Big Data in Healthcare: Extracting Knowledge from Point-of-Care Machines (SpringerBriefs in Pharmaceutical Science & Drug Development)

"This book reviews a number of issues including: Why data generated from POC machines are considered as Big Data. What are the challenges in storing, managing, extracting knowledge from data from POC devices? Why is it inefficient to use traditional data analysis with big data? What are the solutions for the mentioned issues and challenges? What type of analytics skills are required in health care? What big data technologies and tools can be used efficiently with data generated from POC devices? This book shows how it is feasible to store vast numbers of anonymous data and ask highly specific questions that can be performed in real-time to give precise and meaningful evidence to guide public health policy."-- Read more... Abstract: "This book reviews a number of issues including: Why data generated from POC machines are considered as Big Data. What are the challenges in storing, managing, extracting knowledge from data from POC devices? Why is it inefficient to use traditional data analysis with big data? What are the solutions for the mentioned issues and challenges? What type of analytics skills are required in health care? What big data technologies and tools can be used efficiently with data generated from POC devices? This book shows how it is feasible to store vast numbers of anonymous data and ask highly specific questions that can be performed in real-time to give precise and meaningful evidence to guide public health policy." Contents 6 About the Editors 7 1 Introduction—Improving Healthcare with Big Data 8 1.1 Introduction 8 1.2 Big Data and Health 9 1.3 Big Data and Health in Low- and Middle-Income Countries 12 1.3.1 Analytical Challenges 15 1.3.2 Ethical Challenges 16 1.3.2.1 Informed Consent 16 1.3.2.2 Privacy 17 1.3.2.3 Ownership 18 1.3.2.4 Epistemology and Objectivity 18 1.3.2.5 Big Data ‘Divides’ 19 1.4 Conclusion and Structure of the Book 19 References 20 2 Data Science and Analytics 21 2.1 What Is Data Science? 21 2.2 Methods in Data Science 22 2.2.1 Supervised and Unsupervised Learning 23 2.2.2 Data Science Analytical Tasks 24 2.3 Data Science, Analytics, Statistics, Business Intelligence and Data Mining 27 2.3.1 Data Science and Analytics 27 2.3.2 Statistics, Statistical Learning and Data Science 27 2.3.3 Data Science and Business Intelligence 28 2.4 Data Science Process 28 2.4.1 CRISP-DM 29 2.4.2 Domain Knowledge and Business Understanding 31 2.4.3 Data Understanding and Preparation 31 2.4.4 Building Models and Evaluation Metrics 32 2.4.5 Model Deployment 39 2.5 Data Science Tools 40 2.6 Summary 41 References 42 3 Big Data and Big Data Technologies 44 3.1 What Is Big Data? 44 3.2 Data Dimension of Big Data 46 3.2.1 Volume 47 3.2.2 Velocity 47 3.2.3 Variety 48 3.2.4 Other Vs of Big Datasets 48 3.3 Structured, Unstructured and Semi-structured Data 48 3.3.1 Internet of Things and Machine-Generated Data 50 3.3.2 Highly Connected Data 51 3.4 Big Data Technologies 52 3.4.1 Building Blocks of Hadoop: HDFS and MapReduce 53 3.4.2 Distributed Processing with MapReduce 54 3.4.3 HDFS and MapReduce 54 3.4.4 Hadoop Ecosystem: First Generation 57 3.4.5 Hadoop Ecosystem Second Generation 58 3.5 Splunk: A Commercial Big Data Technology 59 3.6 Big Data Pipeline: Lambda and Kappa Architectures 59 3.6.1 Lambda Architecture 60 3.6.2 Kappa Architecture 61 3.7 Big Data Tools and Technologies 62 References 63 4 Big Data Analytics for Extracting Disease Surveillance Information: An Untapped Opportunity 64 4.1 Introduction 64 4.2 The Importance of POC 66 4.3 Technical Requirements of POC 66 4.4 Data Generated by POC and Accessibility Issue 69 4.5 Proposed Solution 70 4.5.1 Common Data Structure of the Proposed Solution 71 4.5.2 Data Analytics in the Proposed Solution 71 4.6 Big Data Architecture of the Proposed Solution 73 4.7 Benefits of the Implemented System 76 4.8 The Implemented Data Analytics and Dashboards 77 4.9 Conclusions and Future Work 85 References 86 5 #Ebola and Twitter. What Insights Can Global Health Draw from Social Media? 89 5.1 Introduction 89 5.2 Ebola Virus Disease and Media Coverage 90 5.3 How Can We Study Social Media Data? 91 5.4 Insights from the Ebola Twitter Dataset 93 5.5 Conclusion 100 Acknowledgements 101 References 101 Index 103 Front Matter ....Pages i-vii Introduction—Improving Healthcare with Big Data (Francois van Loggerenberg, Tatiana Vorovchenko, Pouria Amirian)....Pages 1-13 Data Science and Analytics (Pouria Amirian, Francois van Loggerenberg, Trudie Lang)....Pages 15-37 Big Data and Big Data Technologies (Pouria Amirian, Francois van Loggerenberg, Trudie Lang)....Pages 39-58 Big Data Analytics for Extracting Disease Surveillance Information: An Untapped Opportunity (Pouria Amirian, Trudie Lang, Francois van Loggerenberg, Arthur Thomas, Rosanna Peeling)....Pages 59-83 #Ebola and Twitter. What Insights Can Global Health Draw from Social Media? (Tatiana Vorovchenko, Proochista Ariana, Francois van Loggerenberg, Pouria Amirian)....Pages 85-98 Back Matter ....Pages 99-100