List of Contributors xvii Preface xxi Part I Advances In Biomedical And Health Informatics 1 1 Recent Development in Methodology for Gene Network Problems and Inferences 3Sung W. Han and Hua Zhong 1.1 Introduction 3 1.2 Background 5 1.3 Genetic Data Available 7 1.4 Methodology 7 1.4.1 Structural Equation Model 8 1.4.2 Score Function Formulation 9 1.4.3 Two-Stage Learning 12 1.4.4 Further Issues 13 1.5 Search Algorithm 13 1.5.1 Global Optimal Solution Search 13 1.5.2 Heuristic Algorithm for a Local Optimal Solution 14 1.6 PC Algorithm 15 1.7 Application/Case Studies 16 1.7.1 Skin Cutaneous Melanoma (SKCM) Data from the TCGA Data Portal Website 16 1.7.2 The CCLE (Cancer Cell Line Encyclopedia) Project 20 1.7.3 Cellular Signaling Network in Flow Cytometry Data 20 1.8 Discussion 23 1.9 Other Useful Softwares 23 Acknowledgments 24 References 24 2 Biomedical Analytics and Morphoproteomics: An Integrative Approach for Medical Decision Making for Recurrent or Refractory Cancers 31Mary F. McGuire and Robert E. Brown 2.1 Introduction 31 2.2 Background 32 2.2.1 Data 33 2.2.2 Tools 33 2.2.3 Algorithms 34 2.2.4 Literature Review 35 2.3 Methodology 37 2.3.1 Morphoproteomics (Fig. 2.1(1–3)) 39 2.3.2 Biomedical Analytics (Fig. 2.1(4–10)) 40 2.3.3 Integrating Morphoproteomics and Biomedical Analytics 44 2.4 Case Studies 46 2.4.1 Clinical: Therapeutic Recommendations for Pancreatic Adenocarcinoma 46 2.4.2 Clinical: Biology Underlying Exceptional Responder in Refractory Hodgkin’s Lymphoma 48 2.4.3 Research: Role of the Hypoxia Pathway in Both Oncogenesis and Embryogenesis 50 2.5 Discussion 51 2.6 Conclusions 52 Acknowledgments 53 References 53 3 Characterization and Monitoring of Nonlinear Dynamics and Chaos in Complex Physiological Systems 59Hui Yang, Yun Chen, and Fabio Leonelli 3.1 Introduction 59 3.2 Background 61 3.3 Sensor-Based Characterization and Modeling of Nonlinear Dynamics 65 3.3.1 Multifractal Spectrum Analysis of Nonlinear Time Series 65 3.3.2 Recurrence Quantification Analysis 75 3.3.3 Multiscale Recurrence Quantification Analysis 78 3.4 Healthcare Applications 80 3.4.1 Nonlinear Characterization of Heart Rate Variability 81 3.4.2 Multiscale Recurrence Analysis of Space–Time Physiological Signals 85 3.5 Summary 88 Acknowledgments 90 References 90 4 Statistical Modeling of Electrocardiography Signal for Subject Monitoring and Diagnosis 95Lili Chen, Changyue Song, and Xi Zhang 4.1 Introduction 95 4.2 Basic Elements of ECG 96 4.3 Statistical Modeling of ECG for Disease Diagnosis 99 4.3.1 ECG Signal Denoising 100 4.3.2 Waveform Detection 105 4.3.3 Feature Extraction 106 4.3.4 Disease Classification and Diagnosis 111 4.4 An Example: Detection of Obstructive Sleep Apnea from a Single ECG Lead 115 4.4.1 Introduction to Obstructive Sleep Apnea 115 4.5 Materials and Methods 115 4.5.1 Database 115 4.5.2 QRS Detection and RR Correction 116 4.5.3 R Wave Amplitudes and EDR Signal 117 4.5.4 Feature Set 117 4.5.5 Classifier Training with Feature Selection 118 4.6 Results 118 4.6.1 QRS Detection and RR Correction 118 4.6.2 Feature Selection 118 4.6.3 OSA Detection 120 4.7 Conclusions and Discussions 121 References 121 5 Modeling and Simulation of Measurement Uncertainty in Clinical Laboratories 127Varun Ramamohan, James T. Abbott, and Yuehwern Yih 5.1 Introduction 127 5.2 Background and Literature Review 129 5.2.1 Measurement Uncertainty: Background and Analytical Estimation 130 5.2.2 Uncertainty in Clinical Laboratories 134 5.2.3 Uncertainty in Clinical Laboratories: A System Approach 136 5.3 Model Development Guidelines 138 5.3.1 System Description and Process Phases 138 5.3.2 Modeling Guidelines 139 5.4 Implementation of Guidelines: Enzyme Assay Uncertainty Model 141 5.4.1 Calibration Phase 142 5.4.2 Sample Analysis Phase 149 5.4.3 Results and Analysis 150 5.5 Discussion and Conclusions 152 References 154 6 Predictive Analytics: Classification in Medicine and Biology 159Eva K. Lee 6.1 Introduction 159 6.2 Background 161 6.3 Machine Learning with Discrete Support Vector Machine Predictive Models 163 6.3.1 Modeling of Reserved-Judgment Region for General Groups 164 6.3.2 Discriminant Analysis via Mixed-Integer Programming 165 6.3.3 Model Variations 167 6.3.4 Theoretical Properties and Computational Strategies 170 6.4 Applying DAMIP to Real-World Applications 170 6.4.1 Validation of Model and Computational Effort 171 6.4.2 Applications to Biological and Medical Problems 171 6.5 Summary and Conclusion 182 Acknowledgments 183 References 183 7 Predictive Modeling in Radiation Oncology 189Hao Zhang, Robert Meyer, Leyuan Shi, Wei Lu, and Warren D’Souza 7.1 Introduction 189 7.2 Tutorials of Predictive Modeling Techniques 191 7.2.1 Feature Selection 191 7.2.2 Support Vector Machine 192 7.2.3 Logistic Regression 193 7.2.4 Decision Tree 193 7.3 Review of Recent Predictive Modeling Applications in Radiation Oncology 194 7.3.1 Machine Learning for Medical Image Processing 194 7.3.2 Machine Learning in Real-Time Tumor Localization 196 7.3.3 Machine Learning for Predicting Radiotherapy Response 197 7.4 Modeling Pathologic Response of Esophageal Cancer to Chemoradiotherapy 199 7.4.1 Input Features 200 7.4.2 Feature Selection and Predictive Model Construction 200 7.4.3 Results 202 7.4.4 Discussion 204 7.5 Modeling Clinical Complications after Radiation Therapy 205 7.5.1 Dose-Volume Thresholds: Relationship to OAR Complications 205 7.5.2 Modeling the Radiation-Induced Complications via Treatment Plan Surface 206 7.5.3 Modeling Results 208 7.6 Modeling Tumor Motion with Respiratory Surrogates 211 7.6.1 Cyberknife System Data 211 7.6.2 Modeling for the Prediction of Tumor Positions 212 7.6.3 Results of Tumor Positions Modeling 212 7.6.4 Discussion 214 7.7 Conclusion 215 References 215 8 Mathematical Modeling of Innate Immunity Responses of Sepsis: Modeling and Computational Studies 221Chih-Hang J. Wu, Zhenzhen Shi, David Ben-Arieh, and Steven Q. Simpson 8.1 Background 221 8.2 System Dynamic Mathematical Model (SDMM) 223 8.3 Pathogen Strain Selection 224 8.3.1 Step 1: Kupffer Local Response Model 224 8.3.2 Step 2: Neutrophils Immune Response Model 228 8.3.3 Step 3: Damaged Tissue Model 233 8.3.4 Step 4: Monocytes Immune Response Model 234 8.3.5 Step 5: Anti-inflammatory Immune Response Model 237 8.4 Mathematical Models of Innate Immunity of AIR 239 8.4.1 Inhibition of Anti-inflammatory Cytokines 239 8.4.2 Mathematical Model of Innate Immunity of AIR 239 8.4.3 Stability Analysis 241 8.5 Discussion 247 8.5.1 Effects of Initial Pathogen Load on Sepsis Progression 247 8.5.2 Effects of Pro- and Anti-inflammatory Cytokines on Sepsis Progression 250 8.6 Conclusion 254 References 254 Part II Analytics for Healthcare Delivery 261 9 Systems Analytics: Modeling and Optimizing ClinicWorkflow and Patient Care 263Eva K. Lee, Hany Y. Atallah, Michael D. Wright, Calvin Thomas IV, Eleanor T. Post, Daniel T. Wu, and Leon L. Haley Jr 9.1 Introduction 264 9.2 Background 266 9.3 Challenges and Objectives 267 9.4 Methods and Design of Study 268 9.4.1 ED Workflow and Services 269 9.4.2 Data Collection and Time-Motion Studies 270 9.4.3 Machine Learning for Predicting Patient Characteristics and Return Patterns 274 9.4.4 The Computerized ED System Workflow Model 277 9.4.5 Model Validation 282 9.5 Computational Results, Implementation, and ED Performance Comparison 285 9.5.1 Phase I: Results 285 9.5.2 Phase I: Adoption and Implementation 288 9.5.3 Phase II: Results 288 9.5.4 Phase II: Adoption and Implementation 290 9.6 Benefits and Impacts 292 9.6.1 Quantitative Benefits 294 9.6.2 Qualitative Benefits 296 9.7 Scientific Advances 297 9.7.1 Hospital Care Delivery Advances 297 9.7.2 OR Advances 298 Acknowledgments 298 References 299 10 A Multiobjective Simulation Optimization of the Macrolevel Patient Flow Distribution 303Yunzhe Qiu and Jie Song 10.1 Introduction 303 10.2 Literature Review 305 10.2.1 Simulation Modeling on Patient Flow 305 10.2.2 Multiobjective Patient Flow Optimization Problems 306 10.2.3 Simulation Optimization 307 10.3 Problem Description and Modeling 308 10.3.1 Problem Description 308 10.3.2 System Modeling 310 10.4 Methodology 312 10.4.1 Simulation Model Description 312 10.4.2 Optimization 313 10.5 Case Study: Adjusting Patient Flow for a Two-Level Healthcare System Centered on the Puth 316 10.5.1 Background and Data 316 10.5.2 Simulation under Current Situation 318 10.5.3 Model Validation 320 10.5.4 Optimization through Algorithm 1 321 10.5.5 Optimization through Algorithm 2 322 10.5.6 Comparison of the Two Algorithms 327 10.5.7 Managerial Insights and Recommendations 328 10.6 Conclusions and the Future Work 329 Acknowledgments 330 References 331 11 Analysis of Resource Intensive Activity Volumes in US Hospitals 335Shivon Boodhoo and Sanchoy Das 11.1 Introduction 335 11.2 Structural Classification of Hospitals 337 11.3 Productivity Analysis of Hospitals 339 11.4 Resource and Activity Database for US Hospitals 341 11.4.1 Medicare Data Sources for Hospital Operations 343 11.5 Activity-Based Modeling of Hospital Operations 344 11.5.1 Direct Care Activities 344 11.5.2 The Hospital Unit of Care (HUC) Model 347 11.5.3 HUC Component Results by State 350 11.6 Resource use Profile of Hospitals from HUC Activity Data 351 11.6.1 Comparing the Resource Use Profile of States 353 11.6.2 Application of the Hospital Classification Rules 355 11.7 Summary 357 References 358 12 Discrete-Event Simulation for Primary Care Redesign: Review and a Case Study 361Xiang Zhong, Molly Williams, Jingshan Li, Sally A. Kraft, and Jeffrey S. Sleeth 12.1 Introduction 361 12.2 Review of Relevant Literature 362 12.2.1 Literature on Primary Care Redesign 362 12.2.2 Literature on Discrete-Event Simulation in Healthcare 366 12.2.3 UW Health Improvement Projects 369 12.3 A Simulation Case Study at a Pediatric Clinic 369 12.3.1 Patient Flow 369 12.3.2 Model Development 371 12.3.3 Model Validation 376 12.4 What–If Analyses 376 12.4.1 Staffing Analysis 376 12.4.2 Resident Doctor 377 12.4.3 Schedule Template Change 377 12.4.4 Volume Change 379 12.4.5 Room Assignment 379 12.4.6 Early Start 380 12.4.7 Additional Observations 382 12.5 Conclusions 382 References 382 13 Temporal and Spatiotemporal Models for Ambulance Demand 389Zhengyi Zhou and David S. Matteson 13.1 Introduction 389 13.2 Temporal Ambulance Demand Estimation 391 13.2.1 Notation 392 13.2.2 Factor Modeling with Constraints and Smoothing 393 13.2.3 Adaptive Forecasting with Time Series Models 395 13.3 Spatiotemporal Ambulance Demand Estimation 398 13.3.1 Spatiotemporal Finite Mixture Modeling 400 13.3.2 Estimating Ambulance Demand 403 13.3.3 Model Performance 405 13.4 Conclusions 409 References 410 14 Mathematical Optimization and Simulation Analyses for Optimal Liver Allocation Boundaries 413Naoru Koizumi, Monica Gentili, Rajesh Ganesan, Debasree DasGupta, Amit Patel, Chun-Hung Chen, Nigel Waters, and Keith Melancon 14.1 Introduction 414 14.2 Methods 416 14.2.1 Mathematical Model: Optimal Locations of Transplant Centers and OPO Boundaries 416 14.2.2 Discrete-Event Simulation: Evaluation of Optimal OPO Boundaries 422 14.3 Results 423 14.3.1 New Locations of Transplant Centers 423 14.3.2 New OPO Boundaries 426 14.3.3 Evaluation of New OPO Boundaries 428 14.4 Conclusions 433 Acknowledgment 435 References 435 15 Predictive Analytics in 30-Day Hospital Readmissions for Heart Failure Patients 439Si-Chi Chin, Rui Liu, and Senjuti B. Roy 15.1 Introduction 440 15.2 Analytics in Prediction Hospital Readmission Risk 441 15.2.1 The Overall Prediction Pipeline 441 15.2.2 Data Preprocessing 441 15.2.3 Predictive Models 442 15.2.4 Experiment and Evaluation 444 15.3 Analytics in Recommending Intervention Strategies 447 15.3.1 The Overall Intervention Pipeline 447 15.3.2 Bayesian Network Construction 448 15.3.3 Recommendation Rule Generation 452 15.3.4 Intervention Recommendation 453 15.3.5 Experiments 454 15.4 Related Work 457 15.5 Conclusion 459 References 459 16 Heterogeneous Sensing and Predictive Modeling of Postoperative Outcomes 463Yun Chen, Fabio Leonelli, and Hui Yang 16.1 Introduction 463 16.2 Research Background 466 16.2.1 Acute Physiology and Chronic Health Evaluation (APACHE) 466 16.2.2 Simplified Acute Physiology Score (SAPS) 469 16.2.3 Mortality Probability Model (MPM) 470 16.2.4 Sequential Organ Failure Assessment (SOFA) 472 16.3 Research Methodology 474 16.3.1 Data Categorization 475 16.3.2 Data Preprocessing and Missing Data Imputation 475 16.3.3 Feature Extraction 482 16.3.4 Feature Selection 484 16.3.5 Predictive Model 487 16.3.6 Cross-Validation and Ensemble Voting Processes 489 16.4 Materials and Experimental Design 491 16.5 Experimental Results 491 16.6 Discussion and Conclusions 498 Acknowledgments 499 References 499 17 Analyzing Patient–Physician Interaction in Consultation for Shared Decision Making 503Thembi Mdluli, Joyatee Sarker, Carolina Vivas-Valencia, Nan Kong, and Cleveland G. Shields 17.1 Introduction 503 17.2 Literature Review 505 17.2.1 Patient–Physician Interaction on Prognosis Discussion 506 17.2.2 Physician–Patient Interaction on Pain Assessment 509 17.3 Our Recent Data Mining Studies 510 17.3.1 Predicting Patient Satisfaction with Survey Data 510 17.3.2 Predicting Patient Satisfaction with Conservation Data 513 17.4 Future Directions 515 17.4.1 Regression Shrinkage and Selection 515 17.4.2 Conversational Characterization 517 17.5 Concluding Remarks 519 References 520 18 The History and Modern Applications of Insurance Claims Data in Healthcare Research 523Margrét V. Bjarndóttir, David Czerwinski, and Yihan Guan 18.1 Introduction 523 18.1.1 Advantages and Limitations of Claims Data 525 18.1.2 Application Areas 526 18.1.3 Statistical Methodologies Used in Claims-Based Studies 528 18.2 Healthcare Cost Predictions 531 18.2.1 Modeling of Healthcare Costs 531 18.2.2 Modeling of Disease Burden and Interactions 533 18.2.3 Performance Measures and Baselines 534 18.2.4 Prediction Algorithms 534 18.2.5 Applying Regression Trees to Cost Predictions 535 18.2.6 Applying Clustering Algorithms to Cost Predictions 537 18.2.7 Identifying High-Cost Members 539 18.2.8 Discussion 539 18.3 Measuring Quality of Care 540 18.3.1 Structure, Process, and Outcomes 540 18.3.2 The Quality of Quality Data 542 18.3.3 Composite Quality Measures 542 18.3.4 Practical Considerations for Constructing Quality Scores 544 18.3.5 A Statistical Approach to Measuring Quality 545 18.3.6 Quality as a Case Management Tool 546 18.3.7 Discussion 547 18.4 Conclusions 548 References 548 19 Understanding the Role of Social Media in Healthcare via Analytics: a Health Plan Perspective 555Sinjini Mitra and Rema Padman 19.1 Introduction 555 19.2 Literature Review 556 19.2.1 Privacy and Security Concerns in Social Media and Healthcare 559 19.2.2 Analytics in Healthcare and Social Media 561 19.3 Case Study Description 562 19.3.1 Survey Design 563 19.4 Research Methods and Analytics Tools 564 19.4.1 The Logistic Regression Model 564 19.5 Results and Discussions 568 19.5.1 Descriptive Statistics 568 19.5.2 Baseline of Technology Usage 570 19.5.3 Mobile and Social Media Usage 571 19.5.4 Clustering of Member Population by Technology, Social, and Mobile Media Usage 572 19.5.5 Interest in Adopting Online Tools for Healthcare Purposes 573 19.5.6 Interest in Adopting Mobile Apps for Healthcare Purposes 574 19.5.7 Health and Wellness Objectives 577 19.5.8 Privacy and Security Concerns 580 19.5.9 Predictive Models 581 19.6 Conclusions 584 References 585 Index 589
Les mer