Analysis of EHR Free-text Data with Supervised Deep Neural Networks

In this paper we present an efficient supervised deep neural network architecture to classify patients based solely on free-text notes extracted from their Electronic Health Records (EHRs). In particular, a three-layer Recurrent Neural Network was used in conjunction with the aggregated EHRs of about 127,149 patients from a medical data warehouse. The result forms a key component of an application we name PANNACEA. We evaluated this neural network in the context of competing neural network architectures, comparing the performance of multilayer perceptrons, convolutional neural networks, and recurrent neural networks in relation to the dataset under investigation. We performed evaluation our program to successfully classify the suitability of these patients to the medical service offered based upon a single medical episode.