Journal article icon

Journal article

Using ontologies to facilitate healthcare process mining and analysis

Abstract:

Healthcare organisations collect detailed data on the care that they deliver. This data can be used to identify issues, including deviations from care standards and recommendations, and opportunities for improvement; it can be used also to support the development of new technologies and treatments. The volume and complexity of the data means that automated techniques such as process mining are needed to support the extraction and analysis of relevant information. This paper explains how the ontological information held in clinical terminologies can be used to facilitate process extraction and analysis, by connecting and aggregating clinical events through the classification of diagnoses made and treatments performed. The approach is demonstrated through application to data collected on care delivered to patients with cancer in a major hospital. The results are compared with those obtained from benchmark datasets using approaches in which connections and aggregations are proposed and curated by domain experts. This comparison highlights the potential, and the shortcomings, of ontology-based extraction and analysis in healthcare process mining.

Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1007/s10844-025-00942-8

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
Green Templeton College
Role:
Author
ORCID:
0000-0002-7157-6395
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author


More from this funder
Funder identifier:
https://ror.org/0439y7842
Grant:
2432658


Publisher:
Springer
Journal:
Journal of Intelligent Information Systems More from this journal
Volume:
64
Issue:
3
Pages:
989-1009
Publication date:
2025-05-29
Acceptance date:
2025-04-15
DOI:
EISSN:
1573-7675
ISSN:
0925-9902


Language:
English
Keywords:
Pubs id:
2127119
Local pid:
pubs:2127119
Deposit date:
2025-05-29
ARK identifier:

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP