Ontology based Baysian network for clinical specialty supporting in interactive question answering systems. Issue 7 (2nd October 2017)

• Record Type: Journal Article
• Authors: Yeh, Jui-Feng; Huang, Yu-Jui; Huang, Kao-Pin
• Is Part Of: Engineering computations. Volume 34:Issue 7(2017)
• Page Start: 2435
• Page End: 2447
• Publication Date: 2017-10-02
• Subjects: Ontology -- Baysian network -- Clinical specialty supporting -- Interactive question answering systems; Computer-aided engineering -- Periodicals; Computer graphics -- Periodicals; 620.00285
• DOI: 10.1108/EC-03-2017-0073
• Languages: English
• ISSNs: 0264-4401

Abstract

Abstract : Purpose: This study aims to provide an ontology based Baysian network for clinical specialty supporting. As a knowledge base, ontology plays an essential role in domain applications especially in expert systems. Interactive question answering systems are suitable for personal domain consulting and recommended for real-time usage. Clinical specialty supporting for dispatching patients can assist hospitals to locate desired treatment departments for individuals relevant to their syndromes and disease efficiently and effectively. By referring to interactive question answering systems, individuals can understand how to alleviate time and medical resource wasting according to recommendations from medical ontology-based systems. Design/methodology/approach: This work presents an ontology based on clinical specialty supporting using an interactive question answering system to achieve this aim. The ontology incorporates close temporal associations between words in input query to represent word co-occurrence relationships in concept space. The patterns defined in lexicon chain mechanism are further extracted from the query words to infer related concepts for treatment departments to retrieve information. Findings: The precision and recall rates are considered as the criteria for model optimization. Finally, the inference-based interactive question answering system using natural language interface is adopted for clinical specialty supporting, and indicates its superiority in information retrieval over traditional approaches. Originality/value: From the observed experimental results, we find the proposed method is useful in practice especially in treatment department decision supporting using metrics precision and recall rates. The interactive interface using natural language dialogue attracts the users' attention and obtains a good score in mean opinion score measure.