artificial intelligence models for the purpose studied, it is clear that studies with higher quality evidence need to be produced to prove the effectiveness of these applications.