Table of Contents

Preface v

1 Biomedical Databases and Data Mining 1

1.1 Databases and Knowledge Discovery in Biomedicine 2

1.2 Outline of this Book 5

2 DYNASTAT: A Methodology for Modeling of Multi-agent Systems 11

2.1 Introduction 11

2.2 Literature Review 13

2.3 DYNASTAT Methodology 16

2.4 Use of UML 2.2 in the Framework of DYNASTAT Methodology 18

2.5 UML to Model Medical Multi-agent Systems 23

2.6 Possible Applications 30

2.7 Conclusion 33

3 SciPort: An Extensible Data Management Platform for Biomedical Research 35

3.1 Introduction 35

3.2 Related Work 38

3.3 Unified Scientific Data Modeling 39

3.4 Document Authoring and Searching 47

3.5 Sharing Distributed Biomedical Data 56

3.6 The Architecture of SciPort 59

3.7 Conclusion 62

4 An Integrative Framework for Anonymizing Clinical and Genomic Data 65

4.1 Introduction 65

4.2 Related Work 70

4.3 The DIANOVA Framework 77

4.4 Algorithms for Realizing DIANOVA 83

4.5 Extensions of DIANOVA 88

4.6 Conclusion 88

5 Data Integration Challenges: A Systems Biology Perspective 91

5.1 Introduction 91

5.2 Modeling Biological Systems 92

5.3 Biological and Mathematical Data Sources 94

5.4 Various Data Exchange Formats in Systems Biology 96

5.5 Building an Integrative Framework to Combine Modeling and Biological Data Sources 98

5.6 Analysis of the Developed Integrative Environment 111

5.7 Conclusion 113

6 Ontology-based Data Integration: A Case Study in Clinical Trials 115

6.1 Introduction 115

6.2 System Architecture and Overview 117

6.3 The CTDM Ontology 118

6.4 Ontology-based Data Integration of Study Relevant Information 121

6.5 Assembly of ETL Processes Based on Ontology Mappings 130

6.6 Case Study and Evaluation 132

6.7 Related Work 135

6.8 Conclusion 136

7 A Data Warehouse for Ca. Glomeribacter Gigasporarum Bacterium 139

7.1 Introduction 139

7.2 State-of-the-art of Metagenomics for Genomic Comparison 141

7.3 BIOBITS System Architecture 143

7.4 Software Modules to Support Researchers' Activities 149

7.5 Conclusion 154

8 Quality of Medical Data: A Case Study 157

8.1 Introduction 158

8.2 Case Study 165

8.3 Generation of a Summary Table 172

8.4 Conclusion 173

9 Efficient EMD-based Similarity Search in Medical Image Databases 175

9.1 Introduction 175

9.2 Dimensionality Reduction for the EMD 182

9.3 Query Processing Algorithm 192

9.4 Evaluation on Medical Data Sets 193

9.5 Conclusion 200

10 Fast Multimedia Querying for Medical Applications 203

10.1 Introduction 203

10.2 Related Work 206

10.3 Subspace Tree 208

10.4 Experiments 215

10.5 Conclusion 218

11 Ensemble Feature Selection in Biomedical Applications 221

11.1 Introduction 222

11.2 Evaluation of Feature Selection Approaches 225

11.3 Ensemble Feature Selection 228

11.4 Biomedical Example 230

11.5 Computational Approach 232

11.6 Results 233

11.7 Discussion 235

11.8 Conclusion 238

12 Analysis of Breast Cancer Genomic Data by Fuzzy Association Rule Mining 241

12.1 Introduction 242

12.2 Microarrays 247

12.3 Association Rule Mining 247

12.4 Fuzzy Association Rules 251

12.5 Dataset 254

12.6 Extracting the Fuzzy Association Rules 257

12.7 Results 268

12.8 Conclusion 277

13 Graph Mining on Brain Co-activation Networks 279

13.1 Introduction 281

13.2 Related Work 282

13.3 Method 284

13.4 Experiments 288

13.5 Conclusion 293

14 Automatic Identification of Surgery Indicators 295

14.1 Introduction 295

14.2 Background 297

14.3 Approach 302

14.4 Experiment 308

14.5 Conclusion 318

15 Incremental Learning of Medical Data for Multi-step Patient Health Classification 321

15.1 Introduction 321

15.2 The Bayes Tree 325

15.3 Experimental Evaluation 330

15.4 Incorporating Medical Knowledge Data Bases 337

15.5 Application of Anytime Classification 340

15.6 Conclusion 343

Bibliography 345