12 8 An Access Authorization Mechanism for Electronic Health Records of Blockchain to Sheathe Fragile Information 8.1 Introduction 8.2 Related Work 8.3 Need for Blockchain in Healthcare 8.4 Proposed Frameworks 8.5 Use Cases 8.6 Discussions 8.7 Challenges and Limitations 8.8 Future Work 8.9 Conclusion References
13 9 An Epidemic Graph’s Modeling Application to the COVID-19 Outbreak 9.1 Introduction 9.2 Related Work 9.3 Theoretical Approaches 9.4 Frameworks 9.5 Evaluation of COVID-19 Outbreak 9.6 Conclusions and Future Works References
14 10 Big Data and Data Mining in e-Health: Legal Issues and Challenges 10.1 Introduction 10.2 Big Data and Data Mining in e-Health 10.3 Big Data and e-Health in India 10.4 Legal Issues Arising Out of Big Data and Data Mining in e-Health 10.5 Big Data and Issues of Privacy in e-Health 10.6 Conclusion and Suggestions References
15 11 Basic Scientific and Clinical Applications 11.1 Introduction 11.2 Case Study-1: Continual Learning Using ML for Clinical Applications 11.3 Case Study-2 11.4 Case Study-3: ML Will Improve the RadiologyPatient Experience 11.5 Case Study-4: Medical Imaging AI with Transition from Academic Research to Commercialization 11.6 Case Study-5: ML will Benefit All Medical Imaging ‘ologies’ 11.7 Case Study-6: Health Providers will Leverage Data Hubs to Unlock the Value of Their Data 11.8 Conclusion References
16 12 Healthcare Branding Through Service Quality 12.1 Introduction to Healthcare 12.2 Quality in Healthcare 12.3 Service Quality 12.4 Conclusion and Road Ahead References
17 Index
List of Illustrations
1 Chapter 1Figure 1.1 Big data in healthcare.Figure 1.2 Five vs of big data.Figure 1.3 Areas of big data analytics in medicine.
2 Chapter 2Figure 2.1 Overall of missing values.Figure 2.2 Boruta features importance result.Figure 2.3 Top twenty features ranked by random forest.Figure 2.4 Class distribution before applying sampling techniques.Figure 2.5 C5.0 rule-based decision tree.
3 Chapter 3Figure 3.1 Human brain and neurons.Figure 3.2 Brain atrophy variations of T1 (longitudinal relaxation time), (a) at...Figure 3.3 Extracting volume of brain by image processing.Figure 3.4 Structural MRI images representing different AD stages. (a) Mild deme...Figure 3.5 Age vs demented and non-demented.Figure 3.6 MMSE.Figure 3.7 nWBV.Figure 3.8 eTIV.Figure 3.9 ASF.Figure 3.10 AGE.Figure 3.11 EDUC.Figure 3.12 Non demented, demented and converted demented MRI count.Figure 3.13 Polynomial regression of SES and EDUC.Figure 3.14 Features to be used.Figure 3.15 Ensemble learning.Figure 3.16 Random forest tree of early Alzheimer’s detection.Figure 3.17 Confusion matrix.Figure 3.18 Pre-processing Transverse. (a) Raw/original image. (b) Skull-strippi...Figure 3.19 Smoothing of a Raw MR Imaging.Figure 3.20 Alzheimer’s 4-class images information.Figure 3.21 Classification objective.Figure 3.22 Fully connected CNN.Figure 3.23 Flowchart of proposed model.Figure 3.24 8-layered AlexNet architecture.Figure 3.25 VGG16 architecture with 16 layers.Figure 3.26 Inception module.Figure 3.27 GoogLeNet.Figure 3.28 ResNet architecture with skip connections running parallel.Figure 3.29 MobileNetV2 architectural representation.Figure 3.30 Neural Architecture Search (NASNet).Figure 3.31 ROC curve and predictions.Figure 3.32 Machine Learning Algorithms Comparison.Figure 3.33 Predicting the Alzheimer’s progression: (a) Nondemented (99.13%), (b...Figure 3.34 Validation status.Figure 3.35 Confusion matrix.Figure 3.36 Metric measures of MobileNetV2 during training and validation.
4 Chapter 4Figure 4.1 Image segmentation techniques.Figure 4.2 Process for identifying and detecting retinal diseases.Figure 4.3 Extraction of gray-scaled green channel