We have more and more access to information, more scientific studies are published, there is a need for refinement and reduction of this amount of information, so as to facilitate the mapping of the discoveries made and the discovery of new areas of research, we developed a tool to assist Systematic Review studies. 

Review articles represent the synthesis of scientific knowledge, benefiting from doctoral students, master's degree, undergraduate to funding institutions and critical updates in the medical area. The emergence of citation indexers and electronic scientific databases has facilitated the publication of primary studies; however, the writing of review articles follows a manual and tedious methodology, often failing to contemplate the most recent primary studies at the time of publication. 

We present with this work a tool to support the Systematic Review of Literature, so that the time in the analysis of articles in the selection phase is optimized, allowing the reviewers to move to the extraction phase in a faster and smoother way, based on statistical views. 

We use topic modeling to map and search for relationships not so obvious to human discernment, added to the efficiency of the average time for article analysis in the selection phase, regardless of the number of articles, but rather the computational power to reduce the time of this phase from months to hours or minutes.