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