Exploiting Convolutional Neural Network for Risk Prediction with Medical Feature Embedding

TL;DR

This paper introduces a convolutional neural network with medical feature embedding to improve risk prediction from longitudinal EHR data, effectively capturing complex temporal patterns and high-dimensional features.

Contribution

It proposes a novel CNN-based model with learned medical feature embeddings to handle high dimensionality and temporality in EHR data for risk prediction.

Findings

Effective risk prediction for congestive heart failure and diabetes.

Medical feature embedding improves model performance.

CNN captures local temporal dependencies in EHRs.

Abstract

The widespread availability of electronic health records (EHRs) promises to usher in the era of personalized medicine. However, the problem of extracting useful clinical representations from longitudinal EHR data remains challenging. In this paper, we explore deep neural network models with learned medical feature embedding to deal with the problems of high dimensionality and temporality. Specifically, we use a multi-layer convolutional neural network (CNN) to parameterize the model and is thus able to capture complex non-linear longitudinal evolution of EHRs. Our model can effectively capture local/short temporal dependency in EHRs, which is beneficial for risk prediction. To account for high dimensionality, we use the embedding medical features in the CNN model which hold the natural medical concepts. Our initial experiments produce promising results and demonstrate the effectiveness of both the medical feature embedding and the proposed convolutional neural network in risk prediction on cohorts of congestive heart failure and diabetes patients compared with several strong baselines.