Endre søk
Link to record
Permanent link

Direct link
BETA
Otine, Charles
Publikasjoner (4 av 4) Visa alla publikasjoner
Otine, C. (2012). HIV Patient Monitoring Framework Through Knowledge Engineering. (Doctoral dissertation). Karlskrona: Blekinge Institute of Technology
Åpne denne publikasjonen i ny fane eller vindu >>HIV Patient Monitoring Framework Through Knowledge Engineering
2012 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Uganda has registered more than a million deaths since the HIV virus was first offi¬cially reported in the country over 3 decades ago. The governments in partnership with different groups have implemented different programmes to address the epidemic. The support from different donors and reduction in prices of treatment resulted in the focus on antiretroviral therapy access to those affected. Presently only a quarter of the approximately 1 million infected by HIV in Uganda are undergoing antiretroviral therapy. The number of patients pause a challenge in monitoring of therapy given the overall resource needs for health care in the country. Furthermore the numbers on antiretroviral therapy are set to increase in addition to the stringent requirements in tracking and monitoring of each individual patient during therapy. This research aimed at developing a framework for adopting knowledge engineering in information systems for monitoring HIV/AIDS patients. An open source approach was adopted due to the resource constrained context of the study to ensure a cost effec¬tive and sustainable solution. The research was motivated by the inconclusive literature on open source dimensional models for data warehouses and data mining for monitor¬ing antiretroviral therapy. The first phase of the research involved a situational analysis of HIV in health care and different health care information systems in the country. An analysis of the strengths, weaknesses and opportunities of the health care system to adopt knowledge bases was done. It proposed a dimensional model for implementing a data warehouse focused on monitoring HIV patients. The second phase involved the development of a knowledge base inform of an open source data warehouse, its simulation and testing. The study involved interdisciplinary collaboration between different stakeholders in the research domain and adopted a participatory action research methodology. This involved identification of the most appropriate technologies to foster this collabora¬tion. Analysis was done of how stakeholders can take ownership of basic HIV health information system architecture as their expertise grow in managing the systems and make changes to reflect even better results out of system functionality. Data mining simulations was done on the data warehouse out of which two machine learning algorithms (regression and classification) were developed and tested using data from the data warehouse. The algorithms were used to predict patient viral load from CD4 count test figures and to classify cases of treatment failure with 83% accu¬racy. The research additionally presents an open source dimensional model for moni¬toring antiretroviral therapy and the status of information systems in health care. An architecture showing the integration of different knowledge engineering components in the study including the data warehouse, the data mining platform and user interac-tion is presented.

sted, utgiver, år, opplag, sider
Karlskrona: Blekinge Institute of Technology, 2012
Serie
Blekinge Institute of Technology Doctoral Dissertation Series, ISSN 1653-2090 ; 12
Emneord
Action Research, Antiretroviral therapy (ART), AIDS, Classification, Databases, Data Mining, Data Warehousing, Health, ICT, IT, HIV, Open Source, Knowledge Discovery, Knowledge Engineering, Machine Learning, Regression
HSV kategori
Identifikatorer
urn:nbn:se:bth-00540 (URN)oai:bth.se:forskinfo16555DEA6C430965C1257A92002E5654 (Lokal ID)978-91-7295-241-6 (ISBN)oai:bth.se:forskinfo16555DEA6C430965C1257A92002E5654 (Arkivnummer)oai:bth.se:forskinfo16555DEA6C430965C1257A92002E5654 (OAI)
Tilgjengelig fra: 2012-10-31 Laget: 2012-10-09 Sist oppdatert: 2018-01-11bibliografisk kontrollert
Otine, C. (2011). Participatory approach to data warehousing in health care: UGANDA’S Perspective. (Licentiate dissertation). Karlskrona: Blekinge Institute of Technology
Åpne denne publikasjonen i ny fane eller vindu >>Participatory approach to data warehousing in health care: UGANDA’S Perspective
2011 (engelsk)Licentiatavhandling, med artikler (Annet vitenskapelig)
Abstract [en]

This licentiate thesis presents the use of participatory approach to developing a data warehouse for data mining in health care. Uganda is one of the countries that faced the largest brunt of the HIV/AIDS epidemic at its inception in the early 1980s with reports of close to a million deaths. Government and nongovernmental interventions over the years saw massive reductions in HIV prevalence rates over the years. This reduction in HIV prevalence rates led to great praises by the international community and a call for other countries to model Uganda’s approach to battling the epidemic. In the last decade the reduction in HIV prevalence rates have stagnated and in some cases increased. This has lead to a call for reexamination of the HIV/AIDS fight with an emphasis on collective efforts of all approaches. One of these collective efforts is the introduction of antiretroviral therapy (ART) for those already infected with the virus. Antiretroviral therapy has numerous challenges in Uganda not least of which is the cost of the therapy especially on a developing country with limited resources. It is estimated that of the close to 1 million infected in Uganda only 300,000 are on antiretroviral therapy (UNAIDS, 2009). Additional challenges of the therapy includes following through a treatment regimen that is prescribed. Given the costs of the therapy and the limited number of people able to access the therapy it is imperative that this effort be as effective as possible. This research hinges on using data mining techniques with monitoring HIV patient’s therapy, most specifically their adherence to ART medication. This is crucial given that failure to adhere to therapy means treatment failure, virus mutation and huge losses in terms of costs incurred in administering the therapy to the patients. A system was developed to monitor patient adherence to therapy, by using a participatory approach of gathering system specification and testing to ensure acceptance of the system by the stakeholders. Due to the cost implications of over the shelf software the development of the system was implemented using open source software with limited license costs. These can be implemented in resource constrained settings in Uganda and elsewhere to assist in monitoring patients in HIV therapy. A algorithm that is used to analyze the patient data warehouses for information on and quickly assists therapists in identifying potential risks such as non-adherence and treatment failure. Open source dimensional modeling tools power architect and DB designer were used to model the data warehouse using open source MYSQL database. The thesis is organized in three parts with the first part presenting the background information, the problem, justification, objectives of the research and a justification for the use of participatory methodology. The second part presents the papers, on which this research is based and the final part contains the summary discussions, conclusions and areas for future research. The research is sponsored by SIDA under the collaboration between Makerere University and Blekinge Institute of Technology (BTH) in Sweden.

sted, utgiver, år, opplag, sider
Karlskrona: Blekinge Institute of Technology, 2011. s. 77
Serie
Blekinge Institute of Technology Licentiate Dissertation Series, ISSN 1650-2140 ; 4
Emneord
participatory methodology, data warehouse, data mining in health care, HIV AIDS, Uganda
HSV kategori
Identifikatorer
urn:nbn:se:bth-00491 (URN)oai:bth.se:forskinfo3335D8999227CBD5C125784800395616 (Lokal ID)978-91-7295-204-1 (ISBN)oai:bth.se:forskinfo3335D8999227CBD5C125784800395616 (Arkivnummer)oai:bth.se:forskinfo3335D8999227CBD5C125784800395616 (OAI)
Tilgjengelig fra: 2012-09-18 Laget: 2011-03-03 Sist oppdatert: 2015-06-30bibliografisk kontrollert
Otine, C., Kucel, S. B. & Trojer, L. (2010). Dimensional modeling of HIV data using open source. Proceedings of World Academy of Science, Engineering and Technology, 62(March), 156-161
Åpne denne publikasjonen i ny fane eller vindu >>Dimensional modeling of HIV data using open source
2010 (engelsk)Inngår i: Proceedings of World Academy of Science, Engineering and Technology, ISSN 2010-376X, E-ISSN 2070-3740, Vol. 62, nr March, s. 156-161Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Selecting the data modeling technique for an information system is determined by the objective of the resultant data model. Dimensional modeling is the preferred modeling technique for data destined for data warehouses and data mining, presenting data models that ease analysis and queries which are in contrast with entity relationship modeling. The establishment of data warehouses as components of information system landscapes in many organizations has subsequently led to the development of dimensional modeling. This has been significantly more developed and reported for the commercial database management systems as compared to the open sources thereby making it less affordable for those in resource constrained settings. This paper presents dimensional modeling of HIV patient information using open source modeling tools. It aims to take advantage of the fact that the most affected regions by the HIV virus are also heavily resource constrained (sub-Saharan Africa) whereas having large quantities of HIV data. Two HIV data source systems were studied to identify appropriate dimensions and facts these were then modeled using two open source dimensional modeling tools. Use of open source would reduce the software costs for dimensional modeling and in turn make data warehousing and data mining more feasible even for those in resource constrained settings but with data available.

sted, utgiver, år, opplag, sider
World Academy of Science, Engineering and Technology, 2010
Emneord
About database, Data mining, Data warehouse, Dimensional modeling, Open source
HSV kategori
Identifikatorer
urn:nbn:se:bth-7505 (URN)oai:bth.se:forskinfoB896A783E8C46F33C12578BE002A964C (Lokal ID)oai:bth.se:forskinfoB896A783E8C46F33C12578BE002A964C (Arkivnummer)oai:bth.se:forskinfoB896A783E8C46F33C12578BE002A964C (OAI)
Tilgjengelig fra: 2012-09-18 Laget: 2011-06-29 Sist oppdatert: 2017-12-04bibliografisk kontrollert
Otine, C., Kucel, S. B. & Trojer, L. (2007). Knowledge Discovery in Healthcare using Data Mining. Paper presented at the Conference on Collaborative Research for Technological Development. Paper presented at the Conference on Collaborative Research for Technological Development. Kampala
Åpne denne publikasjonen i ny fane eller vindu >>Knowledge Discovery in Healthcare using Data Mining
2007 (engelsk)Konferansepaper, Publicerat paper (Fagfellevurdert) Published
Abstract [en]

The exponential growth of databanks in health care creates opportunities for knowledge generation using data mining. Advancements in information and communication technologies now mean that large quantities of data collected from different sources can be easily stored, secured and retrieved for analysis using databases. For data mining to be carried out the data sets from the different interacting source systems have to be organised in a data warehouse. Data mining offers the potential for exploring hidden patterns in data sets of a particular domain in this case health care. This can eventually be used to perform diagnosis and prognosis on different patient health care condition. Furthermore it places health care providers at a more informed point by enabling predictions hence through classification enhancing generation of new knowledge. This paper provides the state-of-art on data mining and its role on knowledge discovery in the health care sector.

sted, utgiver, år, opplag, sider
Kampala: , 2007
Emneord
Database, Data mining, Data warehousing, Health care, Knowledge discovery
HSV kategori
Identifikatorer
urn:nbn:se:bth-8711 (URN)oai:bth.se:forskinfo3D33589E73EB2618C12573C900396FB1 (Lokal ID)oai:bth.se:forskinfo3D33589E73EB2618C12573C900396FB1 (Arkivnummer)oai:bth.se:forskinfo3D33589E73EB2618C12573C900396FB1 (OAI)
Konferanse
the Conference on Collaborative Research for Technological Development
Tilgjengelig fra: 2012-09-18 Laget: 2008-01-07 Sist oppdatert: 2018-01-11bibliografisk kontrollert
Organisasjoner