Dataset Information

Developing an ontology for representing the domain knowledge specific to non-pharmacological treatment for agitation in dementia.

ABSTRACT: Introduction:A large volume of clinical care data has been generated for managing agitation in dementia. However, the valuable information in these data has not been used effectively to generate insights for improving the quality of care. Application of artificial intelligence technologies offers us enormous opportunities to reuse these data. For health data science to achieve this, this study focuses on using ontology to coding clinical knowledge for non-pharmacological treatment of agitation in a machine-readable format. Methods:The resultant ontology-Dementia-Related Agitation Non-Pharmacological Treatment Ontology (DRANPTO)-was developed using a method adopted from the NeOn methodology. Results:DRANPTO consisted of 569 concepts and 48 object properties. It meets the standards for biomedical ontology. Discussion:DRANPTO is the first comprehensive semantic representation of non-pharmacological management for agitation in dementia in the long-term care setting. As a knowledge base, it will play a vital role to facilitate the development of intelligent systems for managing agitation in dementia.

SUBMITTER: Zhang Z

PROVIDER: S-EPMC7507392 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Developing an ontology for representing the domain knowledge specific to non-pharmacological treatment for agitation in dementia.

Zhang Zhenyu Z Yu Ping P Chang Hui Chen Rita HCR Lau Sim Kim SK Tao Cui C Wang Ning N Yin Mengyang M Deng Chao C

Alzheimer's & dementia (New York, N. Y.) 20200901 1

<h4>Introduction</h4>A large volume of clinical care data has been generated for managing agitation in dementia. However, the valuable information in these data has not been used effectively to generate insights for improving the quality of care. Application of artificial intelligence technologies offers us enormous opportunities to reuse these data. For health data science to achieve this, this study focuses on using ontology to coding clinical knowledge for non-pharmacological treatment of agi ...[more]

PMID: 32995470

Similar Datasets

Project description:BACKGROUND: Biobanks are a critical resource for translational science. Recently, semantic web technologies such as ontologies have been found useful in retrieving research data from biobanks. However, recent research has also shown that there is a lack of data about the administrative aspects of biobanks. These data would be helpful to answer research-relevant questions such as what is the scope of specimens collected in a biobank, what is the curation status of the specimens, and what is the contact information for curators of biobanks. Our use cases include giving researchers the ability to retrieve key administrative data (e.g. contact information, contact's affiliation, etc.) about the biobanks where specific specimens of interest are stored. Thus, our goal is to provide an ontology that represents the administrative entities in biobanking and their relations. We base our ontology development on a set of 53 data attributes called MIABIS, which were in part the result of semantic integration efforts of the European Biobanking and Biomolecular Resources Research Infrastructure (BBMRI). The previous work on MIABIS provided the domain analysis for our ontology. We report on a test of our ontology against competency questions that we derived from the initial BBMRI use cases. Future work includes additional ontology development to answer additional competency questions from these use cases. RESULTS: We created an open-source ontology of biobank administration called Ontologized MIABIS (OMIABIS) coded in OWL 2.0 and developed according to the principles of the OBO Foundry. It re-uses pre-existing ontologies when possible in cooperation with developers of other ontologies in related domains, such as the Ontology of Biomedical Investigation. OMIABIS provides a formalized representation of biobanks and their administration. Using the ontology and a set of Description Logic queries derived from the competency questions that we identified, we were able to retrieve test data with perfect accuracy. In addition, we began development of a mapping from the ontology to pre-existing biobank data structures commonly used in the U.S. CONCLUSIONS: In conclusion, we created OMIABIS, an ontology of biobank administration. We found that basing its development on pre-existing resources to meet the BBMRI use cases resulted in a biobanking ontology that is re-useable in environments other than BBMRI. Our ontology retrieved all true positives and no false positives when queried according to the competency questions we derived from the BBMRI use cases. Mapping OMIABIS to a data structure used for biospecimen collections in a medical center in Little Rock, AR showed adequate coverage of our ontology.

Dataset Information

Developing an ontology for representing the domain knowledge specific to non-pharmacological treatment for agitation in dementia.

Publications

Developing an ontology for representing the domain knowledge specific to non-pharmacological treatment for agitation in dementia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets