The main challenge for health insurers is to properly manage the disease as well as the health of its members, emphasizing the prevention and implementation of actions that allow the anticipation and prediction of the disease. This article presents a systematic review of the literature on the main machine learning methodologies that allow, through the prediction of mental illnesses, to carry out an early intervention. It was found that the main methodologies for this purpose are statistical models such as logistic regression, Vector support machine and random forest; and that the different indicators of neuroimaging use of cell phonesbecome fundamental predictor variables when it comes to predicting mental illnesses. © 2022, Associacao Iberica de Sistemas e Tecnologias de Informacao. All rights reserved.