Applied Sciences, Vol. 13, Pages 8257: Machine Learning and miRNAs as Potential Biomarkers of Breast Cancer: A Systematic Review of Classification Methods

Applied Sciences, Vol. 13, Pages 8257: Machine Learning and miRNAs as Potential Biomarkers of Breast Cancer: A Systematic Review of Classification Methods

Applied Sciences doi: 10.3390/app13148257

Authors: Jorge Alberto Contreras-Rodríguez Diana Margarita Córdova-Esparza María Zenaida Saavedra-Leos Macrina Beatriz Silva-Cázares

This work aims to offer an analysis of empirical research on the automatic learning methods used in detecting microRNA (miRNA) as potential markers of breast cancer. To carry out this study, we consulted the sources of Google Scholar, IEEE, PubMed, and Science Direct using appropriate keywords to meet the objective of the research. The selection of interesting articles was carried out using exclusion and inclusion criteria, as well as research questions. The results obtained in the search were 36 articles, of which PubMed = 14, IEEE = 8, Science Direct = 4, Google Scholar = 10; among them, six were selected, since they met the search perspective. In conclusion, we observed that the machine learning methods frequently mentioned in the reviewed studies were Support Vector Machine (SVM) and Random Forest (RF), the latter obtaining the best performance in terms of precision.