University of Birmingham
Ontology and text mining: methods and applications for hypertrophic cardiomyopathy and beyond
Abstract
dc:description.abstractIn this thesis we describe a number of contributions across the deeply interlinked domains of ontology, text mining, and prognostic modelling. We explore and evaluate ontology interoperability, and develop new methods for synonym expansion and negation detection in biomedical text. In addition to evaluating these pieces of work individually, we use them to form the basis of a text mining pipeline that can identify and phenotype patients across a clinical text record, which is used to reveal hundreds of University Hospitals Birmingham patients diagnosed with hypertrophic cardiomyopathy who are unknown to the specialist clinic. The work culminates in the text mining results being used to enable prognostic modelling of complication development in patients with hypertrophic cardiomyopathy, finding that routine blood markers, in addition to already well known variables, are powerful predictors.
Degree
thesis:*- Name dc:type.qualificationname
- d_ph
- Level dc:type.qualificationlevel
- d_ph
- Grantor dc:publisher.institution
- University of Birmingham
- Year dc:date.issued
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Slater, Luke Thomas
Subjects
dc:subject × 1Rights
- Language dc:language.dcterms_iso639_2
- eng