Learning a Health Knowledge Graph from Electronic Medical Records

By Maya Rotmensch, Yoni Halpern, Abdulhakim Tlimat, Steven Horng, David A. Sontag. Scientific Reports, 2017

413 citations recorded by the source corpus.

Demand for clinical decision support systems in medicine and self-diagnostic symptom checkers has substantially increased in recent years. Existing platforms rely on knowledge bases manually compiled through a labor-intensive process or automatically derived using simple pairwise statistics. This study explored an automated process to learn high quality knowledge bases linking diseases and symptoms directly from electronic medical records. Medical concepts were extracted from 273,174 de-identified patient records and maximum likelihood estimation of three probabilistic models was used to automatically construct knowledge graphs: logistic regression, naive Bayes classifier and a Bayesian network using noisy OR gates. A graph of disease-symptom relationships was elicited from the learned parameters and the constructed knowledge graphs were evaluated and validated, with permission, against Google’s manually-constructed knowledge graph and against expert physician opinions. Our study shows that direct and automated construction of high quality health knowledge graphs from medical records using rudimentary concept extraction is feasible. The noisy OR model produces a high quality knowledge graph reaching precision of 0.85 for a recall of 0.6 in the clinical evaluation. Noisy OR significantly outperforms all tested models across evaluation frameworks (p < 0.01).

Subfields: Artificial Intelligence, Health Information Management, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/8b0de2074bb42a55395efd7e95503bd74736cdd7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Information Management

In Molecular Biology

Citations in the corpus

A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “For example, [246], [247] and [248] both perform reasoning on the KG constructed from the electronic medical database.”
A Survey on Application of Knowledge Graph (2020, background): “Rotmensch et al. [40] propose an approach to generate a graph mapping diseases to the symptoms, which might cause from electronic medical record (EMR) data automatically.”
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks (2020, background): “Second, it would be interesting to explore the possibility of deploying GNNGUARD for key GNN applications in biomedical domain, where, for example, a GNN diagnostics system could predict false diagnosis if it was trained on the attacked knowledge graph [57].”
Graph Representation Learning in Biomedicine and Healthcare (2021, positive): “Methods that embed medical entities, including EHRs and medical ontologies, leverage the inherently hierarchical structure of knowledge graphs of medical concepts 187 .”
Answering Visual-Relational Queries in Web-Extracted Knowledge Graphs (2017, background): “ where typed edges represent customer reviews and purchasing events. In the medical domain, there are several knowledge graphs that model diseases, symptoms, drugs, genes, and their interactions (cf. [2, 51, 36]). In the online retail domain, there are product and advertising images. In the medical ”
Graph embedding on biomedical networks: methods, applications and evaluations (2019, positive): “, 2018f), and assisting clinical decision making via disease-symptom graphs (Rotmensch et al., 2017).”
Deep Reinforcement Learning (2018, background): “ical record (EHR/EMR).Li et al. (2018b) propose a hybrid retrieval-generation reinforced agent for medical image report generation.Rajkomar et al.(2018) investigate applying deep learning to EHR data.Rotmensch et al. (2017) learn a healthcare knowledge graph from EHR.Fauw et al.(2018) apply deep lea”
Representation Learning for Visual-Relational Knowledge Graphs (2017, background): “In the medical domain, there are several knowledge graphs that model diseases, symptoms, drugs, genes, and their interactions (cf. [2, 36, 51]).”
Retrieval And Structuring Augmented Generation with Large Language Models (2025, unknown): “For example, Rotmensch et al. [212] integrates annotated medical records with existing KGs to build a health-related KG. PAIR [59] uses LLMs as relation filters to streamline relation discovery in online marketing.”