Highlights Two artificial neural networks, type of multilayer perceptron, and a random forest model were developed. Multilayer perceptron and random forest were compared to the OASIS, SAPS, SAPS II, SAPS III, LODS, SOFA, and EVCI Scores. Discrimination was assessed with the receiver operator characteristic and precision-recall curves. Calibration of the predictive models was evaluated with the Brier Score. ABSTRACT Objective The variation in mortality rates of intensive care unit oncological patients may imply that clinical characteristics and prognoses are very […]