Home
JournalsCollections
For Authors For Reviewers For Editorial Board Members
Article Processing Charges Open Access
Ethics Advertising Policy
Editorial Policy Resource Center
Company Information Contact Us Membership Collaborators Partners
OPEN ACCESS

Identification of Cirrhosis Subtypes Through Heterogeneous Medical Information Network

  • Jun Li1,
  • Xin Dong5,
  • Ya-Na Zhou1,2,3,4,
  • Hui-Kun Wu1,2,3,4,
  • Xiao-Dong Li1,2,3,4,* and
  • Xue-Zhong Zhou5,*
Gastroenterology & Hepatology Research   2022;4(3):14

doi: 10.53388/ghr2022-09-056

Published online:

 Author information

Citation: Li J, Dong X, Zhou YN, Wu HK, Li XD, Zhou XZ. Identification of Cirrhosis Subtypes Through Heterogeneous Medical Information Network. Gastroenterol & Hepatol Res. 2022;4(3):14. doi: 10.53388/ghr2022-09-056.

Abstract

Background

Liver cirrhosis is a complex and heterogeneous disease, with a mortality rate of up to 57%, resulting in 1.03 million deaths per year. The prevalence of liver cirrhosis is on the rise. Patients with liver cirrhosis have a variety of clinical phenotypes and are prone to various complications related to liver cirrhosis. Therefore, there is an urgent need to improve the early prevention and clinical management of cirrhosis and its complications.

Methods

We use a precise medical approach to analyze and characterize the complex manifestations of cirrhotic patient populations, and we propose a Heterogeneous Medical Record Network (HEMnet) that includes electronic medical records, molecular interaction networks, and domain knowledge. We train the network embedding vector on HEMnet to obtain the low-dimensional vector representation of each node. With these vectors, we enriched the original medical record and identified six subtypes of cirrhosis.

Results

Subtype 1 is characterized by heart disease, and subtype 2 has the strongest association with metabolic-related diseases. Subtype 3 was characterized by Chronic gastritis diseases. Subtype 4 was characterized by Liver cirrhosis-related complications-serous effusion. Subtype 5 had the strongest association with hepatitis-cirrhosis-related complications diseases and gallbladder disease. Subtype 6 was most strongly associated with Liver cirrhosis-related complications and hepatic carcinoma. By assessing the human disease-gene association of each subtype, the rich phenotype and biological functions of each subtype at the gene level were matched to the disease comorbidities and clinical differences we identified through EHR.

Conclusion

Our approach demonstrates the utility of applying a precision medicine paradigm to cirrhosis and the prospect of extending this approach to other complexes, multifactorial diseases.

Keywords

heterogeneous medical record network, liver cirrhosis, subtype, characteristics

About this Article

Cite this article
Li J, Dong X, Zhou YN, Wu HK, Li XD, Zhou XZ. Identification of Cirrhosis Subtypes Through Heterogeneous Medical Information Network. Gastroenterol & Hepatol Res. 2022;4(3):14. doi: 10.53388/ghr2022-09-056.
Copy Export to RIS Export to EndNote
Article History
Received Revised Accepted Published
September 25, 2022
DOI http://dx.doi.org/10.53388/ghr2022-09-056