Predicting all-cause mortality is a major goal of public health and often medicine in general. Variables such as high blood pressure, advanced age, smoking status, and other factors have been associated with an increased risk in all-cause mortality. The CDC’s Third National Health and Nutrition Examination Survey (NHANES) is a large nationwide probability sample of 39,695 persons. NHANES provides sample information regarding relevant health metrics for example blood pressure or age, in addition to patient vital status during the time period. To retrospectively determine which features are most relevant in predicting mortality, a selection of machine learning models including logistic regression, decision tree classifier, and a random forest classifier were trained on the dataset and compared based on accuracy, precision, F1 score, and subsequently area under a receiver operating characteristic curve. Overall, the random forest classifier seemed to provide the best predictive performance with an accuracy of 0.99, exceeding the 0.95 threshold. Scientists could apply this methodology to guide mortality prediction for other specific outcomes.