Currently submitted to: JMIR AI
Date Submitted: Nov 9, 2026
Open Peer Review Period: Nov 17, 2026 - Jan 12, 2027
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Generating a knowledge graph to understand the mechanistic relationships between multimorbid diabetes, hypertension and kidney diseases
ABSTRACT
Background:
Multimorbidity, defined as the coexistence of two or more chronic diseases, poses significant challenges to patient care. Multimorbid diseases share certain risk factors and can exacerbate each other’s effects. Understanding the mechanistic relationships between diseases is crucial for improving patient outcomes.
Objective:
This study explores the use of a knowledge graph to identify shared risk factors, common biological pathways, and key disease interactions contributing to the development and progression of these multimorbid diabetes, hypertension and kidney disease.
Methods:
We used a literature-based knowledge graph generation framework that involved data collection from published text and databases, triples extraction and filtering, representation of extracted concepts as a knowledge graph and pattern analysis to understand the intricate relationship between multimorbid diseases (Diabetes, hypertension and kidney disease)
Results:
Our multimorbidity KG consisted of 4,391 unique nodes and 10,083 edges, representing relationships between diabetes, hypertension, kidney diseases and other related entities. For the KG nodes, the most common categories were diseases (18.5%), biomolecules (16.5%) and drugs (11.3%), and the most common relationships were ‘location of’ (17.8%), ‘treats’ (10.0%) and ‘causes’ (10.0%). Queries conducted on the knowledge graph identified shared risk factors among diabetes, hypertension, and kidney disease, highlighting the interconnected nature of multimorbid conditions.
Conclusions:
Multimorbid diseases often interact with each other and with the patient in unpredictable ways, due to differing patient characteristics as well as the concurrent use of multiple medications. Our graph provided valuable insights into drug-disease interactions, demonstrating that while a drug may be beneficial for a specific condition, it could also exacerbate the other condition in multimorbid setting. Although we demonstrate the effectiveness of knowledge graphs in elucidating complex disease interactions, limitations such as data integration challenges and terminology discrepancies were noted. Future work could explore developing automated or semi-automated tools to standardize terminologies and map concepts from different sources.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.