Multimodal Learning for Cardiovascular Risk Prediction using EHR Data

TL;DR

This study introduces a multimodal neural network that combines structured clinical data and unstructured medical texts from EHRs to improve cardiovascular risk prediction, achieving state-of-the-art results.

Contribution

It presents a novel multimodal BiLSTM model that effectively integrates text and structured data for enhanced risk prediction in cardiovascular disease.

Findings

BiLSTM outperforms other neural network architectures.

The multimodal approach improves prediction accuracy.

Model demonstrates state-of-the-art performance on real-world data.

Abstract

Electronic health records (EHRs) contain structured and unstructured data of significant clinical and research value. Various machine learning approaches have been developed to employ information in EHRs for risk prediction. The majority of these attempts, however, focus on structured EHR fields and lose the vast amount of information in the unstructured texts. To exploit the potential information captured in EHRs, in this study we propose a multimodal recurrent neural network model for cardiovascular risk prediction that integrates both medical texts and structured clinical information. The proposed multimodal bidirectional long short-term memory (BiLSTM) model concatenates word embeddings to classical clinical predictors before applying them to a final fully connected neural network. In the experiments, we compare performance of different deep neural network (DNN) architectures including convolutional neural network and long short-term memory in scenarios of using clinical variables and chest X-ray radiology reports. Evaluated on a data set of real world patients with manifest vascular disease or at high-risk for cardiovascular disease, the proposed BiLSTM model demonstrates state-of-the-art performance and outperforms other DNN baseline architectures.