An intelligent risk detection model to improve decision efficiency in healthcare contexts: the case of paediatric congenital heart disease

Moghimi, H 2014, An intelligent risk detection model to improve decision efficiency in healthcare contexts: the case of paediatric congenital heart disease, Doctor of Philosophy (PhD), Business IT and Logistics, RMIT University.


Document type: Thesis
Collection: Theses

Attached Files
Name Description MIMEType Size
Moghimi.pdf Thesis application/pdf 3.57MB
Title An intelligent risk detection model to improve decision efficiency in healthcare contexts: the case of paediatric congenital heart disease
Author(s) Moghimi, H
Year 2014
Abstract Objectives: Healthcare is an information rich industry where successful outcomes require the processing of multi-spectral data and sound decision making. The exponential growth of data and big data issues coupled with a rapid increase of service demands in healthcare contexts today, requires a robust framework enabled by IT (information technology) solutions as well as real-time service handling in order to ensure superior decision making and successful healthcare outcomes. Such a context is appropriate for the application of a real time intelligent risk detection decision support systems using business analytics and data science technologies. To illustrate the power and potential of business analytics and data science technologies in healthcare decision making scenarios, the use of an Intelligent Risk Detection (IRD) Model is proffered for the context of Congenital Heart Disease (CHD) in children, an area which requires complex high risk decisions that need to be made expeditiously and accurately in order to ensure successful healthcare outcomes. The main aim of this research is reducing burden of complex surgeries in patients, their family and society through early detecting of surgical risk factors prior to surgery. The research question is: How can an intelligent risk detection (IRD) Model be developed in the healthcare contexts?

Method: This study is exploratory in nature and endeavours to explore the main components, barriers, issues and requirement to design and develop an Intelligent Risk Detection framework to be applied to healthcare contexts. In this research a qualitative approach using an exemplar data site as a single case study is adapted to address research objectives and to answer the research question. Data collection is through semi-structured interviews, questionnaires, observation and the analysis of documents, files and data bases from the study site. After conducting the data collection phase thematic analysis is applied to analyse all collected qualitative data.

Results: This study has a significant contribution to practice and theory; namely confirming a role for business analytics and data science technologies in healthcare contexts. Also, this research serves to demonstrate that the selection of risk detection, prediction by data mining tools as one of the data science techniques and then decision support are very important for decision making in the complex surgeries. IRD, in practice, can also be used as a training tool to train nurses and medical students to detect the CHD surgery risk factors and their impact on surgery outcomes. Moreover, it can also provide decision support to assist doctors to make better clinical and surgical decisions or at least provide a second opinion. Furthermore, IRD can be used as a knowledge sharing and information transferring tools between clinicians, between clinicians and patients or their families and also between patients with the other patients.

In this study also main components, barriers, issues and requirement to design and develop an Intelligent Risk Detection solution are explored and a comprehensive real time Intelligent Risk Detection Model in the healthcare context is designed.

Degree Doctor of Philosophy (PhD)
Institution RMIT University
School, Department or Centre Business IT and Logistics
Keyword(s) Intelligent Risk Detection
Business Analytics
Knowledge Discovery
Decision Support Systems
Congenital Heart Disease
Versions
Version Filter Type
Access Statistics: 407 Abstract Views, 461 File Downloads  -  Detailed Statistics
Created: Fri, 26 Sep 2014, 16:47:18 EST by Maria Lombardo
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us