Practical data analytics for innovation in medicine: building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Oxford
Elsevier
2023
|
| Ausgabe: | Second edition |
| Schlagworte: | |
| Online-Zugang: | Inhaltsverzeichnis Klappentext |
| Beschreibung: | xli, 533 Seiten Illustrationen, Diagramme |
| ISBN: | 9780323952743 |
Internformat
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV048903255 | ||
| 003 | DE-604 | ||
| 005 | 20230801 | ||
| 007 | t | ||
| 008 | 230418s2023 a||| |||| 00||| eng d | ||
| 020 | |a 9780323952743 |9 978-0-323-95274-3 | ||
| 035 | |a (OCoLC)1390809335 | ||
| 035 | |a (DE-599)BVBBV048903255 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-384 | ||
| 084 | |a XC 4001 |0 (DE-625)152514:12907 |2 rvk | ||
| 100 | 1 | |a Miner, Gary |d 1942- |e Verfasser |0 (DE-588)140491813 |4 aut | |
| 245 | 1 | 0 | |a Practical data analytics for innovation in medicine |b building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |c Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill |
| 250 | |a Second edition | ||
| 264 | 1 | |a Oxford |b Elsevier |c 2023 | |
| 300 | |a xli, 533 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Datenanalyse |0 (DE-588)4123037-1 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Medizinische Informatik |0 (DE-588)4038261-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Modellierung |0 (DE-588)4170297-9 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4143413-4 |a Aufsatzsammlung |2 gnd-content | |
| 689 | 0 | 0 | |a Medizinische Informatik |0 (DE-588)4038261-8 |D s |
| 689 | 0 | 1 | |a Datenanalyse |0 (DE-588)4123037-1 |D s |
| 689 | 0 | 2 | |a Modellierung |0 (DE-588)4170297-9 |D s |
| 689 | 0 | |5 DE-604 | |
| 689 | 1 | 0 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 1 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 1 | |5 DE-604 | |
| 856 | 4 | 2 | |m Digitalisierung UB Augsburg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 856 | 4 | 2 | |m Digitalisierung UB Augsburg - ADAM Catalogue Enrichment |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA |3 Klappentext |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-034167614 | ||
Datensatz im Suchindex
| _version_ | 1804185068851167232 |
|---|---|
| adam_text | Contents About the authors Foreword for the 2nd edition-John Halamka Foreword for the Tst edition by Thomas H. Davenport Foreword for the 1st edition by James Taylor Foreword for the 1 st edition by John Halamka Preface and overview for the 2nd edition Preface to the 1st edition Acknowledgment Guest Chapter Author s Listing Endorsements and reviewer Blurbs—from the 1st edition Instructions for using software for the tutorials—how to download from web pages—for the 2nd edition xix xxiii xxv xxvii xxix xxxi xxxiii xxxv xxxvii xxxix xli Prologue to Part I Part I Historical perspective and the issues of concern for health care delivery in the 21st century 1. What we want to accomplish with this second edition of our first Big Green Book 5 Linda A. Miner Prelude 5 Purpose/summary 5 First reasons for our writing this book 6 Highlighted new material 6 Descriptive statistics, data organization, and example 7 Randomized controlled trials 9 Basic predictive analytics and example 10 Example 11 Research standards common to both traditional and predictive analytics 11 Pandemic as related to research standards and accurate data 11 Especially for the second edition 13 Chapter conclusion 13 Postscript 13 References 14 2. History of predictive analytics in medicine and healthcare 15 Robert Nisbet Prelude Outline Introduction Part I. Development of bodies of medical knowledge Earliest medical records in ancient cultures Classification of medical practice among ancient and modern cultures Medical practice documents in major world cultures of Europe and the Middle East Egypt Mesopotamia
Greece Ancient Rome Galen Arabia Summary of royal medical documentation in ancient cultures Effects of the middle ages on medical documentation Rebirth of Interest in medical documentation during the renaissance The printing press The Protestant Reformation Erasmus Human anatomy Andreas Vesalius (1514-1564) William Harvey (1578-1657) Medical documentation after the enlightenment Medical case documentation The development of the National Library of Medicine Part 11. Analytical decision systems in medicine and healthcare Computers and medical databases Early medical databases 15 15 16 16 17 17 18 18 19 20 22 23 24 25 25 26 26 26 27 27 27 28 28 28 28 29 29 30 vii
viii Contents National Library of Medicine list of online medical databases Other medical research databases Bills of Mortality in London, United Kingdom Best practice guidelines Guidelines of the American Academy of Neurology Medical records move into the digital world Healthcare data systems Postscript References 3. Bioinformatics 30 30 31 31 31 32 32 34 34 35 4. Data and process models in medical informatics 57 Robert (Bob) Nisbet Nephi Walton and Cary D. Miner Prelude 35 The rise of predictive analytics in healthcare 35 Moving from reactive to proactive response in healthcare 36 Medicine and big data 36 An approach to predictive analytics projects 37 The predictive analytics process in healthcare 38 Process steps in Fig. 3.1 38 Translational bioinformatics 42 Clinical decision support systems 42 Hybrid clinical decision support systems 43 Consumer health informatics 44 Patient-focused informatics 44 Health literacy 44 Consumer education 45 Direct-to-consumer genetic testing 45 Use of predictive analytics to avoid an undesirable future 45 Consumer health kiosks 45 Who uses the Internet? Nearly everybody 46 Patient monitoring systems 46 Applications for predictive analytics in intensive care unit patient monitoring systems 47 Challenges of medical devices in the intensive care unit 47 Public health informatics 48 The major problem: lack of resources 48 Social networks and the Pulse of public health 48 Predictive analytics and prevention and disease and injury Biosurveillance Food-borne illness Medical imaging Clinical research informatics Intelligent search engines
Personalized medicine 50 51 51 51 52 52 53 54 54 54 Hospital optimization Challenges Data storage volumes Data privacy and security Portability of PA models Regulation of PA models Summary Postscript References Further reading 49 49 49 49 50 50 50 Prelude 57 Chapter purpose 57 Introduction 57 Systems for classification of diseases and mortality 58 Bills of mortality 58 The ICD system 58 The OMOP common data model 58 Reasons for OMOP 59 The OMOP CDM provides a common data format 60 OMOP CDM architecture is patient-centric 60 Additional data processing operations nec essary to serve the analysis of OMOP data 61 The CRISP-DM processing model 62 How this chapter facilitates patient-centric healthcare 63 Postscript 64 References 64 Further reading 64 5. Access to data for analytics—the Biggest Issue in medical and healthcare predictive analytics 65 Gary D. Miner Prelude 65 Size of data in our world: estimated digital universe now and in the future 65 Convergence of healthcare and modern technologies 66 Reasons why healthcare data is difficult to get and difficult to measure 67 Multiple places where medical data are found 68 Many different formats of medical data: structured and unstructured 68
Contents Another problem is inconsistent definitions Changing government regulatory requirements keep changing what data is taken and kept What are some of the benefits of using good data analytics in medical research and healthcare delivery? Conclusion of 5: the importance of health care data analytics Postscript References Further reading 68 Precision (personalized) medicine 73 69 69 69 70 70 71 Nephi Walton Preamble What is personalized/precision medicine? Personalized medicine versus precision medicine P4 medicine P5 to PIO medicine Precision medicine, genomics, and pharmacogenomics Differences among us Differences go beyond our body and into our environment Changes from birth to death Ancestry and disease Gene therapies It is not about just our genome Changing the definition of diseases Systems biology Efficacy of current methods—why we need personalized medicine Predictive analytics in personalized medicine The future: predictive and prescriptive medicine Application of predictive analytics and decisioning in predictive and prescriptive medicine The diversity of available healthcare data Diversity of data types available Phenotypic data Clinical information Real-time physiological data Imaging data Genomic data Transcriptomics data Epigenomics data Proteomic data Glycomic data Metabolomic data Metagenomic data 73 74 75 75 75 75 76 76 77 77 77 78 78 79 80 80 80 81 82 82 83 83 84 84 85 88 89 90 91 91 92 ix Nutrigenomics data Behavioral measures data Socioeconomic status data Personal activity monitoring data Climatological data Environmental data All the other OMICs The
future Challenges Challenge #1 Challenge #2 Challenge #3 Challenge #4 Challenge #5 Challenge #6 Challenge #7 Challenge #6 Challenge #9 Challenge #10 Challenge #11 Challenge #12 Challenge #13 Postscript References Further reading 92 92 93 93 94 95 95 95 96 96 96 97 97 97 97 98 98 98 98 98 98 99 99 99 102 7. Patient-directed healthcare 105 Linda A. Miner Prelude Empowerment in patient-directed medicine Self-monitoring, N of 1 study Research questions The responsible patient Patients changing how medicine is practiced Patient empowerment versus compliance Collaboration between patients and the medical community Patient involvement Patient involvement in medical education Limitations of patient involvement Evidence supporting patient involvement Family-wise statistical errors Communication and trust Communication and trust during the pandemic Collaboration and limitations How patient-directed medicine works using predictive analytics Privacy concerns can hinder research Predictive analytics for patient-directed research 106 106 106 108 108 108 109 109 109 110 110 111 113 113 113 114 114 114 115
x Contents Cultures and decisions Coordination of care and communication for patient-directed healthcare Communication skills in the medical setting Communication studies Barriers to productive communication Patients selecting their best models of care Medical homes The integrated healthcare delivery system model Comparison with accountable care organization Direct pay/direct care model Consumerism and advertising in patient-directed healthcare Advertising to patients Research studies related to advertising and consumerism Privacy of prescription data. Is it private? Patients diagnosing themselves amid targeted advertising Patients making use of technology and advertising for good or for bad Patient payment models and effects on self directed healthcare Burden of healthcare—predicting the future Predicting life and death Misapplication of treatment increases costs Models of insurance—predicting the best for individuals Research assisting patients in self-education and decisions Patient self-responsibility: highlight on obesity Percent of obesity Distribution of obesity in the United States—costs and related diseases Cascading effects on sleep of obesity Obesity, cholesterol, statins, and patient-directed healthcare The need for N of 1 studies N of 1 study examples Data scientists could make a fortune— development of apps and artificial intelligence for phones and PC application Patient portals Alternatives and new models Medical tourism Where could it go wrong? Alternative screenings Self-diagnostic kits An alternative to traditional insurance Doctors striking out on their
own Alternative ways of knowing about ourselves—genomic predictions Some concerns Predictive analytics for patient decision-making Connectivity Controlling some diseases by searching research on one s own Portals, evidence medicine, and gold standards in predictive analytics Patientsite at Beth Israel Cleveland clinic Body computing Diagnostic apps Chapter conclusion Postscript References 116 116 117 117 119 121 121 121 122 122 123 123 142 143 144 145 145 146 147 147 148 148 149 150 150 124 124 125 8. 126 Regulatory measures—agencies. and data issues in medicine and healthcare 159 Cary D. Miner 127 128 128 129 Prelude Introduction What is an electronic medical records? Five of the best open source electronic medical records systems for medical practices Rise of the international classification of disease Six Sigma Quality control Lean concepts for healthcare: the lean hospital as a methodology of Six Sigma Root cause analysis Henry Ford Hospitals and Virginia Mason Hospital Postscript References Further reading 129 131 132 132 133 134 135 136 136 137 138 139 139 140 140 141 142 142 9. Predictive analytics with multiomics data 159 159 160 161 162 164 165 165 166 166 167 167 169 171 Robert A. Nisbet Prelude Introduction to multiomics Genomics Multiomics Multiomics systems biology 171 171 172 172 173
Contents Basic analytics operations in multiomics 174 Multiomics data integration 174 Multiomics data preparation 174 Methodological bias 175 Unrepresentative negatives 175 Imbalance of data sets with rare target variables 175 Data preparation issues specific to particular omics data sets 175 Analysis methods 177 Statistical analysis methods 177 Machine learning methods 177 Data conditioning 178 Data preprocessing tools in multiomics 179 Multiomics analytical methods 179 Open source tools for multiomics analytics 179 Machine learning tools in multiomics analytics 180 Focus on metabolomics 180 Prediction of pancreatic and lung cancer from metabolomics data 181 Postscript 182 References 182 Further reading 183 10. Artificial intelligence and genomics 185 Nephi Walton and Cary D. Miner Prelude 185 How do we enable the clinical application of artificial intelligence in genomics? 185 Genomics fast moving field—and now ready for artificial intelligence to have an impact 185 Need to open existing large datasets to more researchers 186 Successful artificial intelligence models will be ones that use smaller and manageable portions of the human genome 186 Polygenic risk scores 186 Artificial intelligence models cannot replace but must augment physicians diagnosis and treatment decisions 186 Governance—balance between rapid approval of models and ensuring no human harm 187 EHR and integration of artificial intelligence into clinical workflows 187 What would an artificial intelligence and genomics integration look like? 187 Real-world examples of artificial intelligence and genomics
modeling systems emerging in 2022 187 Conclusions 189 Postscript References Further reading xi 189 190 190 Prologue to Part II Part II Practical step-by-step tutorials and case studies Prologue to Part III Part III Practical application examples 11. Glaucoma (eye disease): a real case study; with suggested predictive analytic modeling for identifying an individual patient s best diagnosis and best treatment 199 Cary D. Miner, Linda A. Miner and Billie Corkerin Prelude Why this chapter in this book? How serious is glaucoma? Why do we need to watch for it? What is a normal eye pressure? Characteristics of glaucoma disease Risk factors and treatment Basic anatomy of the eye and relation of physical structure to glaucoma disease What is glaucoma? What is the normal pressure (IOP) in the eye? What causes a rise in intraocular pressure above the norm of 10-21 ? Pathophysiology of glaucoma Diagnosis of glaucoma lllustrations/photo of eye Minimally invasive surgeries can be invasive Invasive surgical treatments What does the XEN-gel stint look like? What is its size? Ahmed valve shunt. What does the Ahmed valve shunt look like? Long-term results of using Ahmed valve shunts for glaucoma Fluid flow in the two main types of glaucoma Open angle Closed angle 200 200 200 200 200 201 201 202 202 202 204 204 205 205 206 207 207 207 209 209 209
xii Contents Photography of eye—looking at fundus in the diagnosis of glaucoma 209 Case study: my (Gary s) glaucoma progression (from about 2010 to 2022) 209 Self-monitoring intraocular pressure by the patient for more accurate DX and treatment decisions 213 i-CARE home device for patient home monitoring of intraocular pressure values 213 As others are stating 217 My invasive surgery—2021-XEN-gel shunt and later Ahmed valve shunt 217 Increased night-time urination frequency was an unpleasant side-effect of my using steroid eyedrops 219 Is increase in urination frequency a common side effect of use of steroids in eye drops ? 219 Suggested absorbsion pathway of Loetmax SM; Helping to determine best treatment 226 Predictive analytic modeling possibilities 227 Even visual field tests can now be automated with artificial intelligence—machine learning methods 234 Using STATISTICA statistical and predictive analytic software to visualize patient Gary s IOP data DOSE OF Generic-COSOPT (=Dorzolam¡de-Timolol)—is three times a day OK? Future possible treatments for glaucoma FINAL IOP levels for Gary upon finding optimum mix of steroid and IOP eye drops Postscript References Further reading 238 239 245 246 251 251 255 12. Using data science algorithms in predicting ICU patient urine output in response to diuretics to aid clinicians and healthcare workers in clinical decision-making 257 AnnaJ.C. Russell-Toner Prelude Introduction Outputs and conclusion from a literature review The data used 257 258 258 258 Source of data Data demographics Technology used Algorithm outputs and
decisions Algorithm version 1 Algorithm version 2 Algorithm version 3 The champion algorithms Further research not published here—a 258 258 261 264 264 283 303 313 champion emerges The conclusions on our champion 320 algorithm Examples to illustrate model performance 320 for actual patients Conclusions and further recommendations 321 322 322 323 323 323 Conclusions Recommendations Postscript Further reading 13. Prediction tool developmentcreation and adoption of robust predictive model metrics at the bedside for greatly benefiting the patient, like preterm infants at risk of bronchopulmonary dysplasia, using Shiny-R 325 John B.C. Tan, Rebekah Μ. Leigh and Fu-Sheng Chou Prelude Author s note Rationale Exploratory data analysis for health data Methods Obtaining and processing data Using R Shiny for efficient data input and visualization After obtaining the finalized clean data Code examples and tutorial Data cleaning and TidyR examples Initializing an R Shiny web app Loading and saving onto a SQL database Showing and interacting with data Conclusion Appendix Download links Versions of software and packages Postscript References Further reading 325 325 326 326 328 328 329 329 331 331 332 334 334 336 336 336 336 336 337 337
Contents 14. Modeling precancerous colon polyps with OMOP data 339 Robert A. Nisbet Prelude Chapter purpose Introduction The University of California, Irvine Colonoscopy Quality Database The UCl Colon Polyp Project Previous colon cancer risk screening and predictive modeling programs OMOP data Caveat Modeling objective Methods Major tasks of data preparation of OMOP data for modeling Data access The modeling tool Data integration Target variable definition Data type changes Data quality assessment and resolution Data exclusions Aggregation to the patient level Unique code determination Text mining frequency analysis Manual variable derivation Derivation of one-hot (binary) variables Feature selection process The short-list Methods of feature selection Variable filtering Wrapper methods Data conditioning Balancing the data set Unrepresentative negatives Positive unlabeled learning Modeling Modeling algorithms Cross-validation Ensemble modeling Results and discussion Model evaluation Prediction accuracies Receiver operator characteristic curve Other important aspects of the trained model Important predictor variables Emergent properties Automation of data preparation for medical informatics? 339 340 340 340 341 341 342 342 342 342 342 342 343 343 344 345 345 345 345 345 346 346 347 347 347 348 348 348 348 348 348 349 349 349 349 350 350 350 351 351 351 351 351 353 Conclusions How this chapter facilitates patient-centric medical health care Postscript References Further reading xiii 353 353 354 354 354 15. Prediction of pancreatic and lung cancer from metabolomics data 355
Robert A. Nisbet Prelude Purpose of this chapter Introduction Cancer deaths in the United States Cancer metabolites Methods The modeling process Results Model accuracy Specific models for lung cancer and pancreatic cancer Discussion Implications of this case study for future medical diagnosis Conclusions How this chapter facilitates patient-centric healthcare Postscript References 16. Covid-19 descriptive analytics visualization of pandemic and hospitalization data 355 355 356 356 356 356 356 358 358 359 359 360 360 360 360 360 361 Robert (Bob) Nisbet Preamble Introduction 3 KNIME workflow data streams Preparatory steps for using this tutorial General introduction to KNIME Data access—the file reader node Data understanding Country selection Visualization data stream Using the workflow for another country How this chapter facilitates patient-centric healthcare Postscript Further reading 361 361 361 362 364 365 365 365 368 372 373 373 373
xiv Contents 17. Disseminated intravascular coagulation predictive analytics with pediatric ICU admissions 375 Linda A. Miner, Harsha Chandnani, Mitchell Goldstein, Mahmood H. Khichi and Cynthia H. Tinsley Prelude 375 Introduction 375 Background (from first edition) 376 The example 377 Data files 377 First week of analysis 378 Data mining recipes using statistica 379 Data imputation 380 Using the 11,459 imputed file—training data 381 Training data (11,569 imputed) continued 384 A problem 385 Randomly separating the data and new data mining recipe 385 Final analysis—a return to the past 387 Conclusion—personal ending thoughts 388 Postscript 388 References 388 Prologue to Part IV Part IV Advanced topics in administration and delivery of health care including practical predictive analytics for medicine in the future 18. Challenges for healthcare administration and delivery: integrating predictive and prescriptive modeling into personalized-precision healthcare 19. Challenges of medical research in incorporating modern data analytics in studies 401 Nephi Walton, Gary D. Miner and Linda A. Miner Prelude Introduction—challenges to medical researchers Trends that we might want toknow about Automation and machinelearning (AutoML) Blockchain Conversational artificial intelligence Digital twins Medical competitions Conclusion Postscript References Further reading 401 401 402 403 403 403 403 403 403 404 404 404 20. The nature of insight from data and implications for automated decisioning: predictive and prescriptive models, decisions, and actions 405 Thomas Hill 395 Nephi Walton,
Gary D. Miner and Mitchell Goldstein Prelude Introduction to challenges in healthcare delivery Challenge #1 Challenge #2 Challenge #3 Challenge #4 Challenge #5 397 397 397 398 398 398 398 398 399 Challenge #6 Challenge #7 Challenge #8 Challenge #9 Challenge #10 Challenge # 11 Postscript References Further reading 395 395 395 396 396 396 396 Prelude Overview The purpose of this chapter The nature of insight and expertise Procedural and declarative knowledge 405 406 406 406 406 Nonconscious acquisition of knowledge Conclusion: expertise and the application of pattern recognition methods Statistical analysis versus pattern recognition Fitting a priori models Pattern recognition: data are the model The data are the model 407 Pattern recognition in artificial intelligence/ machine learning: general approximators 407 408 408 408 408 410
Contents Pattern recognition and declarative knowledge: interpretability of results 410 Explainability of artificial intelligence/machine learning models 410 Global and local explainability 410 Statistical models, and reason scores for linear models 411 What-if, and reason scores asderivatives 412 Explainability of nonlinear models, artificial intelligence/machine learning models 412 Local interpretable model-agnostic explanations 412 Shapley additive exPlanations 412 Comparing local interpretable model-agnostic explanations and Shapley additive explanations 413 Caution: inverse predictions can bevery risky 413 Inverse prediction 413 Correlation is not necessarily causation 413 Lack of evidence at the specific point in the input space 414 Optimization of inputs to achieve a desired output 414 Naive explanations 415 Summary 415 Postscript 415 References 415 21. Model management and ModelOps: managing an artificial intelligence-driven enterprise 417 Thomas Hi!! Prelude 417 Introduction 417 The model building/authoring life cycle 418 Overview: managing the life cycles for thousands of models 419 Types of analytic models 419 Managing the risks of analytics, artificial intelligence 420 Do-no-harm 421 ModelOps scope 421 ModelOps details: managing model pipelines and reusable steps 422 The tools and languages of artificial intelligence/machine learning 422 Reusable steps, building intellectual property 423 Managing model life cycles 424 Model monitoring 425 Monitoring risks 427 Efficiency, agility, elasticity, and technology 427 Cloud architecture Managing models for data-at-rest
and data-in-motion Conclusion Postscript References Further reading XV 427 428 430 430 430 431 22. The forecasts for advances in predictive and prescriptive analytics and related technologies for the year 2022 and beyond 433 Cary D. Miner, Linda A. Miner and Scott Burk Prelude Section I: specific technological trends predicted for 2022-2023+ What is predictive analytics, and what are the most frequently used methods (or algorithms) in predictive analytics? What is prescriptive analytics, and what is an example of prescriptive analytics? Part I—healthcare: what trends can we expect in the year 2022 and beyond? What do these three things mean? Part 2—In general: PA and business intelligence trends for 2022 TOP 10 analytics and business intelligence trends for 2022 Key artificial intelligence and data analytics trends for 2022 andbeyond Section II: overriding philosophies which will guide trendsover thenext 10 years Postscript References 433 433 433 434 434 435 436 437 437 439 440 440 23. Sampling and data analysis: variability in data may be a better predictor than exact data points with many kinds of Medical situations 443 Mitchell Goldstein and Gary D. Miner Prelude Sampling and data analysis issues Purpose summary of this chapter One issue—electronic health record and specific measures taken on patients Pulse oximetry data measurements, as an example Introduction Objective 443 443 443 444 445 445 445
xvi Contents Methods 445 Results 445 Discussion 449 Conclusion on Pulse Oximetry Example 450 Eye-intraocular pressure measurements: a personal example by one of the authors to illustrate the problem of when and how data is collected 450 Example of comparison of Goldman with i-CARE HOME intraocular pressure readings 451 In conclusion 451 Types of data analysis that may be helpful in solving the types of issues presented in this chapter 452 Reliability of inputs determines the validity of models 453 However, it gets more complicated 453 Butthen, it gets even more complicated 453 Clinical Dx and treatment needed changes for true patient-centered care 454 Postscript 454 References 455 Further reading 456 24. Analytics architectures for the 21st century 457 Scott Burk Prelude Introduction Purpose/summary Organizational design for success Some say it starts with data,it doesn t Organizational alignment Framework for trustworthy and ethical Al and analytics Data design for success Why is data so important? The potential of data is insight and action Data and analytics literacy are requirements to successful programs Brief considerations in data architecture Processes, systems, and data Data volume Data variety Data velocity Data value Data veracity Connecting and moving data—data in motion Application programming interfaces and management Microservices 457 457 457 458 458 458 459 459 459 459 460 460 461 461 461 462 462 462 462 462 463 Streaming data Data stores and limitations of the enterprise data warehouses Analytics design for success Technology to create analytics Technology
to communicate and act upon analytics Conclusion Postscript References 463 463 468 468 471 471 472 472 25. Predictive models versus prescriptive models; causal inference and Bayesian networks 473 Scott Burk Prelude Introduction Classification of Al and ML models in medicine Descriptive analytics Diagnostics analytics Predictive analytics Prescriptive analytics Process optimization Causation—the most misunderstood concept in data science today Some basic assumptions for predictive modeling Some basic assumptions for prescriptive modeling Using a predictive model for prescription purposes Some important notes on observational studies Causal inference and why it is important Bridging the causal models to statistical models—causal inference Bayesian networks Causal inference and the do-calculus A summary example of causal modeling Conclusion Postscript References Further reading 473 473 474 474 475 475 475 475 476 477 477 478 479 479 480 480 481 482 484 485 485 485 26. The future: 21st century healthcare and wellness in the digital age 487 Cary D. Miner and Linda A Miner Prelude Overview 487 488
Contents Background and need for change Comparative effectiveness research and heterogeneous treatment effect research New technology and 21 st century healthcare: health startup firms We wrote this back in 2014 for the first edition of this book Well did this all happen as predicted? Not quite Listing of other e-items in this outside of healthcare facilities category but within at least the partial control of patients Examples of wearable devices that are working for people today Atrial fibrillation wearable watch sensors Eye pressure (1OP) home measurement devices Nonautomatic vital health signal measuring devices Blood pressure devices Oxygen level home monitors Trends and expectations for the future of health IT and analytics 488 489 490 490 491 493 493 493 494 495 495 495 495 Bottom-Up small-sized but working individually controlled data gathering and instant analytics output systems Where will the next innovations in medicine come from? N-of-1 studies—the future for person-centered healthcare Styles of thinking—how brain laterality affects innovation in healthcare Final concluding statements 505 How much should we listen to algorithms?— Should machines make the decisions? Genomics and Al will start exploding in 2 02 2 and subsequent years, and thus we need to be prepared Patient-centered (precision) health for the future Postscript References Further reading Appendix A: Modeling new COVID-19 deaths Index xvii 501 502 502 503 505 505 505 505 506 508 511 519
Practical Data Analytics for Innovation in Medicine Building Real Predictive and Prescriptive Models in Personalized Healthcare and Medical Research Using Al, ML, and Related Technologies Second Edition Gary D. Miner, PhD, CEO, Μ Μ Predictive Analytics LLC, Tulsa, OK; Associate Editor, The Journal of Geriatric Psychiatry and Neurology; Private Con sulting, Tulsa, OK Linda A. Miner, PhD, Professor Emeritus, Professional and Graduate Studies as Program Director, Southern Nazarene University; Editorial Board, The Journal of Geriatric Psychiatry and Neurology; Private Consulting, Tulsa, OK Scott Burk, PțiD, Data Scientist, Architect Thought Leader TIBCO; Professor, Data Mining and Predictive Analytics, New York University; Temple, TX Mitchell Goldstein, MD, MBA, CML, FAAP, Professor of Pediatrics, Division of Neonatology, Director Neonatal ECMO Program; Loma Linda School of Medicine, Loma Linda University Children s Hospital; Loma Linda, CA; Editor-in-Chief Neonatology Today, Loma Linda, CA Robert Nisbet, PhD, Researcher-Medical Informatics, H.H. Chao Comprehensive Digestive Disease Center, University of California Irvine Medical Center, Private Consulting, Santa Barbara, CA Nephi Walton, MD, MS, FACMG, FAMIA, Associate Medical Director, Intermountain Healthcare, Precision Genomics, Salt Lake City, UT Thomas Hill, PhD, Senior Director and Product Manager, Advanced Analytics,TIBCO,Tulsa, OK Practical Data Analytics for Innovation in Medicine: Building Real Predictive Prescriptive Models in Personalized Healthcare and Medical Research Using Al, ML, and Related Technologies
Second Edition discusses the needs of healthcare and medicine in the 21 st century and ex plains how data analytics play an important and revolutionary role on fulfilling them. With healthcare effectiveness and economics facing growing challenges, there is a rapidly emerging movement to fortify medical treatment and administration by tapping the predictive power of big data, and it has shown solid results: predictive analytics bolster patient care, reduce cost, and deliver greater efficiencies across a wide range of operational functions. The first ¿Dart of the book brings a historical perspective and the issues of concern for healthcare delivery currently, highlighting the importance of using predictive analytics to help solve health crisis such as the COVID-19 pandemic. The second part provides access to practical step-by-step tu torials and case studies online, available in the book s companion website, to help reader to apply the knowledge gained through exercises based on real-world examples of successful predictive and prescriptive tools and systems. The central part of the book also contains seven case studies emphasizing precision medicine. The final part focuses on specific technical operations related to quality, cost-effective medical and nursing care delivery and administration brought by practical predictive analytics; in addition, it discusses future developments on decisioning platforms that allow rapid/instant decisions on medical care and delivery. The book is a valuable resource for researchers, practitioners, healthcare industry workers, policy makers,
and members of medical and biomedical fields who are interested to learn about recent developments on data analytics applied to healthcare and medicine. Key Features • Brings a historical perspective in medical care to discuss both the current status of health care delivery worldwide and the importance of using modern predictive analytics to help solve the health care crisis. Provides online tutorials on several predictive analytics systems to help readers to apply their knowledge on today s medical issues and basic research. Teaches how to develop effective predictive analytical research and to create decisioning/prescriptive analytics systems to make medical decisions quicker and more accurate.
|
| adam_txt |
Contents About the authors Foreword for the 2nd edition-John Halamka Foreword for the Tst edition by Thomas H. Davenport Foreword for the 1st edition by James Taylor Foreword for the 1 st edition by John Halamka Preface and overview for the 2nd edition Preface to the 1st edition Acknowledgment Guest Chapter Author's Listing Endorsements and reviewer Blurbs—from the 1st edition Instructions for using software for the tutorials—how to download from web pages—for the 2nd edition xix xxiii xxv xxvii xxix xxxi xxxiii xxxv xxxvii xxxix xli Prologue to Part I Part I Historical perspective and the issues of concern for health care delivery in the 21st century 1. What we want to accomplish with this second edition of our first "Big Green Book" 5 Linda A. Miner Prelude 5 Purpose/summary 5 First reasons for our writing this book 6 Highlighted new material 6 Descriptive statistics, data organization, and example 7 Randomized controlled trials 9 Basic predictive analytics and example 10 Example 11 Research standards common to both traditional and predictive analytics 11 Pandemic as related to research standards and accurate data 11 Especially for the second edition 13 Chapter conclusion 13 Postscript 13 References 14 2. History of predictive analytics in medicine and healthcare 15 Robert Nisbet Prelude Outline Introduction Part I. Development of bodies of medical knowledge Earliest medical records in ancient cultures Classification of medical practice among ancient and modern cultures Medical practice documents in major world cultures of Europe and the Middle East Egypt Mesopotamia
Greece Ancient Rome Galen Arabia Summary of royal medical documentation in ancient cultures Effects of the middle ages on medical documentation Rebirth of Interest in medical documentation during the renaissance The printing press The Protestant Reformation Erasmus Human anatomy Andreas Vesalius (1514-1564) William Harvey (1578-1657) Medical documentation after the enlightenment Medical case documentation The development of the National Library of Medicine Part 11. Analytical decision systems in medicine and healthcare Computers and medical databases Early medical databases 15 15 16 16 17 17 18 18 19 20 22 23 24 25 25 26 26 26 27 27 27 28 28 28 28 29 29 30 vii
viii Contents National Library of Medicine list of online medical databases Other medical research databases Bills of Mortality in London, United Kingdom Best practice guidelines Guidelines of the American Academy of Neurology Medical records move into the digital world Healthcare data systems Postscript References 3. Bioinformatics 30 30 31 31 31 32 32 34 34 35 4. Data and process models in medical informatics 57 Robert (Bob) Nisbet Nephi Walton and Cary D. Miner Prelude 35 The rise of predictive analytics in healthcare 35 Moving from reactive to proactive response in healthcare 36 Medicine and big data 36 An approach to predictive analytics projects 37 The predictive analytics process in healthcare 38 Process steps in Fig. 3.1 38 Translational bioinformatics 42 Clinical decision support systems 42 Hybrid clinical decision support systems 43 Consumer health informatics 44 Patient-focused informatics 44 Health literacy 44 Consumer education 45 Direct-to-consumer genetic testing 45 Use of predictive analytics to avoid an undesirable future 45 Consumer health kiosks 45 Who uses the Internet? Nearly everybody 46 Patient monitoring systems 46 Applications for predictive analytics in intensive care unit patient monitoring systems 47 Challenges of medical devices in the intensive care unit 47 Public health informatics 48 The major problem: lack of resources 48 Social networks and the "Pulse" of public health 48 Predictive analytics and prevention and disease and injury Biosurveillance Food-borne illness Medical imaging Clinical research informatics Intelligent search engines
Personalized medicine 50 51 51 51 52 52 53 54 54 54 Hospital optimization Challenges Data storage volumes Data privacy and security Portability of PA models Regulation of PA models Summary Postscript References Further reading 49 49 49 49 50 50 50 Prelude 57 Chapter purpose 57 Introduction 57 Systems for classification of diseases and mortality 58 Bills of mortality 58 The ICD system 58 The OMOP common data model 58 Reasons for OMOP 59 The OMOP CDM provides a common data format 60 OMOP CDM architecture is patient-centric 60 Additional data processing operations nec essary to serve the analysis of OMOP data 61 The CRISP-DM processing model 62 How this chapter facilitates patient-centric healthcare 63 Postscript 64 References 64 Further reading 64 5. Access to data for analytics—the "Biggest Issue" in medical and healthcare predictive analytics 65 Gary D. Miner Prelude 65 Size of data in our world: estimated digital universe now and in the future 65 Convergence of healthcare and modern technologies 66 Reasons why healthcare data is difficult to get and difficult to measure 67 Multiple places where medical data are found 68 Many different formats of medical data: structured and unstructured 68
Contents Another problem is inconsistent definitions Changing government regulatory requirements keep changing what data is taken and kept What are some of the benefits of using good data analytics in medical research and healthcare delivery? Conclusion of 5: the importance of health care data analytics Postscript References Further reading 68 Precision (personalized) medicine 73 69 69 69 70 70 71 Nephi Walton Preamble What is personalized/precision medicine? Personalized medicine versus precision medicine P4 medicine P5 to PIO medicine Precision medicine, genomics, and pharmacogenomics Differences among us Differences go beyond our body and into our environment Changes from birth to death Ancestry and disease Gene therapies It is not about just our genome Changing the definition of diseases Systems biology Efficacy of current methods—why we need personalized medicine Predictive analytics in personalized medicine The future: predictive and prescriptive medicine Application of predictive analytics and decisioning in predictive and prescriptive medicine The diversity of available healthcare data Diversity of data types available Phenotypic data Clinical information Real-time physiological data Imaging data Genomic data Transcriptomics data Epigenomics data Proteomic data Glycomic data Metabolomic data Metagenomic data 73 74 75 75 75 75 76 76 77 77 77 78 78 79 80 80 80 81 82 82 83 83 84 84 85 88 89 90 91 91 92 ix Nutrigenomics data Behavioral measures data Socioeconomic status data Personal activity monitoring data Climatological data Environmental data All the other OMICs The
future Challenges Challenge #1 Challenge #2 Challenge #3 Challenge #4 Challenge #5 Challenge #6 Challenge #7 Challenge #6 Challenge #9 Challenge #10 Challenge #11 Challenge #12 Challenge #13 Postscript References Further reading 92 92 93 93 94 95 95 95 96 96 96 97 97 97 97 98 98 98 98 98 98 99 99 99 102 7. Patient-directed healthcare 105 Linda A. Miner Prelude Empowerment in patient-directed medicine Self-monitoring, N of 1 study Research questions The responsible patient Patients changing how medicine is practiced Patient empowerment versus compliance Collaboration between patients and the medical community Patient involvement Patient involvement in medical education Limitations of patient involvement Evidence supporting patient involvement Family-wise statistical errors Communication and trust Communication and trust during the pandemic Collaboration and limitations How patient-directed medicine works using predictive analytics Privacy concerns can hinder research Predictive analytics for patient-directed research 106 106 106 108 108 108 109 109 109 110 110 111 113 113 113 114 114 114 115
x Contents Cultures and decisions Coordination of care and communication for patient-directed healthcare Communication skills in the medical setting Communication studies Barriers to productive communication Patients selecting their best models of care Medical homes The integrated healthcare delivery system model Comparison with accountable care organization Direct pay/direct care model Consumerism and advertising in patient-directed healthcare Advertising to patients Research studies related to advertising and consumerism Privacy of prescription data. Is it private? Patients diagnosing themselves amid targeted advertising Patients making use of technology and advertising for good or for bad Patient payment models and effects on self directed healthcare Burden of healthcare—predicting the future Predicting life and death Misapplication of treatment increases costs Models of insurance—predicting the best for individuals Research assisting patients in self-education and decisions Patient self-responsibility: highlight on obesity Percent of obesity Distribution of obesity in the United States—costs and related diseases Cascading effects on sleep of obesity Obesity, cholesterol, statins, and patient-directed healthcare The need for N of 1 studies N of 1 study examples Data scientists could make a fortune— development of apps and artificial intelligence for phones and PC application Patient portals Alternatives and new models Medical tourism Where could it go wrong? Alternative screenings Self-diagnostic kits An alternative to traditional insurance Doctors striking out on their
own Alternative ways of knowing about ourselves—genomic predictions Some concerns Predictive analytics for patient decision-making Connectivity Controlling some diseases by searching research on one's own Portals, evidence medicine, and gold standards in predictive analytics Patientsite at Beth Israel Cleveland clinic Body computing Diagnostic apps Chapter conclusion Postscript References 116 116 117 117 119 121 121 121 122 122 123 123 142 143 144 145 145 146 147 147 148 148 149 150 150 124 124 125 8. 126 Regulatory measures—agencies. and data issues in medicine and healthcare 159 Cary D. Miner 127 128 128 129 Prelude Introduction What is an electronic medical records? Five of the best open source electronic medical records systems for medical practices Rise of the international classification of disease Six Sigma Quality control Lean concepts for healthcare: the lean hospital as a methodology of Six Sigma Root cause analysis Henry Ford Hospitals and Virginia Mason Hospital Postscript References Further reading 129 131 132 132 133 134 135 136 136 137 138 139 139 140 140 141 142 142 9. Predictive analytics with multiomics data 159 159 160 161 162 164 165 165 166 166 167 167 169 171 Robert A. Nisbet Prelude Introduction to multiomics Genomics Multiomics Multiomics systems biology 171 171 172 172 173
Contents Basic analytics operations in multiomics 174 Multiomics data integration 174 Multiomics data preparation 174 Methodological bias 175 Unrepresentative negatives 175 Imbalance of data sets with rare target variables 175 Data preparation issues specific to particular omics data sets 175 Analysis methods 177 Statistical analysis methods 177 Machine learning methods 177 Data conditioning 178 Data preprocessing tools in multiomics 179 Multiomics analytical methods 179 Open source tools for multiomics analytics 179 Machine learning tools in multiomics analytics 180 Focus on metabolomics 180 Prediction of pancreatic and lung cancer from metabolomics data 181 Postscript 182 References 182 Further reading 183 10. Artificial intelligence and genomics 185 Nephi Walton and Cary D. Miner Prelude 185 How do we enable the clinical application of artificial intelligence in genomics? 185 Genomics fast moving field—and now ready for artificial intelligence to have an impact 185 Need to open existing large datasets to more researchers 186 Successful artificial intelligence models will be ones that use smaller and manageable portions of the human genome 186 Polygenic risk scores 186 Artificial intelligence models cannot replace but must augment physicians diagnosis and treatment decisions 186 Governance—balance between rapid approval of models and ensuring no human harm 187 EHR and integration of artificial intelligence into clinical workflows 187 What would an artificial intelligence and genomics integration look like? 187 Real-world examples of artificial intelligence and genomics
modeling systems emerging in 2022 187 Conclusions 189 Postscript References Further reading xi 189 190 190 Prologue to Part II Part II Practical step-by-step tutorials and case studies Prologue to Part III Part III Practical application examples 11. Glaucoma (eye disease): a real case study; with suggested predictive analytic modeling for identifying an individual patient's best diagnosis and best treatment 199 Cary D. Miner, Linda A. Miner and Billie Corkerin Prelude Why this chapter in this book? How serious is glaucoma? Why do we need to watch for it? What is a normal eye pressure? Characteristics of glaucoma disease Risk factors and treatment Basic anatomy of the eye and relation of physical structure to glaucoma disease What is glaucoma? What is the normal pressure (IOP) in the eye? What causes a rise in intraocular pressure above the norm of 10-21 ? Pathophysiology of glaucoma Diagnosis of glaucoma lllustrations/photo of eye "Minimally invasive" surgeries can be invasive Invasive surgical treatments What does the XEN-gel stint look like? What is its size? Ahmed valve shunt. What does the Ahmed valve shunt look like? Long-term results of using Ahmed valve shunts for glaucoma Fluid flow in the two main types of glaucoma Open angle Closed angle 200 200 200 200 200 201 201 202 202 202 204 204 205 205 206 207 207 207 209 209 209
xii Contents Photography of eye—looking at fundus in the diagnosis of glaucoma 209 Case study: my (Gary's) glaucoma progression (from about 2010 to 2022) 209 Self-monitoring intraocular pressure by the patient for more accurate DX and treatment decisions 213 i-CARE home device for patient home monitoring of intraocular pressure values 213 As others are stating 217 My invasive surgery—2021-XEN-gel shunt and later Ahmed valve shunt 217 Increased night-time urination frequency was an unpleasant side-effect of my using steroid eyedrops 219 Is increase in "urination frequency" a common side effect of use of "steroids in eye drops"? 219 Suggested absorbsion pathway of Loetmax SM; Helping to determine best treatment 226 Predictive analytic modeling possibilities 227 Even visual field tests can now be automated with artificial intelligence—machine learning methods 234 Using STATISTICA statistical and predictive analytic software to visualize patient Gary's IOP data DOSE OF "Generic-COSOPT" (=Dorzolam¡de-Timolol)—is three times a day OK? Future possible treatments for glaucoma FINAL IOP levels for Gary upon finding "optimum mix of steroid and IOP eye drops" Postscript References Further reading 238 239 245 246 251 251 255 12. Using data science algorithms in predicting ICU patient urine output in response to diuretics to aid clinicians and healthcare workers in clinical decision-making 257 AnnaJ.C. Russell-Toner Prelude Introduction Outputs and conclusion from a literature review The data used 257 258 258 258 Source of data Data demographics Technology used Algorithm outputs and
decisions Algorithm version 1 Algorithm version 2 Algorithm version 3 The champion algorithms Further research not published here—a 258 258 261 264 264 283 303 313 champion emerges The conclusions on our champion 320 algorithm Examples to illustrate model performance 320 for actual patients Conclusions and further recommendations 321 322 322 323 323 323 Conclusions Recommendations Postscript Further reading 13. Prediction tool developmentcreation and adoption of robust predictive model metrics at the bedside for greatly benefiting the patient, like preterm infants at risk of bronchopulmonary dysplasia, using Shiny-R 325 John B.C. Tan, Rebekah Μ. Leigh and Fu-Sheng Chou Prelude Author's note Rationale Exploratory data analysis for health data Methods Obtaining and processing data Using R Shiny for efficient data input and visualization After obtaining the finalized clean data Code examples and tutorial Data cleaning and TidyR examples Initializing an R Shiny web app Loading and saving onto a SQL database Showing and interacting with data Conclusion Appendix Download links Versions of software and packages Postscript References Further reading 325 325 326 326 328 328 329 329 331 331 332 334 334 336 336 336 336 336 337 337
Contents 14. Modeling precancerous colon polyps with OMOP data 339 Robert A. Nisbet Prelude Chapter purpose Introduction The University of California, Irvine Colonoscopy Quality Database The UCl Colon Polyp Project Previous colon cancer risk screening and predictive modeling programs OMOP data Caveat Modeling objective Methods Major tasks of data preparation of OMOP data for modeling Data access The modeling tool Data integration Target variable definition Data type changes Data quality assessment and resolution Data exclusions Aggregation to the patient level Unique code determination Text mining frequency analysis Manual variable derivation Derivation of one-hot (binary) variables Feature selection process The "short-list" Methods of feature selection Variable filtering Wrapper methods Data conditioning Balancing the data set Unrepresentative negatives Positive unlabeled learning Modeling Modeling algorithms Cross-validation Ensemble modeling Results and discussion Model evaluation Prediction accuracies Receiver operator characteristic curve Other important aspects of the trained model Important predictor variables Emergent properties Automation of data preparation for medical informatics? 339 340 340 340 341 341 342 342 342 342 342 342 343 343 344 345 345 345 345 345 346 346 347 347 347 348 348 348 348 348 348 349 349 349 349 350 350 350 351 351 351 351 351 353 Conclusions How this chapter facilitates patient-centric medical health care Postscript References Further reading xiii 353 353 354 354 354 15. Prediction of pancreatic and lung cancer from metabolomics data 355
Robert A. Nisbet Prelude Purpose of this chapter Introduction Cancer deaths in the United States Cancer metabolites Methods The modeling process Results Model accuracy Specific models for lung cancer and pancreatic cancer Discussion Implications of this case study for future medical diagnosis Conclusions How this chapter facilitates patient-centric healthcare Postscript References 16. Covid-19 descriptive analytics visualization of pandemic and hospitalization data 355 355 356 356 356 356 356 358 358 359 359 360 360 360 360 360 361 Robert (Bob) Nisbet Preamble Introduction 3 KNIME workflow data streams Preparatory steps for using this tutorial General introduction to KNIME Data access—the file reader node Data understanding Country selection Visualization data stream Using the workflow for another country How this chapter facilitates patient-centric healthcare Postscript Further reading 361 361 361 362 364 365 365 365 368 372 373 373 373
xiv Contents 17. Disseminated intravascular coagulation predictive analytics with pediatric ICU admissions 375 Linda A. Miner, Harsha Chandnani, Mitchell Goldstein, Mahmood H. Khichi and Cynthia H. Tinsley Prelude 375 Introduction 375 Background (from first edition) 376 The example 377 Data files 377 First week of analysis 378 Data mining recipes using statistica 379 Data imputation 380 Using the 11,459 imputed file—training data 381 Training data (11,569 imputed) continued 384 A problem 385 Randomly separating the data and new data mining recipe 385 Final analysis—a return to the past 387 Conclusion—personal ending thoughts 388 Postscript 388 References 388 Prologue to Part IV Part IV Advanced topics in administration and delivery of health care including practical predictive analytics for medicine in the future 18. Challenges for healthcare administration and delivery: integrating predictive and prescriptive modeling into personalized-precision healthcare 19. Challenges of medical research in incorporating modern data analytics in studies 401 Nephi Walton, Gary D. Miner and Linda A. Miner Prelude Introduction—challenges to medical researchers Trends that we might want toknow about Automation and machinelearning (AutoML) Blockchain Conversational artificial intelligence Digital twins Medical competitions Conclusion Postscript References Further reading 401 401 402 403 403 403 403 403 403 404 404 404 20. The nature of insight from data and implications for automated decisioning: predictive and prescriptive models, decisions, and actions 405 Thomas Hill 395 Nephi Walton,
Gary D. Miner and Mitchell Goldstein Prelude Introduction to challenges in healthcare delivery Challenge #1 Challenge #2 Challenge #3 Challenge #4 Challenge #5 397 397 397 398 398 398 398 398 399 Challenge #6 Challenge #7 Challenge #8 Challenge #9 Challenge #10 Challenge # 11 Postscript References Further reading 395 395 395 396 396 396 396 Prelude Overview The purpose of this chapter The nature of insight and expertise Procedural and declarative knowledge 405 406 406 406 406 Nonconscious acquisition of knowledge Conclusion: expertise and the application of pattern recognition methods Statistical analysis versus pattern recognition Fitting a priori models Pattern recognition: data are the model The data are the model 407 Pattern recognition in artificial intelligence/ machine learning: general approximators 407 408 408 408 408 410
Contents Pattern recognition and declarative knowledge: interpretability of results 410 Explainability of artificial intelligence/machine learning models 410 Global and local explainability 410 Statistical models, and reason scores for linear models 411 What-if, and reason scores asderivatives 412 Explainability of nonlinear models, artificial intelligence/machine learning models 412 Local interpretable model-agnostic explanations 412 Shapley additive exPlanations 412 Comparing local interpretable model-agnostic explanations and Shapley additive explanations 413 Caution: inverse predictions can bevery risky 413 Inverse prediction 413 Correlation is not necessarily causation 413 Lack of evidence at the specific point in the input space 414 Optimization of inputs to achieve a desired output 414 Naive explanations 415 Summary 415 Postscript 415 References 415 21. Model management and ModelOps: managing an artificial intelligence-driven enterprise 417 Thomas Hi!! Prelude 417 Introduction 417 The model building/authoring life cycle 418 Overview: managing the life cycles for thousands of models 419 Types of analytic models 419 Managing the risks of analytics, artificial intelligence 420 Do-no-harm 421 ModelOps scope 421 ModelOps details: managing model pipelines and reusable steps 422 The tools and languages of artificial intelligence/machine learning 422 Reusable steps, building intellectual property 423 Managing model life cycles 424 Model monitoring 425 Monitoring risks 427 Efficiency, agility, elasticity, and technology 427 Cloud architecture Managing models for data-at-rest
and data-in-motion Conclusion Postscript References Further reading XV 427 428 430 430 430 431 22. The forecasts for advances in predictive and prescriptive analytics and related technologies for the year 2022 and beyond 433 Cary D. Miner, Linda A. Miner and Scott Burk Prelude Section I: specific technological trends predicted for 2022-2023+ What is predictive analytics, and what are the most frequently used methods (or algorithms) in predictive analytics? What is prescriptive analytics, and what is an example of prescriptive analytics? Part I—healthcare: what trends can we expect in the year 2022 and beyond? What do these three things mean? Part 2—In general: PA and business intelligence trends for 2022 TOP 10 analytics and business intelligence trends for 2022 Key artificial intelligence and data analytics trends for 2022 andbeyond Section II: overriding philosophies which will guide trendsover thenext 10 years Postscript References 433 433 433 434 434 435 436 437 437 439 440 440 23. Sampling and data analysis: variability in data may be a better predictor than exact data points with many kinds of Medical situations 443 Mitchell Goldstein and Gary D. Miner Prelude Sampling and data analysis issues Purpose summary of this chapter One issue—electronic health record and specific measures taken on patients Pulse oximetry data measurements, as an example Introduction Objective 443 443 443 444 445 445 445
xvi Contents Methods 445 Results 445 Discussion 449 Conclusion on Pulse Oximetry Example 450 Eye-intraocular pressure measurements: a personal example by one of the authors to illustrate the problem of when and how data is collected 450 Example of comparison of Goldman with i-CARE HOME intraocular pressure readings 451 In conclusion 451 Types of data analysis that may be helpful in solving the types of issues presented in this chapter 452 Reliability of inputs determines the validity of models 453 However, it gets more complicated 453 Butthen, it gets even more complicated 453 Clinical Dx and treatment needed changes for true patient-centered care 454 Postscript 454 References 455 Further reading 456 24. Analytics architectures for the 21st century 457 Scott Burk Prelude Introduction Purpose/summary Organizational design for success Some say it starts with data,it doesn't Organizational alignment Framework for trustworthy and ethical Al and analytics Data design for success Why is data so important? The potential of data is insight and action Data and analytics literacy are requirements to successful programs Brief considerations in data architecture Processes, systems, and data Data volume Data variety Data velocity Data value Data veracity Connecting and moving data—data in motion Application programming interfaces and management Microservices 457 457 457 458 458 458 459 459 459 459 460 460 461 461 461 462 462 462 462 462 463 Streaming data Data stores and limitations of the enterprise data warehouses Analytics design for success Technology to create analytics Technology
to communicate and act upon analytics Conclusion Postscript References 463 463 468 468 471 471 472 472 25. Predictive models versus prescriptive models; causal inference and Bayesian networks 473 Scott Burk Prelude Introduction Classification of Al and ML models in medicine Descriptive analytics Diagnostics analytics Predictive analytics Prescriptive analytics Process optimization Causation—the most misunderstood concept in data science today Some basic assumptions for predictive modeling Some basic assumptions for prescriptive modeling Using a predictive model for prescription purposes Some important notes on observational studies Causal inference and why it is important Bridging the causal models to statistical models—causal inference Bayesian networks Causal inference and the do-calculus A summary example of causal modeling Conclusion Postscript References Further reading 473 473 474 474 475 475 475 475 476 477 477 478 479 479 480 480 481 482 484 485 485 485 26. The future: 21st century healthcare and wellness in the digital age 487 Cary D. Miner and Linda A Miner Prelude Overview 487 488
Contents Background and need for change Comparative effectiveness research and heterogeneous treatment effect research New technology and 21 st century healthcare: health startup firms We wrote this back in 2014 for the first edition of this book Well did this all happen as predicted? Not quite Listing of other e-items in this "outside of healthcare facilities" category but within at least the partial control of patients Examples of wearable devices that are working for people today Atrial fibrillation wearable watch sensors Eye pressure (1OP) home measurement devices Nonautomatic vital health signal measuring devices Blood pressure devices Oxygen level home monitors Trends and expectations for the future of health IT and analytics 488 489 490 490 491 493 493 493 494 495 495 495 495 Bottom-Up "small-sized" but working individually controlled data gathering and instant analytics output systems Where will the next innovations in medicine come from? N-of-1 studies—the future for person-centered healthcare Styles of thinking—how brain laterality affects innovation in healthcare Final concluding statements 505 How much should we listen to algorithms?— Should machines make the decisions? Genomics and Al will start exploding in 2 02 2 and subsequent years, and thus we need to be prepared Patient-centered (precision) health for the future Postscript References Further reading Appendix A: Modeling new COVID-19 deaths Index xvii 501 502 502 503 505 505 505 505 506 508 511 519
Practical Data Analytics for Innovation in Medicine Building Real Predictive and Prescriptive Models in Personalized Healthcare and Medical Research Using Al, ML, and Related Technologies Second Edition Gary D. Miner, PhD, CEO, Μ Μ Predictive Analytics LLC, Tulsa, OK; Associate Editor, The Journal of Geriatric Psychiatry and Neurology; Private Con sulting, Tulsa, OK Linda A. Miner, PhD, Professor Emeritus, Professional and Graduate Studies as Program Director, Southern Nazarene University; Editorial Board, The Journal of Geriatric Psychiatry and Neurology; Private Consulting, Tulsa, OK Scott Burk, PțiD, Data Scientist, Architect Thought Leader TIBCO; Professor, Data Mining and Predictive Analytics, New York University; Temple, TX Mitchell Goldstein, MD, MBA, CML, FAAP, Professor of Pediatrics, Division of Neonatology, Director Neonatal ECMO Program; Loma Linda School of Medicine, Loma Linda University Children's Hospital; Loma Linda, CA; Editor-in-Chief Neonatology Today, Loma Linda, CA Robert Nisbet, PhD, Researcher-Medical Informatics, H.H. Chao Comprehensive Digestive Disease Center, University of California Irvine Medical Center, Private Consulting, Santa Barbara, CA Nephi Walton, MD, MS, FACMG, FAMIA, Associate Medical Director, Intermountain Healthcare, Precision Genomics, Salt Lake City, UT Thomas Hill, PhD, Senior Director and Product Manager, Advanced Analytics,TIBCO,Tulsa, OK Practical Data Analytics for Innovation in Medicine: Building Real Predictive Prescriptive Models in Personalized Healthcare and Medical Research Using Al, ML, and Related Technologies
Second Edition discusses the needs of healthcare and medicine in the 21 st century and ex plains how data analytics play an important and revolutionary role on fulfilling them. With healthcare effectiveness and economics facing growing challenges, there is a rapidly emerging movement to fortify medical treatment and administration by tapping the predictive power of big data, and it has shown solid results: predictive analytics bolster patient care, reduce cost, and deliver greater efficiencies across a wide range of operational functions. The first ¿Dart of the book brings a historical perspective and the issues of concern for healthcare delivery currently, highlighting the importance of using predictive analytics to help solve health crisis such as the COVID-19 pandemic. The second part provides access to practical step-by-step tu torials and case studies online, available in the book's companion website, to help reader to apply the knowledge gained through exercises based on real-world examples of successful predictive and prescriptive tools and systems. The central part of the book also contains seven case studies emphasizing precision medicine. The final part focuses on specific technical operations related to quality, cost-effective medical and nursing care delivery and administration brought by practical predictive analytics; in addition, it discusses future developments on decisioning platforms that allow rapid/instant decisions on medical care and delivery. The book is a valuable resource for researchers, practitioners, healthcare industry workers, policy makers,
and members of medical and biomedical fields who are interested to learn about recent developments on data analytics applied to healthcare and medicine. Key Features • Brings a historical perspective in medical care to discuss both the current status of health care delivery worldwide and the importance of using modern predictive analytics to help solve the health care crisis. Provides online tutorials on several predictive analytics systems to help readers to apply their knowledge on today's medical issues and basic research. Teaches how to develop effective predictive analytical research and to create decisioning/prescriptive analytics systems to make medical decisions quicker and more accurate. |
| any_adam_object | 1 |
| any_adam_object_boolean | 1 |
| author | Miner, Gary 1942- |
| author_GND | (DE-588)140491813 |
| author_facet | Miner, Gary 1942- |
| author_role | aut |
| author_sort | Miner, Gary 1942- |
| author_variant | g m gm |
| building | Verbundindex |
| bvnumber | BV048903255 |
| classification_rvk | XC 4001 |
| ctrlnum | (OCoLC)1390809335 (DE-599)BVBBV048903255 |
| discipline | Medizin |
| discipline_str_mv | Medizin |
| edition | Second edition |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02362nam a2200457 c 4500</leader><controlfield tag="001">BV048903255</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20230801 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">230418s2023 a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9780323952743</subfield><subfield code="9">978-0-323-95274-3</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1390809335</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV048903255</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-384</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">XC 4001</subfield><subfield code="0">(DE-625)152514:12907</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Miner, Gary</subfield><subfield code="d">1942-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)140491813</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Practical data analytics for innovation in medicine</subfield><subfield code="b">building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies</subfield><subfield code="c">Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">Second edition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Oxford</subfield><subfield code="b">Elsevier</subfield><subfield code="c">2023</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xli, 533 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Datenanalyse</subfield><subfield code="0">(DE-588)4123037-1</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Medizinische Informatik</subfield><subfield code="0">(DE-588)4038261-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Modellierung</subfield><subfield code="0">(DE-588)4170297-9</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4143413-4</subfield><subfield code="a">Aufsatzsammlung</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Medizinische Informatik</subfield><subfield code="0">(DE-588)4038261-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Datenanalyse</subfield><subfield code="0">(DE-588)4123037-1</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">Modellierung</subfield><subfield code="0">(DE-588)4170297-9</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="689" ind1="1" ind2="0"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="1"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Augsburg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Augsburg - ADAM Catalogue Enrichment</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Klappentext</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-034167614</subfield></datafield></record></collection> |
| genre | (DE-588)4143413-4 Aufsatzsammlung gnd-content |
| genre_facet | Aufsatzsammlung |
| id | DE-604.BV048903255 |
| illustrated | Illustrated |
| index_date | 2024-07-03T21:51:30Z |
| indexdate | 2024-07-10T09:49:22Z |
| institution | BVB |
| isbn | 9780323952743 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-034167614 |
| oclc_num | 1390809335 |
| open_access_boolean | |
| owner | DE-384 |
| owner_facet | DE-384 |
| physical | xli, 533 Seiten Illustrationen, Diagramme |
| publishDate | 2023 |
| publishDateSearch | 2023 |
| publishDateSort | 2023 |
| publisher | Elsevier |
| record_format | marc |
| spelling | Miner, Gary 1942- Verfasser (DE-588)140491813 aut Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill Second edition Oxford Elsevier 2023 xli, 533 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Künstliche Intelligenz (DE-588)4033447-8 gnd rswk-swf Datenanalyse (DE-588)4123037-1 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Medizinische Informatik (DE-588)4038261-8 gnd rswk-swf Modellierung (DE-588)4170297-9 gnd rswk-swf (DE-588)4143413-4 Aufsatzsammlung gnd-content Medizinische Informatik (DE-588)4038261-8 s Datenanalyse (DE-588)4123037-1 s Modellierung (DE-588)4170297-9 s DE-604 Künstliche Intelligenz (DE-588)4033447-8 s Maschinelles Lernen (DE-588)4193754-5 s Digitalisierung UB Augsburg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis Digitalisierung UB Augsburg - ADAM Catalogue Enrichment application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA Klappentext |
| spellingShingle | Miner, Gary 1942- Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies Künstliche Intelligenz (DE-588)4033447-8 gnd Datenanalyse (DE-588)4123037-1 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Medizinische Informatik (DE-588)4038261-8 gnd Modellierung (DE-588)4170297-9 gnd |
| subject_GND | (DE-588)4033447-8 (DE-588)4123037-1 (DE-588)4193754-5 (DE-588)4038261-8 (DE-588)4170297-9 (DE-588)4143413-4 |
| title | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |
| title_auth | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |
| title_exact_search | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |
| title_exact_search_txtP | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |
| title_full | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill |
| title_fullStr | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill |
| title_full_unstemmed | Practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies Gary D. Miner, Linda A. Miner, Scott Burk, Mitchell Goldstein, Robert Nisbet, Nephi Walton, Thomas Hill |
| title_short | Practical data analytics for innovation in medicine |
| title_sort | practical data analytics for innovation in medicine building real predictive and prescriptive models in personalized healthcare and medical research using ai ml and related technologies |
| title_sub | building real predictive and prescriptive models in personalized healthcare and medical research using AI, ML, and related technologies |
| topic | Künstliche Intelligenz (DE-588)4033447-8 gnd Datenanalyse (DE-588)4123037-1 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Medizinische Informatik (DE-588)4038261-8 gnd Modellierung (DE-588)4170297-9 gnd |
| topic_facet | Künstliche Intelligenz Datenanalyse Maschinelles Lernen Medizinische Informatik Modellierung Aufsatzsammlung |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=034167614&sequence=000003&line_number=0002&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT minergary practicaldataanalyticsforinnovationinmedicinebuildingrealpredictiveandprescriptivemodelsinpersonalizedhealthcareandmedicalresearchusingaimlandrelatedtechnologies |