Mental Health Informatics: Enabling a Learning Mental Healthcare System

Preface
Acknowledgments
Contents
Chapter 1: Precision Medicine and a Learning Health System for Mental Health
1.1 Introduction
1.2 The Need for Precision Mental Healthcare
1.2.1 Informatics: A Brief Preview
1.3 The Path to the Learning Health System
1.3.1 The Traditional Model for the Discovery and Application of Knowledge in Healthcare
1.3.2 Translational Science
1.3.2.1 Limitations of Translational Research
1.3.3 The Learning Health System Paradigm
1.3.3.1 Limitations of the Learning Health System Paradigm
1.3.4 Foundational Requirements of a Learning Health System in Mental Health
1.3.5 Learning Health System Models: The Role of Informatics
1.4 Precision Medicine in Mental Health
1.4.1 The Role of Informatics in Precision Medicine
1.4.2 A Learning Heath System for Precision Mental Health
1.5 Summary and Conclusions
References
Chapter 2: What Is Informatics?
2.1 History and Role in Biomedicine and Health
2.2 From Data to Knowledge (D2K)
2.2.1 Knowledge Discovery Process
2.2.2 Data and Databases
2.2.3 Natural Language Processing and Text Mining
2.2.4 Data Mining and Machine Learning
2.2.5 Standards and Interoperability
2.3 From Knowledge to Performance (K2P)
2.3.1 Clinical Decision Support
2.3.2 Software and Knowledge Engineering
2.3.3 Human Factors Engineering
2.4 From Performance to Data (P2D)
2.4.1 Evaluation Models
2.4.2 Quantitative and Qualitative Methods
2.5 Summary
References
Chapter 3: The Mental Health System: Definitions and Diagnoses
3.1 Introduction
3.2 Defining Mental Health and Mental Illness
3.2.1 The Concept of Mental Health
3.2.2 Health and Disease
3.2.3 Definitions of Mental Health
3.2.4 Mental Health and Somatic Health
3.3 The Concept of Mental Illness
3.3.1 The Continuums of Mental Health and Illness
3.4 Theories of Psychopathology
3.4.1 Biological Theories of Psychopathology
3.4.2 Psychological Theories of Psychopathology
3.4.3 Social Theories of Psychopathology
3.4.4 The Biopsychosocial Theory of Psychopathology
3.5 Defining Mental Disorders
3.5.1 Diagnostic Classification Systems Used in Mental Healthcare: DSM-5 and ICD-11
3.5.2 Mental Health Conditions
3.6 Conclusions
References
Chapter 4: The Mental Healthcare System: Organization and Structure
4.1 Introduction
4.2 Mental Healthcare Professionals
4.2.1 Types of Mental Healthcare Professionals
4.3 Mental Healthcare Settings
4.3.1 Inpatient Settings
4.3.2 Outpatient Settings
4.4 Disparities in the Mental Health Workforce
4.5 Mental Healthcare Payment Models
4.5.1 Privately-Funded Insurances
4.5.2 Publicly-Funded Insurances
4.6 Summary
References
Chapter 5: The Mental Health System: Access, Diagnosis, Treatment, and Monitoring
5.1 Introduction
5.2 Access to Mental Healthcare
5.2.1 Pathways to Care: Primary Care
5.2.2 Alternate Pathways to Care
5.2.3 Delays in Care
5.3 Mental Health Assessment and Diagnosis
5.3.1 The Assessment of Illness
5.3.2 Diagnosis and Case Conceptualization
5.4 Mental Health Treatment
5.4.1 The Treatment Setting
5.4.2 Selecting the Right Treatment
5.4.3 Psychotherapy and Social Interventions
5.4.4 Pharmacotherapy
5.4.5 Neuromodulation and Surgical Interventions
5.5 Treatment Monitoring
5.5.1 Patient Reported Outcome Measures
5.5.2 Side Effect Monitoring
5.6 Conclusion
References
Chapter 6: Mental Health Informatics
6.1 Mental Health Informatics as an Informatics Subdiscipline
6.2 Contrasting Mental Health Informatics with Related Disciplines
6.2.1 How Mental Health Informatics Differs from Mainstream Biomedical and Health Informatics
6.2.1.1 Differences in the Phenomena of Interest
6.2.1.2 Differences in the Knowledge Acquisition Cycle
6.2.1.3 How Mental Health Informatics Differs from Other Informatics Work in Mental Health
6.2.2 Mental, Behavioral, and Social Phenomena in Mainstream Health Informatics
6.3 Mental Health Informatics: Bridging the Biological, Behavioral, and Social Sciences
6.3.1 Mainstream Health Informatics Has Not Fully Embraced Social and Behavioral Phenomena
6.3.2 Epistemological Differences Between the Behavioral and Biological Sciences
6.3.3 A Primary Epistemological Challenge for Informaticians: The Relationship Between the Mind and Brain
6.3.4 Epistemological Differences within the Behavioral and Social Sciences: A Multiplicity of Theories of ‘Mind’ and Behavior
6.3.5 Points of Intersection Between the Biological, Behavioral, and Social Sciences
6.4 How Mental Health Informatics Extends Informatics
6.5 Summary
References
Chapter 7: Technologies for the Computable Representation and Sharing of Data and Knowledge in Mental Health
7.1 Introduction
7.2 Technologies for Representing Data, Information, and Knowledge
7.2.1 The Terminology Used to Describe “Terminology”
7.2.2 Concept Representation
7.2.3 Controlled Vocabularies
7.2.4 Classifications
7.2.5 Terminologies
7.2.6 Information Models
7.2.7 Knowledge Representation
7.3 What Is a Standard?
7.3.1 Content Standards
7.3.2 Syntax Standards
7.3.3 Semantic Standards
7.3.3.1 SNOMED CT
7.3.3.2 LOINC
7.4 Interoperability Standards
7.4.1 HL7 Messages
7.4.2 Consolidated Clinical Document Architecture (C-CDA)
7.4.3 Fast Health Interoperability Resources (FHIR)
7.5 Repositories of Standards
7.5.1 FAIRSharing
7.5.2 Interoperability Standards Advisory (ISA)
7.6 Addressing Gaps in Standards to Accommodate Mental Health
7.6.1 Standards for Concept and Knowledge Representation in Mental Health
7.6.2 Minimum Clinical Data Sets
7.6.3 Quality of Terminologies Relative to Mental Health
7.7 Conclusions and Recommendations
References
Chapter 8: Use of Medical Imaging to Advance Mental Health Care: Contributions from Neuroimaging Informatics
8.1 Introduction
8.2 Capturing Meaningful Neuroscientific Anatomic and Physiologic Data
8.3 Radiology Workflow: From Order to Storage
8.4 Data and Standards
8.5 Image-Derived Features for Mental Health
8.5.1 Magnetic Resonance Imaging
8.5.2 Nuclear Medicine Imaging
8.5.3 Neurophysiology Workflows
8.5.4 Neuroimaging Informatics
8.6 Challenges and Opportunities
References
Chapter 9: Informatics Technologies for the Acquisition of Psychological, Behavioral, Interpersonal, Social and Environmental Data
9.1 Introduction
9.2 Psychometrics: A Brief Primer
9.3 Types of Data Relevant for Mental Health
9.3.1 Psychological Data
9.3.1.1 What Is Measured
9.3.1.2 Measurement Approaches
9.3.2 Behavioral Data
9.3.3 Social and Interpersonal Data
9.3.4 Environmental Data
9.4 Informatics Technologies for Data Acquisition
9.5 Challenges, Limitations and Future Directions
References
Chapter 10: Data to Information: Computational Models and Analytic Methods
10.1 Introduction
10.2 Analytic Approaches to Computational Modeling
10.3 Theory-Based Approaches
10.3.1 Dynamical Systems
10.3.2 Causal Networks
10.4 Data-Driven Approaches
10.4.1 The Workflow in Machine Learning
10.5 Preprocessing
10.5.1 Dimensionality Reduction
10.5.2 Feature Selection Methods
10.5.3 Feature Extraction Methods
10.6 Machine Learning Algorithms
10.6.1 Supervised Learning
10.6.2 Unsupervised Learning
10.6.3 Semi-Supervised Learning
10.6.4 Deep Learning
10.7 Evaluation of Model Performance
10.7.1 Supervised Models
10.7.2 Unsupervised Models
10.8 Applications of Computational Models in Mental Health
10.9 Standards for Reporting Models
10.10 Policy, Ethical, and Safety Issues
10.11 Conclusion
References
Chapter 11: Bioinformatics in Mental Health: Deriving Knowledge from Molecular and Cellular Data
11.1 Introduction
11.1.1 Translational Bioinformatics and Biomarker Discovery
11.1.2 How Bioinformatics and Data Science Contribute to Biomarker Discovery in Mental Health
11.2 Types of Data in Biomarker Discovery
11.2.1 Genomics: The Study of the DNA
11.2.1.1 Data Processing
11.2.1.2 Strengths and Limitations
11.2.1.3 Examples in Mental Health
11.2.2 Transcriptomics: The Study of the RNA
11.2.2.1 Data Processing
11.2.2.2 Strengths and Limitations
11.2.2.3 Examples in Mental Health
11.2.3 Proteomics: The Study of Proteins
11.2.3.1 Data Processing
11.2.3.2 Strengths and Limitations
11.2.3.3 Examples in Mental Health
11.2.4 Metabolomics: The Study of Metabolites
11.2.4.1 Data Processing
11.2.4.2 Strengths and Limitations
11.2.4.3 Examples in Mental Health
11.2.5 Epigenetics/Epigenomics
11.2.5.1 Data Processing
11.2.5.2 Strengths and Limitations
11.2.5.3 Examples in Mental Health
11.2.6 microRNA
11.2.6.1 Data Processing
11.2.6.2 Strengths and Limitations
11.2.6.3 Examples in Mental Health
11.2.7 DNA Copy Number
11.2.7.1 Data Processing
11.2.7.2 Strengths and Limitations
11.2.7.3 Examples in Mental Health
11.2.8 Neuro-Imaging
11.2.8.1 Data Processing
11.2.8.2 Strengths and Limitations
11.2.8.3 Examples in Mental Health
11.2.9 Emerging Data Types: Microbiome
11.2.9.1 Data Processing
11.2.9.2 Strengths and Limitations
11.2.9.3 Examples in Mental Health
11.3 Cellular Attributes in Biomarker Discovery
11.4 Systems Biology in Mental Health
11.5 Mental Health Vs. Medical Conditions
11.5.1 Bioinformatics Knowledge Discovery and Application: An Example in Mental Health
11.6 Conclusion
References
Chapter 12: Integrative Paradigms for Knowledge Discovery in Mental Health: Overcoming the Fragmentation of Knowledge Inherent in Disparate Theoretical Paradigms
12.1 Introduction
12.2 Integrative Semantic Frameworks and the RDoC Initiative
12.3 Integrative Computational Methods
12.3.1 Factor Analysis
12.3.2 Network Analysis
12.3.3 Computational Psychiatry
12.3.4 Within- and Between-Person Reasoning
12.4 Discussion: Epistemology and the Limitations of Integrative Paradigms
12.5 Conclusions
References
Chapter 13: Natural Language Processing in Mental Health Research and Practice
13.1 Introduction
13.2 Corpus Generation
13.2.1 Using Medical Records as a Corpus
13.2.1.1 Collecting Medical Records
13.2.1.2 De-Identification of Medical Records
13.2.1.3 Annotation of Medical Records
13.2.1.4 Publicly Available Medical Record Datasets
13.2.2 Generating a Corpus from Social Media Data
13.2.2.1 Collecting and Annotating Social Media Data
13.2.2.2 Privacy with Social Media Data
13.2.3 Other Data Sources
13.3 Data Processing
13.3.1 Preprocessing
13.3.2 Featurization
13.3.2.1 Term Vectors
13.3.2.2 Sentence and Document Vectors
13.3.2.3 Count-Based Features
13.3.2.4 Rule-Based Features
13.3.2.5 Sentiment and Psycholinguistic Features
13.3.2.6 Sociability Features
13.3.2.7 Temporal Features
13.3.3 Analyzing Natural Language Data
13.3.3.1 Rule-Based Systems
13.3.3.2 Supervised Machine Learning Systems
13.3.3.3 Deep Learning Systems
13.3.3.4 Unsupervised Machine Learning
13.4 Applications of Natural Language Processing in Mental Health
13.4.1 Mental Illness Detection
13.4.2 Symptom and Severity Extraction
13.4.3 Lexicon and Ontology Construction
13.4.4 Knowledge Discovery
13.4.5 Other Applications
13.5 NLP in Mental Health Practice
13.6 Challenges, Limitations, and Ethical Considerations
13.6.1 Challenges
13.6.2 Ethical Considerations
13.7 Conclusions
References
Chapter 14: Information Visualization in Mental Health Research and Practice
14.1 Introduction
14.2 A Crash Course in Information Visualization
14.2.1 Why Visualization?
14.2.2 Visualization Tasks
14.2.3 Building Visualizations
14.2.3.1 Understanding User Needs and Goals
14.2.3.2 Preparing Data
14.2.3.3 Displaying Data
14.2.3.4 Interacting with Data
14.3 Mental Health Data
14.3.1 Survey and Psychometric Instrument Data
14.3.2 Electronic Health Record (EHR) Data
14.3.3 Genetic Data
14.3.4 Environmental Data
14.3.5 Mobile Health Data
14.3.6 Using Data and Predictive Models in Mental Health Visualization
14.4 Current State and Outstanding Challenges
14.4.1 Uncertainty
14.4.2 Evaluation
14.5 Conclusion
References
Chapter 15: Big Data: Knowledge Discovery and Data Repositories
15.1 What Is “Big Data”: The Big Part, the Data Part?
15.2 Methods and Paradigms
15.2.1 Essential Elements for Big Data Repositories
15.2.1.1 Governance
Technical Infrastructure
Metadata
15.3 Big Data and Data Repositories
15.3.1 The Fair Guiding Principles
15.4 Secondary Usage
15.4.1 Biobanks
15.5 Categories of Data and Data Repositories
15.5.1 Refined Scientific Knowledge: Publication Databases and Specialist Databases
15.5.2 Biological Data
15.5.3 Behavioral Data
15.5.4 Clinical Administrative Data Repositories
15.5.5 Electronic Health Records
15.5.6 Linked Multi-Modal Data Repositories: Multiple Data Sources
15.5.7 Practical Challenges of Using Data Repositories for Mental Health Research
15.6 Case Study: Developing a Big Data Registry/Repository
15.6.1 Who Develops Disease-Specific Data Repositories in Mental Health and Why?
15.7 Closing Thoughts: Opportunities and Challenges
References
Chapter 16: Electronic Health Records (EHRS) and Other Clinical Information Systems in Mental Health
16.1 Introduction
16.1.1 Historical Perspective
16.1.2 Federal Initiatives Related to Health IT
16.1.3 ACOs and PCMHs
16.1.3.1 The State Innovation Models (SIM) Initiative
16.1.4 Overview of EHRs
16.1.4.1 Landscape of EHRs Across Medical and Mental Health Care
16.1.4.2 Common EHR Vendors in the Mental Health Field
16.1.4.3 Medical EHRs with Behavioral Health Components
16.1.5 The Proposed Value of EHRs
16.1.5.1 Patient Safety and Quality of Care
16.1.5.2 Improved Efficiency
16.1.5.3 EHR Disadvantages
16.1.5.4 Secondary Uses for EHRs
Research Uses
Learning Health Systems (LHS) and Quality Improvement (QI)
16.1.6 Personal Health Records (PHRs)
16.1.6.1 Types of PHRs
16.1.6.2 Drawbacks of PHRs
16.1.7 Future Directions
16.1.8 Conclusion
References
Chapter 17: Informatics Technologies in the Diagnosis and Treatment of Mental Health Conditions
17.1 Introduction
17.2 Detection and Diagnosis
17.2.1 Consumer Facing Technologies
17.2.1.1 Wearable Devices
17.2.1.2 Smartphone Based Assessment
17.2.1.3 Social Media
17.2.1.4 Implications for Mental Health Conditions
17.2.2 Provider Facing Technologies
17.2.2.1 Computerized Psychometric Assessment
17.2.2.2 Telemedicine
17.2.2.3 Mobile Medical Devices
17.2.2.4 Specialized Clinical Information Systems
17.3 Prevention and Treatment
17.3.1 Consumer and Provider Facing Technologies
17.3.1.1 Online Support Groups
17.3.1.2 Web Based and Mobile Applications
17.3.1.3 Coordination and Continuity of Care
17.4 Ongoing Issues and Challenges
17.4.1 Contemporary Psychiatric Diagnostics
17.4.2 Clinician Acceptance
17.4.3 Patient Acceptance, Access and Equity
17.5 Summary and Conclusion
References
Chapter 18: Ethical, Legal, and Social Issues (ELSI) in Mental Health Informatics
18.1 Introduction
18.2 Stigma and Data Sharing
18.3 Ethical AI in Mental Healthcare
18.3.1 Ethical Issues at Data-Level
18.3.2 Ethical Issues in Designing AI-Based Systems
18.3.3 Ethical Issues in Deploying AI-Based Systems in Practice
18.4 Mobile Health and eHealth Applications for Mental Health
18.4.1 Passive Data Collection
18.4.2 Telepsychiatry and Telemental Health
18.4.3 Virtual Helpers and Providers
18.4.3.1 Minders
18.4.3.2 Prostheses
18.4.3.3 Caregivers
18.4.3.4 Providers
18.4.3.5 Personhood and AI
18.5 Mental Health Advocacy
18.5.1 What Role Does Patient Advocacy Play in General?
18.5.2 What Motivates Self-Advocacy in Mental Health?
18.5.3 How Do Mental Health Service Users and Advocates Bring Lived Experience to Mental Health Treatment?
18.6 Genomics and Mental Health Informatics
18.7 Laws and Regulations
18.7.1 Health Insurance Portability and Accountability Act of 1996 (HIPAA)
18.7.2 HIPAA Privacy Rule
18.7.3 HIPAA Security Rule
18.7.4 Confidentiality of Substance Use Disorder Records
18.7.5 21st Century Cures Act
18.7.6 Research Regulations
18.7.7 General Data Protection Regulation (GDPR)
18.7.8 California Consumer Privacy Act (CCPA)
18.8 Concluding Remarks
18.9 Discussion Questions for Reader Consideration
References
Chapter 19: The Future of Mental Health Informatics
19.1 Envisioning an Ambitious Future
19.1.1 Essential Component 1: Datasets, Data Storage, and Workflows
19.1.2 Essential Component 2: Harmonizing and Integrating across Datasets
19.1.3 Training
19.2 Making a Difference Now: Informatics and a Learning Health System for Psychosis
19.3 Conclusion
References
Index