This report summarizes work to predict patient mortality using medical diagnoses data. It identifies errors in the dataset, calculates likelihood ratios for diagnoses, and uses a patient's medical history to predict their prognosis and probability of mortality. An example is given of a patient with a high risk medical history and 89.5% predicted probability of mortality within 6 months based on their diagnoses. The model is evaluated for accuracy using sensitivity and specificity metrics in a contingency table. Finally, the importance of this work for healthcare facilities in utilizing big data to better serve patients and the impact preparation decisions can have on findings is discussed.