Effective Medical Archives Processing Using Knowledge Graphs

被引：5

作者：

Wang, Xiaoli ^{[1
]}

Wang, Rongzhen ^{[2
]}

Bao, Zhifeng ^{[3
]}

Liang, Jiayin ^{[1
]}

Lu, Wei ^{[4
]}

机构：

[1] Xiamen Univ, Xiamen, Fujian, Peoples R China

[2] Quanzhou Med Coll, Quanzhou, Fujian, Peoples R China

[3] RMIT Univ, Melbourne, Vic, Australia

[4] Renmin Univ China, Beijing, Peoples R China

来源：

PROCEEDINGS OF THE 42ND INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '19) | 2019年

关键词：

Medical archives processing; Medical information system; Knowledge graphs;

D O I：

10.1145/3331184.3331350

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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 task. This measure can value semantic relatedness between medical documents, to enhance the text classification. We use medical archives collected from real hospitals for validation. The results show that our algorithms can significantly outperform typical baselines that employs only term statistics.

引用

页码：1141 / 1144

页数：4

共 13 条

[1] AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].

ALTMAN, NS .

AMERICAN STATISTICIAN, 1992, 46 (03) :175-185

[2]

Carpineto C, 2009, LECT NOTES ARTIF INT, V5548, P237

[3]

Hughes M, 2017, STUD HEALTH TECHNOL, V235, P246, DOI 10.3233/978-1-61499-753-5-246

[4]

Kuhn H. W., 2004, NAV RES LOG, V1, P7, DOI DOI 10.1002/nav.20053

[5]

Lakiotaki Kleanthi, 2013, Health Information Science. Second International Conference, HIS 2013. Proceedings, P93, DOI 10.1007/978-3-642-37899-7_8

[6]

Lee C., 2017, Big Healthcare Data Analytics: Challenges and Applications, P11

[7]

Li Xiang, 2015, AMIA Annu Symp Proc, V2015, P833

[8] Special issue on deep learning for document analysis and recognition [J].

Liu, Cheng-Lin ;

Fink, Gernot A. ;

Govindaraju, Venu ;

Jin, Lianwen .

INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2018, 21 (03) :159-160

[9] QALink: Enriching Text Documents with Relevant Q&A Site Contents [J].

Tang, Yixuan ;

Huang, Weilong ;

Liu, Qi ;

Tung, Anthony K. H. ;

Wang, Xiaoli ;

Yang, Jisong ;

Zhang, Beibei .

CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, :1359-1368

[10]

Tarau P, 2004, P 2004 C EMP METH NA, P404

← 1 2 →