Semantic Health Knowledge Graph: Semantic Integration of Heterogeneous Medical Knowledge and Services.

Longxiang Shi,Shijian Li,Jiaheng Qi,Binbin Zhou,Xiaoran Yang,Gang Pan

doi:10.1155/2017/2858423

Longxiang Shi, Shijian Li + Show 4 more

Open Access

https://doi.org/10.1155/2017/2858423

Copy DOI

Abstract

With the explosion of healthcare information, there has been a tremendous amount of heterogeneous textual medical knowledge (TMK), which plays an essential role in healthcare information systems. Existing works for integrating and utilizing the TMK mainly focus on straightforward connections establishment and pay less attention to make computers interpret and retrieve knowledge correctly and quickly. In this paper, we explore a novel model to organize and integrate the TMK into conceptual graphs. We then employ a framework to automatically retrieve knowledge in knowledge graphs with a high precision. In order to perform reasonable inference on knowledge graphs, we propose a contextual inference pruning algorithm to achieve efficient chain inference. Our algorithm achieves a better inference result with precision and recall of 92% and 96%, respectively, which can avoid most of the meaningless inferences. In addition, we implement two prototypes and provide services, and the results show our approach is practical and effective.

Highlights

As an indispensable part of today’s healthcare information systems (HIS), textual medical knowledge (TMK) plays a pivotal role in healthcare knowledge delivery and decision support to both patients and medical practitioners [1, 2]
In this paper we study two types of textual medical knowledge sources: open healthcare contents from the web and a medical book [20] which was retrieved by Optical Character Recognition (OCR) technique
(a) Model: our model provides the requirements of the facts retrieving framework: Medical Knowledge Model (MKM) provides the relations that need to be retrieved from knowledge sources; Terminology Glossary (TG) provides terminology dictionaries for entity recognition

Summary

Introduction

As an indispensable part of today’s healthcare information systems (HIS), textual medical knowledge (TMK) plays a pivotal role in healthcare knowledge delivery and decision support to both patients and medical practitioners [1, 2]. There has emerged a tremendous amount of TMK, which is aroused by continuous digitalization of medical literature, ongoing expansion of biomedical knowledge, and rapid proliferation of hierarchical online healthcare providers Facing such tremendous amount of heterogeneous TMK, it has become a challenge to organize and integrate relevant information, and provide useful processed information to users with an efficient approach. Computation systems cannot interpret human knowledge and serve inefficiently when performing complex queries such as acquiring syntactic, semantic, and structural information behind the vast TMK. Their knowledge bases are always manually managed and updated, are unable to cope with the proliferation of TMK [5, 6, 8,9,10]. An efficient TMK integrating and delivering method is imperative

Objectives

Methods

Findings

Conclusion