Knowledge discovery and anomalies — towards a dynamic decision-making model for medical informatics

dc.contributor.advisorKinghorn, Johannen_ZA
dc.contributor.authorArndt, Heidien_ZA
dc.contributor.otherStellenbosch University. Faculty of Arts and Social Sciences. Dept. of Information Science.en_ZA
dc.date.accessioned2018-01-13T20:25:33Z
dc.date.accessioned2018-04-09T06:52:27Z
dc.date.available2018-01-13T20:25:33Z
dc.date.available2018-04-09T06:52:27Z
dc.date.issued2018-03
dc.descriptionThesis (PhD)--Stellenbosch University, 2018.en_ZA
dc.description.abstractENGLISH SUMMARY : Worldwide healthcare has become a major concern for modern society, which is challenged to make quality care accessible and affordable to all. With a slowing world economy, rapidly rising medical costs and a better-informed customer base, governments and healthcare organisations are under pressure to deliver a product that focuses on quality care, transparent costs and an excellent patient experience. This requires well-informed and nimble operating and decision-making by healthcare organisations, putting pressure on the discipline of informatics within systems. In a comprehensive literature survey, it was found that healthcare organisations are organisations made up of a wide variety of subsystems operating in a complex environment. In addition, there are individualities that challenge the development of health information systems. Bisociative knowledge discovery, which is the creative discovery of previously unknown information from habitually incompatible domains, was introduced as an alternative tool to address the need for decision support in the healthcare sector. It was further found that information networks are a useful way to integrate data from habitually incompatible domains. Lastly, frequent pattern mining was identified as the machine learning tool for mining bisociations within information networks. A knowledge discovery framework for data-intensive research focusing on the field of biomedical informatics was developed in this study. Within this framework, data are represented as integrated, heterogeneous information networks, and machine learning algorithms are applied to the data with the explicit purpose of finding interconnectedness within these structures that can lead to bisociative knowledge discoveries. This framework was further developed into a knowledge discovery process model for bisociative knowledge discovery with a focus on the healthcare sector. The knowledge discovery process model for bisociative knowledge discovery was then applied in a case study which made use of the Nationwide Inpatient Sample data that forms part of the Healthcare Cost and Utilization Project. The case study successfully demonstrated the construction of habitually incompatible domains and their integration into a heterogeneous information network. Furthermore, it demonstrated the application of frequent pattern mining algorithms to extract subgraphs from the constructed information network. This was followed by the constructing of the extracted subgraphs as concept graphs with the purpose of visualising the results for further interpretation. At the end of this research it was concluded that:  The proposed explorative data mining method using bisociative knowledge discovery revealed unexpected, potentially interesting relationships within the constructed information network.  Modelling data from the healthcare sector as an information network allowed visual insights into the structure of the data, which supported the detection of novel insights that otherwise would not have been revealed.  Organisations operating in a complex environment can be successfully unpacked into rich layers of abstraction and the integration of these layers can be automated through computing.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING : Wêreldwyd het gesondheidsorg 'n groot kommer geword vir die moderne samelewing wat uitgedaag word om gehalte versorging toeganklik en bekostigbaar vir almal te maak. Met 'n tanende wêreld ekonomie, toenemende mediese koste en 'n beter ingeligte kliëntebasis, is regerings sowel as gesondheidsorg-organisasies onder toenemende druk om 'n produk te lewer wat fokus op gehalte versorging, deursigtige koste en 'n uitstekende pasiënt ervaring. Dit vereis goed ingeligte en doelgerigte operasies en besluitneming deur gesondheidsorg-organisasies wat weer druk plaas op inligtingstelsels van die gesondheidsorg sektor. In 'n omvattende literatuurstudie is bevind dat gesondheidsorg-organisasies organisasies is wat bestaan uit 'n wye verskeidenheid subsisteme in ʼn komplekse omgewing. Daarbenewens is daar eienaardighede wat die ontwikkeling van gesondheid-inligtingstelsels uitdaag. Bisosiatiewe kennis ontdekking, wat die kreatiewe ontdekking van voorheen onbekende inligting uit onverenigbare domeine is, is ontwikkel as 'n alternatiewe instrument om die behoefte aan besluitneming-ondersteuning in die gesondheidsorg-sektor aan te spreek. Daar is verder bevind dat inligting-netwerke 'n nuttige manier is om data te integreer vanaf onverenigbare domeine. Laastens is gereelde patroon-ontginning geïdentifiseer as die masjienleer-instrument vir die ontginning van bisosiatiewe assosiasies binne inligting-netwerke. ‘n Kennis-ontdekking-raamwerk vir data-intensiewe navorsing gefokus op die veld van biomediese informatika is in hierdie studie ontwikkel. Binne hierdie raamwerk word data as ‘n geïntegreerde, heterogene inligting-netwerk en masjienleer-algoritmes voorgestel, met die uitdruklike doel om inter-konneksies binne hierdie strukture te vind wat tot bisosiatiewe kennis-ontdekking kan lei. Hierdie raamwerk is verder ontwikkel tot 'n kennis-ontdekking-proses model vir bisosiatiewe kennis-ontdekking, gefokus op die gesondheidsorg-sektor. Die kennis-ontdekking-model vir bisosiatiewe kennis ontdekking is dan toegepas in ‘n gevallestudie wat gebruik gemaak het van die “Nationwide Inpatient Sample” data wat deel uitmaak van die “Healthcare Cost and Utilization Project.” Die gevallestudie het die konstruksie van onverenigbare domeine en hul integrasie in 'n heterogene inligting-netwerk suksesvol gedemonstreer. Verder het dit die toepassing van gereelde patroon-ontdekking-algoritmes gedemonstreer om sub-grafieke uit die gekonstrueerde inligting-netwerk te onttrek. Dit is gevolg deur die opbou van die onttrokke sub-grafieke as konsep-grafieke met die doel om die resultate te visualiseer vir verdere interpretasie. Die volgende gevolgtrekkings is gemaak uit die resultate van die navorsing: — Die voorgestelde verkennende data-ontginningsmetode wat gebruik maak van bisosiatiewe kennis-ontdekking het onverwagte, potensieel interessante verwantskappe binne die gekonstrueerde inligting-netwerk openbaar. — Die modellering van gesondheidsorg data as 'n inligting-netwerk het visuele insig in die struktuur van die data toegelaat, wat die opsporing van nuwe insigte ondersteun het wat andersins nie geopenbaar sou wees nie. — En het bewys dat organisasies in komplekse omgewings suksesvol ontleed kan word in ryk lae van abstraksie en die integrasie van hierdie lae kan geoutomatiseer word deur berekening.af_ZA
dc.format.extentxiv, 178 pages ; illustrations, includes annexures
dc.identifier.urihttp://hdl.handle.net/10019.1/103311
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch University
dc.rights.holderStellenbosch University
dc.subjectAlgorithmic knowledge discoveryen_ZA
dc.subjectBiomedical informaticsen_ZA
dc.subjectComplex organisationsen_ZA
dc.subjectBisociative knowledge discoveryen_ZA
dc.subjectUCTD
dc.titleKnowledge discovery and anomalies — towards a dynamic decision-making model for medical informaticsen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
arndt_knowledge_2018.pdf
Size:
4.84 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: