Risk Prediction with Electronic Health Records: A Deep Learning Approach

Abstract

The recent years have witnessed a surge of interests in data analytics with patient Electronic Health Records (EHR). Data-driven healthcare, which aims at effective utilization of big medical data, representing the collective learning in treating hundreds of millions of patients, to provide the best and most personalized care, is believed to be one of the most promising directions for transforming healthcare. EHR is one of the major carriers for make this data-driven healthcare revolution successful. There are many challenges on working directly with EHR, such as temporality, sparsity, noisiness, bias, etc. Thus effective feature extraction, or phenotyping from patient EHRs is a key step before any further applications. In this paper, we propose a deep learning approach for phenotyping from patient EHRs. We first represent the EHRs for every patient as a temporal matrix with time on one dimension and event on the other dimension. Then we build a fourlayer convolutional neural network model for extracting phenotypes and perform prediction. The first layer is composed of those EHR matrices. The second layer is a one-side convolution layer that can extract phenotypes from the first layer. The third layer is a max pooling layer introducing sparsity on the detected phenotypes, so that only those significant phenotypes will remain. The fourth layer is a fully connected softmax prediction layer. In order to incorporate the temporal smoothness of the patient EHR, we also investigated three different temporal fusion mechanisms in the model: early fusion, late fusion and slow fusion. Finally the proposed model is validated on a real world EHR data warehouse under the specific scenario of predictive modeling of chronic diseases.

A Predictive Model for Medical Events Based on Contextual Embedding of Temporal Sequences

“…However, their method can only predict discharge codes at international classification of diseases (ICD)-9 level 1, which are relatively generic and cannot differentiate among a wide range of diverse diagnoses. In risk prediction with EHR, Cheng et al [16] used convolutional neural network with a temporal fusion to predict congestive heart failure and chronic obstructive pulmonary disease within the next 180 days. Their approach can only handle 2 diagnoses and achieved an AUC of less than 0.77.…”

Applying deep learning for adverse pregnancy outcome detection with pre-pregnancy health data

“…Cheng et al [11] developed a CNN network to predict future events based on 4-year EHR data from more than 300,000 patients. Chio et.al [12] was the first to use the RNN-based approach to the prediction of heart failure (HF) to analyse temporal relation before clinical events in electronic medical records.…”

An RNN Architecture with Dynamic Temporal Matching for Personalized Predictions of Parkinson's Disease

“…In [4], the authors proposed an adjustable temporal fusion scheme using CNNextracted features. In [21], the authors develop a deep neural network composed of a stack of denoising autoencoders to process electronic health records (EHR) in an unsupervised manner and then compute patient similarity based on such representation.…”