University of Sussex
Browse
Aziz,_Ayesha.pdf (3.27 MB)

A service oriented architecture to implement clinical guidelines for evidence-based medical practice

Download (3.27 MB)
thesis
posted on 2023-06-08, 20:13 authored by Ayesha Aziz
Health information technology (HIT) has been identified as the fundamental driver to streamline the healthcare delivery processes to improve care quality and reduce operational costs. Of the many facets of HIT is Clinical Decision Support (CDS) which provides the physician with patient-specific inferences, intelligently filtered and organized, at appropriate times. This research has been conducted to develop an agile solution to Clinical Decision Support at the point of care in a healthcare setting as a potential solution to the challenges of interoperability and the complexity of possible solutions. The capabilities of Business Process Management (BPM) and Workflow Management systems are leveraged to support a Service Oriented Architecture development approach for ensuring evidence based medical practice. The aim of this study is to present an architecture solution that is based on SOA principles and embeds clinical guidelines within a healthcare setting. Since the solution is designed to implement real life healthcare scenarios, it essentially supports evidence-based clinical guidelines that are liable to change over a period of time. The thesis is divided into four parts. The first part consists of an Introduction to the study and a background to existing approaches for development and integration of Clinical Decision Support Systems. The second part focuses on the development of a Clinical Decision Support Framework based on Service Oriented Architecture. The CDS Framework is composed of standards based open source technologies including JBoss SwitchYard (enterprise service bus), rule-based CDS enabled by JBoss Drools, process modelling using Business Process Modelling and Notation. To ensure interoperability among various components, healthcare standards by HL7 and OMG are implemented. The third part provides implementation of this CDS Framework in healthcare scenarios. Two scenarios are concerned with the medical practice for diagnosis and early intervention (Chronic Obstructive Pulmonary Disease and Lung Cancer), one case study for Genetic data enablement of CDS systems (New born screening for Cystic Fibrosis) and the last case study is about using BPM techniques for managing healthcare organizational perspectives including human interaction with automated clinical workflows. The last part concludes the research with contributions in design and architecture of CDS systems. This thesis has primarily adopted the Design Science Research Methodology for Information Systems. Additionally, Business Process Management Life Cycle, Agile Business Rules Development methodology and Pattern-Based Cycle for E-Workflow Design for individual case studies are used. Using evidence-based clinical guidelines published by UK’s National Institute of Health and Care Excellence, the integration of latest research in clinical practice has been employed in the automated workflows. The case studies implemented using the CDS Framework are evaluated against implementation requirements, conformance to SOA principles and response time using load testing strategy. For a healthcare organization to achieve its strategic goals in administrative and clinical practice, this research has provided a standards based integration solution in the field of clinical decision support. A SOA based CDS can serve as a potential solution to complexities in IT interventions as the core data and business logic functions are loosely coupled from the presentation. Additionally, the results of this this research can serve as an exemplar for other industrial domains requiring rapid response to evolving business processes.

History

File Version

  • Published version

Pages

173.0

Department affiliated with

  • Engineering and Design Theses

Qualification level

  • doctoral

Qualification name

  • phd

Language

  • eng

Institution

University of Sussex

Full text available

  • Yes

Legacy Posted Date

2015-03-05

Usage metrics

    University of Sussex (Theses)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC