Graph-based multi-label disease prediction model learning from medical data and domain knowledge
Article
Article Title | Graph-based multi-label disease prediction model learning from medical data and domain knowledge |
---|---|
ERA Journal ID | 18062 |
Article Category | Article |
Authors | Pham, Thuan (Author), Tao, Xiaohui (Author), Zhang, Ji (Author), Yong, Jianming (Author), Li, Yuefeng (Author) and Xie, Haoran (Animator) |
Journal Title | Knowledge-Based Systems |
Journal Citation | 235, pp. 1-15 |
Article Number | 107662 |
Number of Pages | 15 |
Year | 2022 |
Publisher | Elsevier |
Place of Publication | Netherlands |
ISSN | 0950-7051 |
1872-7409 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.knosys.2021.107662 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0950705121009242 |
Abstract | In recent years, the means of disease diagnosis and treatment have been improved remarkably, along with the continuous development of technology and science. Researchers have spent tremendous time and effort to build models, with an aim to assist medical practitioners in decision-making support. One of the greatest challenges remains is how to identify the connection between different diseases. This study aims to discover the relationship between diseases and symptoms and predict potential diseases for patients. Considering it a multi-label classification problem, the study proposed a new multi-disease prediction model learning from NHANES, an extensive health related dataset, and MEDLINE, a corpus with medical domain knowledge. A heterogeneous information graph is firstly constructed and then populated using medical domain knowledge discovered from MEDLINE. The knowledge graph is analysed for clarification of the relevancy within nodes in positive or negative space, helping to access to the correlation amongst multiple diseases and their symptoms. A multi-label disease prediction model is then developed adopting the medical domain knowledge graph. Empirical experiments are conducted to evaluate the proposed model. The experimental results show that the performance of the proposed model surpassed state-of-the-art related works representing the mainstreams of multi-label classification. This study contributes with a novel model for multi-disease prediction to the medical community and represents a new endeavour on multi-label classification using knowledge graphs. |
Keywords | Multi-label classification; Knowledge graph; Medicine domain knowledge; Disease prediction; NHANES; MEDLINE |
ANZSRC Field of Research 2020 | 420308. Health informatics and information systems |
460902. Decision support and group support systems | |
460502. Data mining and knowledge discovery | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | School of Sciences |
School of Business | |
Queensland University of Technology | |
Lingnan Normal University, China | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q6w0x/graph-based-multi-label-disease-prediction-model-learning-from-medical-data-and-domain-knowledge
256
total views5
total downloads1
views this month0
downloads this month