With the rapid accumulation of electronic health record (EHR) data, deep learning (DL) models have exhibited promising performance on patient risk prediction. Recent advances have also demonstrated the effectiveness of knowledge graphs (KG) in providing valuable prior knowledge for further improving DL model performance. However, it is still unclear how KG can be utilized to encode highorder relations among clinical concepts and how DL models can make full use of the encoded concept relations to solve real-world healthcare problems and to interpret the outcomes. We propose a novel knowledge graph guided double attention LSTM model named KGDAL for rolling mortality prediction for critically ill patients with acute kidney injury requiring dialysis (AKI-D). KGDAL constructs a KG-based two-dimension attention in both time and feature spaces. In the experiment with two large healthcare datasets, we compared KGDAL with a variety of rolling mortality prediction models and conducted an ablation study to test the effectiveness, efficacy, and contribution of different attention mechanisms. The results showed that KGDAL clearly outperformed all the compared models. Also, KGDAL-derived patient risk trajectories may assist healthcare providers to make timely decisions and actions. The source code, sample data, and manual of KGDAL are available at https://github.com/lucasliu0928/KGDAL.
|Title of host publication||Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, BCB 2021|
|State||Published - Jan 18 2021|
|Event||12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, BCB 2021 - Virtual, Online, United States|
Duration: Aug 1 2021 → Aug 4 2021
|Name||Proceedings of the 12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, BCB 2021|
|Conference||12th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, BCB 2021|
|Period||8/1/21 → 8/4/21|
Bibliographical noteFunding Information:
This work is supported by NIDDK R56 DK126930 (PI JAN) and P30 DK079337.
© 2021 ACM.
- attention mechanism
- deep learning
- knowledge graph
- rolling mortality prediction
ASJC Scopus subject areas
- Computer Science Applications
- Biomedical Engineering
- Health Informatics