Systematic Map of Data Mining for Gynecologic Oncology

Gynecologic cancers are a significant cause of morbidity and mortality among women both in developed and low- middle- income countries. To alleviate the burden, the application of Data Mining (DM) in gynecologic oncology is needed in clinical environments. This study presents a systematic mapping to explore in detail the breadth of the available literature on the use of DM in gynecologic oncology. The mapping questions and the PICO framework served to determine the search string of this systematic map. The resultant was conducted on five well-known databases, PubMed, IEEE Xplore, ScienceDirect, Springer Link, and Google Scholar, to catch relevant articles published between 2011, and mid of 2021. Of the 2,807 potential records, 169 studies fulfilled the inclusion/exclusion criteria and were in-depth analyzed. The findings revealed that DM efforts peaked considerably from 2019 in terms of cervical cancer screening and diagnosis. Further studies are needed to investigate a wider range of research questions as gynecologic oncology is a very rich field with a collection of distinct features cancers which, in turn, allow Machine Learning (ML) opportunities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.