Conference Proceedings

Effective medical archives processing using knowledge graphs

X Wang, R Wang, Z Bao, J Liang, W Lu

SIGIR 2019 Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval | ASSOC COMPUTING MACHINERY | Published : 2019

Abstract

Medical archives processing is a very important task in a medical information system. It generally consists of three steps: medical archives recognition, feature extraction and text classification. In this paper, we focus on empowering the medical archives processing with knowledge graphs. We first build a semantic-rich medical knowledge graph. Then, we recognize texts from medical archives using several popular optical character recognition (OCR) engines, and extract keywords from texts using a knowledge graph based feature extraction algorithm. Third, we define a semantic measure based on knowledge graph to evaluate the similarity between medical texts, and perform the text classification ..

View full abstract

University of Melbourne Researchers

Grants

Awarded by Appalachian Regional Commission


Funding Acknowledgements

This work was supported by NSFC (61702432), the Fundamental Research Funds for Central Universities of China (20720180070) and the International Cooperation Projects of Fujian in China (2018I0016). This work was partially supported by the Research Funds administered by the Digital Fujian, at the Big Data Institute for Urban Public Safety. Rongzhen Wang was partially supported by Research Funds of Fujian Province for Young Teachers (JAS161068). Zhifeng Bao was partially supported by ARC (DP170102726, DP180102050) and NSFC (61728204, 91646204), and is a recipient of Google Faculty Award. Wei Lu was partially supported by Beijing Municipal Science and Technology Project (Z171100005117002) and NSFC (U1711261).