Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records
Publication date
2021-03-22
Document type
Book part
Author
Organisational unit
University of Bonn
Scopus ID
ISBN
ISSN
E-ISSN
Conference
19th International Conference on Artificial Intelligence in Medicine, AIME 2021, Virtual Event, June 15–18, 2021
Series or journal
Lecture Notes in Computer Science
Book title
Artificial Intelligence in Medicine
First page
408
Last page
417
Peer-reviewed
✅
Part of the university bibliography
Nein
Keyword
Demographics Probabilistic medical knowledge graph
Electronic medical record
Knowledge graph embedding
Abstract
Medical knowledge graphs (KGs) constructed from Electronic Medical Records (EMR) contain abundant information about patients and medical entities. The utilization of KG embedding models on these data has proven to be efficient for different medical tasks. However, existing models do not properly incorporate patient demographics and most of them ignore the probabilistic features of the medical KG. In this paper, we propose DARLING (Demographic Aware pRobabiListic medIcal kNowledge embeddinG), a demographic-aware medical KG embedding framework that explicitly incorporates demographics in the medical entities space by associating patient demographics with a corresponding hyperplane. Our framework leverages the probabilistic features within the medical entities for learning their representations through demographic guidance. We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.
Version
Not applicable (or unknown)
Access right on openHSU
Metadata only access