Systems and methods for predicting continuous organ failure assessment (SOFA) scores using artificial intelligence and machine learning

摘要

Various aspects of the subject technology relate to systems and methods for predicting continuous organ failure assessment (SOFA) scores using machine learning. The system can be configured to receive patient data including one or more characteristics associated with one or more patients. The system may process the features using one or more SOFA score prediction models derived from at least one machine learning process to output individual predicted SOFA scores. One of the prediction models is trained to output a first SOFA component score at a first amount of time in the future, and a second prediction model is trained to output a second SOFA component score at a first amount of time in the future. Trained to output SOFA component scores. The system can output, on a graphical user interface, a total SOFA score, a first SOFA component score, and a second SOFA component score that are predicted for an individual patient.