Graph augmented triplet architecture for fine-grained patient similarity
- PDF / 619,355 Bytes
- 14 Pages / 439.642 x 666.49 pts Page_size
- 106 Downloads / 211 Views
Graph augmented triplet architecture for fine-grained patient similarity Yanda Wang1 · Weitong Chen2 · Dechang Pi1
· Robert Boots2
Received: 13 March 2019 / Revised: 6 August 2019 / Accepted: 27 January 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Electronic Health Records (EHRs) provide rich information for the research of multiple healthcare applications that improve chance of survival in Intensive Care Units (ICU), especially the case-based decision support system, which helps physicians make effective clinical decisions in the rapidly changing environment of ICUs according to similar historical patient records. Thus, an efficient approach being able to measure clinically similarities among patients is a fundamental and critical module for the decision support system. In this paper, we propose a novel framework that derives informative EHR graphs from patient records to augment information transmission in Recurrent Neural Networks (RNNs) for fine-grained patient similarity learning, named Graph Augmented Triplet Architecture (GATA). Specifically, GATA firstly derives Dynamic Bayesian Networks (DBNs) from EHRs to reveal correlations among medical variables, then it constructs graph augmented RNNs where each unit aggregate information from variables that it conditionally dependent in DBNs. After that, the specially designed RNNs will act as the fundamental components of the Triplet architecture to measure similarities among patients. GATA has been compared to different baselines based on a real-world ICU dataset MIMIC III, and the experimental results illustrate the effectiveness of GATA in fine-grained patient similarity learning, providing a promising direction for the research on clinical decision support. Keywords Patient similarity · EHRs · Graph augmentation · Triplet architecture
1 Introduction Health Information Technology (HIT) has received enormous attention in recent years while most of the related healthcare applications employ EHRs as a strong supporting evidence, which consist of multiple types of medical information, such as lab measurements and vital This article belongs to the Topical Collection: Special Issue on Application-Driven Knowledge Acquisition Guest Editors: Xue Li, Sen Wang, and Bohan Li Dechang Pi
[email protected]
Extended author information available on the last page of the article.
World Wide Web
signs. Meanwhile, the complex correlations among those medical events makes it a challenging task to obtain the informative underlying patterns in EHRs, which play a critical role in searching for similar patients. As a fundamental component of efficient decision making systems, the study of patient similarity makes an effort to deriving a clinically meaningful measurement of distance to measure the similarities among patients based on ERHs, so that physicians could obtain accurate alternative treatments and diagnoses according to similar historical cases. These derived similar patients also make decisions much more convincing by acting as c
Data Loading...
