2022
DOI: 10.1101/2022.01.07.475444
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

A graph-embedded topic model enables characterization of diverse pain phenotypes among UK Biobank individuals

Abstract: Large biobank repositories of clinical conditions and medications data open opportunities to investigate the phenotypic disease network. To enable systematic investigation of entire structured phenomes, we present graph embedded topic model (GETM). We offer two main methodological contributions in GETM. First, to aid topic inference, we integrate existing biomedical knowledge graph information in the form of pre-trained graph embedding into the embedded topic model. Second, leveraging deep learning techniques,… Show more

Help me understand this report
View published versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 30 publications
0
3
0
Order By: Relevance
“…We considered it as a baseline because it has a similar generative process as GAT-ETM but does not utilize knowledge graph. • GETM 28 is an embedded topic model that leverages ICD and ATC medical taxonomy hierarchies by initializing word embedding as the output of node2vec. Note that GETM obtains code embedding on only ICD and ATC taxonomy hierarchies respectively.…”
Section: Data Processing To Evaluate Our Model We Used a Real-world L...mentioning
confidence: 99%
“…We considered it as a baseline because it has a similar generative process as GAT-ETM but does not utilize knowledge graph. • GETM 28 is an embedded topic model that leverages ICD and ATC medical taxonomy hierarchies by initializing word embedding as the output of node2vec. Note that GETM obtains code embedding on only ICD and ATC taxonomy hierarchies respectively.…”
Section: Data Processing To Evaluate Our Model We Used a Real-world L...mentioning
confidence: 99%
“…These recent models are mostly focused on supervision, and their learning algorithms require labelled data. In contrast, GETM [28] leveraged a knowledge graph by combining node2vec [29] with embedded topic model (ETM) [30] in a pipeline approach. GETM is an unsupervised model that directly learn the distribvution of the EHR data using the node2vec embedding.…”
Section: Related Workmentioning
confidence: 99%
“…• GETM [28] is an embedded topic model that leverages ICD and ATC medical taxonomy hierarchies by initializing word embedding as the output of node2vec. Note that GETM obtain code embedding on only ICD and ATC taxonomy hierarchies respectively.…”
Section: Baselinesmentioning
confidence: 99%