Principles of Biomedical Informatics (eBook)

Front Cover 1
Principles of Biomedical Informatics 4
Copyright 5
Dedication 6
Table of Contents 8
Foreword 14
Preface 18
Part I: Foundations of Biomedical Informatics 28
Chapter 1. Biomedical Data 30
1.1 The Nature and Representation of Biomedical Data 33
1.1.1 What Can Be Represented in a Computer? 40
1.1.2 DNA and the Genetic Code 54
1.1.3 Anatomy 64
1.1.4 Medical Laboratory Data 65
1.1.5 Medical Images 69
1.1.6 Metadata 77
1.2 Objects, Metadata, and Serialization 80
1.2.1 A Simple Solution Using Tags (Keywords) 81
1.2.2 An Object-oriented Design 82
1.2.3 A Better Solution Using Meta-objects 92
1.2.4 Medical Images: Incorporating Binary Data 99
1.3 XML 104
1.4 Database Systems and Ideas 111
1.4.1 The Relational Model 112
1.4.2 The Entity–Attribute–Value Model 119
1.5 Data Quality 120
1.6 Data, Information and Knowledge 122
1.7 Summary 124
Chapter 2. Symbolic Biomedical Knowledge 126
2.1 Biomedical Theories and Computer Programs 128
2.1.1 A World Class Reasoning Example 128
2.1.2 Biological Examples 129
2.1.3 Symbolic Theories 129
2.2 Logic and Inference Systems 132
2.2.1 Predicate Calculus 133
2.2.2 Unsound Inference: Abduction and Induction 151
2.2.3 First Order Logic 152
2.2.4 Rule-based Programming for FOL 160
2.2.5 Limitations of FOL 166
2.3 Frames, Semantic Nets, and Ontologies 169
2.3.1 A Simple Frame System 170
2.3.2 Extensions to Frame Systems 186
2.3.3 Frame System Implementations, Interfaces, and APIs 189
2.3.4 Frames and Object-oriented Programming Languages 189
2.4 Description Logics 190
2.4.1 Description Logic Languages 193
2.4.2 Examples from GALEN 194
2.4.3 The Semantic Web 197
2.4.4 Back to the Future 200
2.5 Search 200
2.5.1 A General Framework for Search 201
2.5.2 Uninformed Search Strategies 205
2.5.3 Informed Search Strategies 207
2.5.4 Path Search 209
2.6 Summary 210
Chapter 3. Probabilistic Biomedical Knowledge 212
3.1 Probability and Statistics 213
3.1.1 Probability 213
3.1.2 Statistics 214
3.1.3 The Laws of Probability 215
3.1.4 Conditional Probability 217
3.1.5 Independence 218
3.1.6 Random Variables and Estimation 219
3.2 Application and Generalization of Bayes’ rule 226
3.2.1 Simple Bayesian Inference 228
3.2.2 Non-Boolean Variables 229
3.2.3 Bayes Nets 230
3.3 Utility and Decision Modeling 234
3.3.1 A Decision Analysis Vignette 235
3.3.2 Graph Structure and Probability Assignment 236
3.3.3 Determining Utilities 237
3.3.4 Computation of Expected Values 238
3.4 Information Theory 240
3.4.1 Encoding of Messages 240
3.4.2 Entropy and Information 243
3.4.3 Efficient Encoding 244
3.4.4 Error Detection and Correction 247
3.4.5 Information Theory in Biology and Medicine 247
3.5 Summary 248
Chapter 4. Biomedical Information Access 250
4.1. Information Retrieval Systems 250
4.2. IR System Design 254
4.2.1 Indexing 254
4.2.2 Processing Queries 259
4.2.3 Searching and Matching 260
4.2.4 Ranking the Results 260
4.2.5 Performance Evaluation 261
4.3 Intelligent Query Processing 262
4.4 Network Access to Document Repositories 262
4.5 Natural Language Processing 273
4.6 Beyond Text Documents 275
4.6.1 Biomedical Images 276
4.6.2 Electronic Medical Records 277
4.7 Summary 277
Part II: Biomedical Ideas and Computational Realizations 278
Chapter 5. Computing With Genes, Proteins, and Cells 280
5.1 Getting Data From Files 282
5.2 Computing With DNA Sequences 286
5.3 Mapping Genes to Proteins 291
5.4 Computing With Protein Sequences 295
5.4.1 Representing Amino Acid and Proteins 295
5.4.2 Simple Properties of Proteins From Sequence Data 298
5.4.3 Amino Acid Profiles 299
5.5 The Gene Ontology 304
5.6 Biochemical Pathways 307
5.6.1 Searching for Pathways 308
5.6.2 Biochemical Reachability Logic 314
5.7 Simulation With State Machines 318
5.7.1 State Machines 318
5.7.2 A Simple State Machine 320
5.7.3 Simulating the Cell Cycle in Yeast 324
5.8 Summary 329
Chapter 6. Modeling Biological Structure 330
6.1 The UW Foundational Model of Anatomy 331
6.1.1 The Components of the FMA 331
6.1.2 Representing Anatomical Relations in the FMA 332
6.1.3 Metaclasses 332
6.1.4 The part-of Relationship 335
6.2 A Simple Network Interface – the FMS 335
6.3 Semantic Consistency Checking and the FMA 342
6.3.1 The Lymphatic System: An Example 344
6.3.2 Current State of the Lymphatics in the FMA 346
6.4 Summary 350
Chapter 7. Drug Interactions 352
7.1 Drug Information Catalogs 354
7.2 Reasoning About Pharmacokinetics 358
7.2.1 Procedural Knowledge About Enzymatic Metabolism 360
7.2.2 A Rule-based Drug Interaction System 361
7.2.3 Truth Maintenance Systems 364
7.2.4 A Drug Interactions Theory with Justifications 367
7.2.5 Evidence-based Reasoning 369
7.3 Reasoning About Pharmacodynamics 372
7.4 Summary 374
Chapter 8. Medical Data Communication 376
8.1 EMR Systems and PACS 377
8.1.1 EMR Systems 377
8.1.2 Medical Images and PACS 379
8.2 Networks and Protocols 379
8.2.1 Network Architecture 379
8.2.2 Network Client and Server Design 381
8.3 HL7 383
8.3.1 The HL7 Message Exchange Protocol 383
8.3.2 HL7 Message Structure 384
8.3.3 Scanning HL7 Messages 386
8.3.4 HL7 Message Field Content 388
8.4 DICOM: Medical Image Information Agents 391
8.4.1 A Short History of DICOM 391
8.4.2 About the DICOM Standard 393
8.5 How to Implement DICOM 397
8.5.1 The DICOM State Machine 398
8.5.2 Parsing and Generation of PDUs 407
8.5.3 Parsing and Generation of Commands and Data 413
8.5.4 How It All Turned Out 417
8.6 Summary 418
Chapter 9. Cancer Radiotherapy Planning 420
9.1. Radiation Therapy 421
9.2. Radiotherapy Planning Software 422
9.3. Locating the Target 425
9.3.1 Computing the CTV 427
9.3.2 Computing the PTV 433
9.4. Influence Diagrams in RTP 440
9.5 Summary 441
Chapter 10. Safety and Security 444
10.1 A Bit of Personal History and Perspective 445
10.2 Some Real-Life Stories 446
10.2.1 Radiation Therapy Planning Systems 447
10.2.2 Who is Master, the Human or the Computer? 449
10.2.3 The Therac-25: A Real-Time Disaster 449
10.2.4 Prism 450
10.2.5 The UW Neutron Therapy Facility 450
10.2.6 DICOM and Internet Security 451
10.2.7 Intravenous Infusion Pumps on the Internet 451
10.3 Safety By Design: Radiotherapy Machines 452
10.3.1 A Simple Linac Control System 453
10.3.2 Adding a Dosimetry System 455
10.3.3 Formal and Automated Analysis 456
10.4 It Security in Health Care Organizations 456
10.5 Epilogue 458
Appendix A. Lisp Notes, Software, and Other Resources 460
A.1 Lisp Notes 460
A.1.1 General Notes on Lisp 460
A.1.2 CLOS and MOP 461
A.1.3 Optimization 463
A.1.4 Books on Lisp 464
A.2 Software 465
A.2.1 Data and Knowledge Resources 465
A.2.2 Common Lisp Systems, Libraries, and Resources 466
A.2.3 Languages and Tools for Knowledge Representation 466
A.2.4 Code from the Book 467
A.3 Other Resources 468
Bibliography 470
Index 486