Demographic Aware Probabilistic Medical Knowledge Graph Embeddings of Electronic Medical Records

TL;DR

This paper introduces DARLING, a novel demographic-aware probabilistic embedding framework for medical knowledge graphs derived from EMRs, improving representation learning by integrating patient demographics and probabilistic features.

Contribution

DARLING is the first model to explicitly incorporate demographics and probabilistic information into medical KG embeddings, enhancing task performance.

Findings

DARLING outperforms existing models in link prediction tasks.

Incorporating demographics improves embedding quality.

Probabilistic features contribute to better medical entity representations.

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.