Healthcare Pathway Discovery, Conformance, and Enrichment

ResearchSpace Repository

Show simple item record

dc.contributor.advisor O'Sullivan, M en
dc.contributor.advisor Kempa-Liehr, AW en
dc.contributor.author Lin, Christina en
dc.date.accessioned 2019-06-30T21:38:32Z en
dc.date.issued 2019 en
dc.identifier.uri http://hdl.handle.net/2292/47295 en
dc.description Full Text is available to authenticated members of The University of Auckland only. en
dc.description.abstract Healthcare pathways define the execution sequence of clinical activities as patients move through a treatment process, and they are critical for maintaining quality of care and improving health outcome for all patients. Past studies show that there is potential for informative healthcare pathways to be extracted from hospital health records, but there is currently no consensus on a systematic healthcare pathway mining method that supports explicit design and conformance analysis of concise and comprehensible healthcare pathway models. This study investigates the utilization of business process modelling methods to design a process mining pipeline for healthcare pathway discovery, conformance analysis and enrichment using hospital records. The process mining pipeline is designed with emphasis on producing pathway models that are concise and easy to interpret for clinicians without a sufficient background in process mining. The proposed process mining pipeline is applied to an appendicitis and cholecystitis case study as an example of a simple pathway, and an ambulatory cardiac care case study as an example of a complex pathway. Results from the two case studies indicate that the proposed pipeline designed with business process mining tools is effective for healthcare pathways of different levels of complexity. The produced healthcare pathway models are easy for clinical interpretation and provide an unbiased overview of real patient movements through the treatment process. Preliminary analysis on building machine learning models to predict post-operation length of stay in hospital, using information extracted by the process mining pipeline, is showing promising results. This means that the proposed mining pipeline also has the potential to support the development of machine learning models to further relate healthcare pathways to performance indicators such as readmission rates and mortality rates. This study establishes the use of business process modelling methods for the improvement of healthcare pathway mining methods, and there is value in investigating the capabilities of other business process mining tools for healthcare pathway mining purposes. en
dc.publisher ResearchSpace@Auckland en
dc.relation.ispartof Masters Thesis - University of Auckland en
dc.relation.isreferencedby UoA99265162812502091 en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights Restricted Item. Full Text is available to authenticated members of The University of Auckland only. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/nz/ en
dc.title Healthcare Pathway Discovery, Conformance, and Enrichment en
dc.type Thesis en
thesis.degree.discipline Engineering Science en
thesis.degree.grantor The University of Auckland en
thesis.degree.level Masters en
dc.rights.holder Copyright: The author en
pubs.elements-id 775662 en
pubs.record-created-at-source-date 2019-07-01 en


Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc-sa/3.0/nz/ Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc-sa/3.0/nz/

Share

Search ResearchSpace


Advanced Search

Browse

Statistics