Knowledge engineering for mental-health risk assessment and decision support

Doctoral thesis English OPEN
Ahmed, Abu

Mental-health risk assessment practice in the UK is mainly paper-based, with little standardisation in the tools that are used across the Services. The tools that are available tend to rely on minimal sets of items and unsophisticated scoring methods to identify at-risk individuals. This means the reasoning by which an outcome has been determined remains uncertain. Consequently, there is little provision for: including the patient as an active party in the assessment process, identifying underlying causes of risk, and eecting shared decision-making. This thesis develops a tool-chain for the formulation and deployment of a computerised clinical decision support system for mental-health risk assessment. The resultant tool, GRiST, will be based on consensual domain expert knowledge that will be validated as part of the research, and will incorporate a proven psychological model of classication for risk computation. GRiST will have an ambitious remit of being a platform that can be used over the Internet, by both the clinician and the layperson, in multiple settings, and in the assessment of patients with varying demographics. Flexibility will therefore be a guiding principle in the development of the platform, to the extent that GRiST will present an assessment environment that is tailored to the circumstances in which it nds itself. XML and XSLT will be the key technologies that help deliver this exibility.
  • References (63)
    63 references, page 1 of 7

    1 Introduction 21 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 1.1.1 Current exigencies in mental-health assessment . . . . . . . . . . . . . . . 23 1.2 Thesis Aims and Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 1.3 Thesis Organisation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

    2 The Galatean Model of Classi cation 27 2.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 2.2 Classi cation Theories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.2.1 Exemplar theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 2.2.2 Prototype theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 2.2.3 Dual-process theories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 2.3 The Galatean Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 2.3.1 The Galatean classi cation process . . . . . . . . . . . . . . . . . . . . . . 30 2.3.2 The hierarchical Galatean model and its classi cation process . . . . . . . 30

    3 Clinical Decision Support Systems 37 3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 3.2 The Scope of CDSSs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 3.2.1 CDSS knowledge representation and architecture . . . . . . . . . . . . . . 38 3.2.2 CDSS domains . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 3.2.3 CDSS contexts and audiences . . . . . . . . . . . . . . . . . . . . . . . . . 41 3.3 Strategic Challenges to CDSS Implementers . . . . . . . . . . . . . . . . . . . . . 42 3.4 The Characteristics of a Good CDSS . . . . . . . . . . . . . . . . . . . . . . . . . 43 3.4.1 Practices and features yielding positive outcomes . . . . . . . . . . . . . . 43 3.4.2 Practices and in uences reducing CDSS e cacy . . . . . . . . . . . . . . . 47 3.5 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48

    4 Choosing a Representation Format for Domain Knowledge 50 4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50 4.2 The Ubiquity of XML-based Serialisation . . . . . . . . . . . . . . . . . . . . . . 51 4.3 Web Ontology Language . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 4.4 On the Appropriateness of OWL for Developing GRiST . . . . . . . . . . . . . . 53 4.4.1 The maturity of supporting tools . . . . . . . . . . . . . . . . . . . . . . . 54 4.4.2 The OWL le format is complex . . . . . . . . . . . . . . . . . . . . . . . 54 4.4.3 Learning curve of OWL ontology creation tools . . . . . . . . . . . . . . . 55 4.4.4 The dangers of feature overload and restrictions . . . . . . . . . . . . . . 55 4.5 Using XML and XSLT to Produce Flexible Knowledge Representations . . . . . 56 4.6 XSLT Primer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 4.6.1 XSLT and web Browsers . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 4.6.2 Standalone XSLT processors . . . . . . . . . . . . . . . . . . . . . . . . . 58 4.7 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59

    5 Validation of Mental-health Knowledge Elicited From Experts 60 5.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 5.2 Interviewing of Experts & Mind Map Generation . . . . . . . . . . . . . . . . . . 61 5.2.1 Reviewing of mind maps . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63 5.3 Generic Software and Web Infrastructure for Remote Activities . . . . . . . . . . 64

    6 The Structure Tree and its Enrichment 82 6.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 82 6.2 Overview of the ST at End of Knowledge Re nement . . . . . . . . . . . . . . . . 83 6.3 Semantics and Organisation of Generic Nodes . . . . . . . . . . . . . . . . . . . . 84 6.3.1 Generic concepts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84 6.3.2 Generic datums . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85 6.3.3 Direct risk children . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86 6.3.4 Rules governing generic nodes and where they are fully de ned . . . . . . 87 6.4 Question-related Paraphernalia and Data Types . . . . . . . . . . . . . . . . . . . 88 6.4.1 The di erent types of question: question, filter-q attributes . . . . . . 88 6.4.2 Generating rapid screening questions: the layer attribute . . . . . . . . . 89 6.4.3 Data types associated with questions . . . . . . . . . . . . . . . . . . . . . 91 6.5 Representing Membership Grade Pro les . . . . . . . . . . . . . . . . . . . . . . . 96 6.5.1 Collection of preliminary value-mg data . . . . . . . . . . . . . . . . . . . 96

    6.6 Flexible Assessments Based on User Expertise Level . . . . . . . . . . . . . . . . 98 6.6.1 Practitioner expertise quantised as levels . . . . . . . . . . . . . . . . . . . 98

    6.7 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 101

    7 Representing Relative In uence 103 7.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103 7.2 The ST is Not Suitable for Recording RI Information . . . . . . . . . . . . . . . . 104 7.3 Generating the Relative In uence Tree . . . . . . . . . . . . . . . . . . . . . . . . 106 7.3.1 Priming the ST for transformation . . . . . . . . . . . . . . . . . . . . . . 106 7.3.2 RIT generation process . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107 7.4 RI Elicitation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108 7.5 The Galatean Tree Hierarchy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110 7.6 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110

    10 Further Customisation of GRiST for Di erent Populations and Contexts 164 10.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164 10.2 The Need for Lateral Customisation . . . . . . . . . . . . . . . . . . . . . . . . . 165 10.2.1 The organisational perspective . . . . . . . . . . . . . . . . . . . . . . . . 165 10.2.2 The clinical perspective . . . . . . . . . . . . . . . . . . . . . . . . . . . . 166 10.2.3 The patient perspective . . . . . . . . . . . . . . . . . . . . . . . . . . . . 167 10.3 Rationale for a Super Structure Tree . . . . . . . . . . . . . . . . . . . . . . . . . 167 10.4 Super Structure Tree Syntax . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 168 10.4.1 The populations attribute . . . . . . . . . . . . . . . . . . . . . . . . . . 169 10.4.2 The enhanced layer and order attributes . . . . . . . . . . . . . . . . . . 169 10.4.3 The SST Enhanced question, filter-q, label and help attributes . . . 170 10.4.4 Inverting value-mgs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 170 10.4.5 Population-speci c pruning of nodes . . . . . . . . . . . . . . . . . . . . . 171 10.4.6 Adding additional nodes . . . . . . . . . . . . . . . . . . . . . . . . . . . . 172 10.4.7 Adding new populations to the SST . . . . . . . . . . . . . . . . . . . . . 172

  • Related Research Results (1)
  • Similar Research Results (7)
  • Metrics
    0
    views in OpenAIRE
    0
    views in local repository
    18
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    Aston Publications Explorer - IRUS-UK 0 18
Share - Bookmark