Highrisk Prediction from Electronic Medical Records via Deep Attention Networks

TL;DR

This paper introduces deep attention models that predict high-risk vascular diseases using only symbolic medical histories, outperforming standard models in accuracy and efficiency.

Contribution

The paper proposes novel attention-based deep learning models, R-MeHPAN and C-MeHPAN, for predicting vascular disease risk from medical history sequences, requiring only symbolic data.

Findings

R-MeHPAN achieves higher discriminative performance across metrics.

C-MeHPAN trains faster with comparable accuracy.

Both models outperform standard classification approaches.

Abstract

Predicting highrisk vascular diseases is a significant issue in the medical domain. Most predicting methods predict the prognosis of patients from pathological and radiological measurements, which are expensive and require much time to be analyzed. Here we propose deep attention models that predict the onset of the high risky vascular disease from symbolic medical histories sequence of hypertension patients such as ICD-10 and pharmacy codes only, Medical History-based Prediction using Attention Network (MeHPAN). We demonstrate two types of attention models based on 1) bidirectional gated recurrent unit (R-MeHPAN) and 2) 1D convolutional multilayer model (C-MeHPAN). Two MeHPAN models are evaluated on approximately 50,000 hypertension patients with respect to precision, recall, f1-measure and area under the curve (AUC). Experimental results show that our MeHPAN methods outperform standard classification models. Comparing two MeHPANs, R-MeHPAN provides more better discriminative capability with respect to all metrics while C-MeHPAN presents much shorter training time with competitive accuracy.