Deep Diabetologist: Learning to Prescribe Hyperglycemia Medications with Hierarchical Recurrent Neural Networks

TL;DR

This paper introduces Deep Diabetologist, a hierarchical RNN model that predicts personalized hyperglycemia medications for diabetic patients by effectively modeling the sequential EHR data, leading to improved clinical decision support.

Contribution

The paper presents a novel hierarchical RNN architecture tailored for EHR data, enhancing medication prediction accuracy over baseline models.

Findings

Hierarchical RNN outperforms basic RNN and logistic regression models.

Improved prediction accuracy for hyperglycemia medication recommendations.

Provides deeper insights into patient data for clinical decision support.

Abstract

In healthcare, applying deep learning models to electronic health records (EHRs) has drawn considerable attention. EHR data consist of a sequence of medical visits, i.e. a multivariate time series of diagnosis, medications, physical examinations, lab tests, etc. This sequential nature makes EHR well matching the power of Recurrent Neural Network (RNN). In this paper, we propose "Deep Diabetologist" - using RNNs for EHR sequential data modelling, to provide the personalized hyperglycemia medication prediction for diabetic patients. Particularly, we develop a hierarchical RNN to capture the heterogeneous sequential information in the EHR data. Our experimental results demonstrate the improved performance, compared with a baseline classifier using logistic regression. Moreover, hierarchical RNN models outperform basic ones, providing deeper data insights for clinical decision support.