Artificial neural network-enabled prognostics for patient health management

Prognostics and prediction of patients' short term physiological health status are of critical importance in medicine because they afford medical interventions that prevent escalating medical complications. This study proposes a prognostics engine to predict patient physiological status. The prognostics engine builds models from historical clinical data using neural network as its computational kernel. This study compared accuracy of various neural network models. Given the diversity of clinical data and disease conditions, no single model is ideal for all medical cases. Certain algorithms are more accurate than others depending on the type, amount and diversity of possible outcomes. Utilizing multiple neural network algorithms is a sound approach to building a generalizable prognostics engine. The study proposes using an ensemble of algorithms and an oracle, an overseer program to select the most accurate combination of the predictive models that is most suited for a particular disease prediction.