nilesh981/KGDAL

KGDAL: Knowledge Graph Guided Double Attention LSTM for Rolling Mortality Prediction for AKI-D Patients

Table of contents

• General info
• Setup
• Code sections
• Status
• Contact

General info

1. KGDAL obtains two-dimensional attention in both the time and feature spaces for improved prediction power and enhanced model interpretability.
2. The attention mechanism in the feature space is automatically derived based on the KG rather than manual curation. %as a guidance to build the attention mechanism
3. KGDAL can model both continuous and discrete temporal EHR data types.
4. KGDAL can make precise rolling mortality predictions for AKI-D patients on two independent clinical datasets.

Setup

Describe how to install / setup your local environement / add link to demo version.

Code sections

Code Examples

Status

Project is: in progress for final cleaning and organizing

Contact

Created by Lucas J. Liu (jli394@uky.edu) - feel free to contact me!