Automated Knowledge Graph Construction for Healthcare Domain
Paper
Paper/Presentation Title | Automated Knowledge Graph Construction for Healthcare Domain |
---|---|
Presentation Type | Paper |
Authors | Jaworsky, Markian, Tao, Xiaohui, Yong, Jianming, Pan, Lei, Zhang, Ji and Pokhrel, Shiva |
Journal or Proceedings Title | Proceedings of the 11th International Conference on Health Information Science (HIS 2022) |
Journal Citation | 13705, pp. 258-265 |
Number of Pages | 8 |
Year | 2022 |
Place of Publication | Switzerland |
ISBN | 9783031206276 |
9783031206269 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-031-20627-6_24 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007/978-3-031-20627-6_24 |
Web Address (URL) of Conference Proceedings | https://link.springer.com/book/10.1007/978-3-031-20627-6 |
Conference/Event | 11th International Conference on Health Information Science (HIS 2022) |
Event Details | 11th International Conference on Health Information Science (HIS 2022) Parent International Conference on Health Information Science (HIS) Event Date 28 to end of 30 Oct 2022 Event Location Biarritz, France |
Abstract | This research seeks to optimize the process of identifying correlations in common and high severity diseases via the fusion of knowledge graphs and deep learning artificial intelligence. Knowledge graphs can be complicated to construct and resource-intensive, alternatively, knowledge graphs can be seen to legitimize correlation incidence and better explain AI outputs. We propose automation of knowledge graph construction from identifying significant text frequency relations within established knowledge base document structures to identifying inter-feature relations and creating a novel approach for artificial intelligence and machine-learning feature extraction and feature selection. Our knowledge graph construction exploits the structured World Health Organization (WHO) International Classification of Disease (ICD) code chapters, which are specific to a single organ system of the human body. A sorted vector of text-to-chapter frequencies enables Wilcox Rank significance tests to determine the most related features. |
Keywords | Knowledge graphs; Feature selection; Risk factors; Chronic illness |
ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Series | Lecture Notes in Computer Science |
Byline Affiliations | School of Mathematics, Physics and Computing |
School of Business | |
Deakin University |
https://research.usq.edu.au/item/z58yx/automated-knowledge-graph-construction-for-healthcare-domain
107
total views1
total downloads6
views this month0
downloads this month