Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records

03/22/2021
by   Aynur Guluzade, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/17/2017

PDD Graph: Bridging Electronic Medical Records and Biomedical Knowledge Graphs via Entity Linking

Electronic medical records contain multi-format electronic medical data ...
research
10/07/2019

Representation Learning of EHR Data via Graph-Based Medical Entity Embedding

Automatic representation learning of key entities in electronic health r...
research
06/20/2023

Intersectionality and Testimonial Injustice in Medical Records

Detecting testimonial injustice is an essential element of addressing in...
research
09/02/2019

PrTransH: Embedding Probabilistic Medical Knowledge from Real World EMR Data

This paper proposes an algorithm named as PrTransH to learn embedding ve...
research
09/20/2017

EMR-based medical knowledge representation and inference via Markov random fields and distributed representation learning

Objective: Electronic medical records (EMRs) contain an amount of medica...
research
06/06/2018

Medical Concept Embedding with Time-Aware Attention

Embeddings of medical concepts such as medication, procedure and diagnos...
research
12/24/2018

PatientEG Dataset: Bringing Event Graph Model with Temporal Relations to Electronic Medical Records

Medical activities, such as diagnoses, medicine treatments, and laborato...

Please sign up or login with your details

Forgot password? Click here to reset