Comparison of Machine Learning Techniques with Classical Statistical Models in Predicting Health Outcomes

Several machine learning techniques (multilayer and single layer perceptron, logistic regression, least square linear separation and support vector machines) are applied to calculate the risk of death from two biomedical data sets, one from patient care records, and another from a population survey. Each dataset contained multiple sources of information: history of related symptoms and other illnesses, physical examination findings, laboratory tests, medications (patient records dataset), health attitudes, and disabilities in activities of daily living (survey dataset). Each technique showed very good mortality prediction in the acute patients data sample (AUC up to 0.89) and fair prediction accuracy for six year mortality (AUC from 0.70 to 0.76) in individuals from epidemiological database surveys. The results suggest that the nature of data is of primary importance rather than the learning technique. However, the consistently superior performance of the artificial neural network (multi-layer perceptron) indicates that nonlinear relationships (which cannot be discerned by linear separation techniques) can provide additional improvement in correctly predicting health outcomes.