Healthcare Solutions Using Machine Learning and Informatics

Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgments
Chapter 1: Introduction to Artificial Intelligence in Healthcare
1.1 Introduction
1.1.1 Major Activities in Medical Image Analysis
1.1.2 The Role of ML in Medical Image Analysis
1.2 Medical Imaging Types
1.2.1 Pre-Processing Using ML
1.2.1.1 Introduction to Pre-processing
1.2.2 Segmentation Using ML
1.2.2.1 Introduction to Segmentation
1.2.3 Registration Using ML
1.2.3.1 Introduction
1.3 Deep Learning in Medical Imaging
1.4 Conclusion
References
Chapter 2: Machine Learning in Radio Imaging
2.1 Introduction
2.2 Analysis of Related Work
2.3 Summary
References
Chapter 3: Solutions Using Machine Learning for Diabetes
3.1 Introduction
3.2 Diabetes Prevalence
3.3 Diabetes Risk Factors
3.4 Machine Learning
3.4.1 Artificial Neural Networks
3.4.2 Support Vector Machine
3.4.3 Fuzzy Logic
3.4.4 Logistic Regression
3.5 A Case Study
3.6 Results and Discussion
3.6.1 Multicollinearity Test Results/ Variables
3.6.2 Multilinear Regression Test Results / Coefficients
3.7 Conclusions
References
Chapter 4: A Highly Reliable Machine Learning Algorithm for Cardiovascular Disease Prediction
4.1 Introduction
4.2 Literature Review
4.3 Methodology
4.3.1 Dataset
4.3.2 Implementing the Classifiers
4.3.2.1 XGBOOST
4.3.2.1.1 XGBoost Result Analysis
4.3.2.2 Random Forest
4.3.2.2.1 Random Forest Result Analysis
4.3.2.3 Naïve Bayes
4.3.2.3.1 Naïve Bayes Result Analysis
4.3.2.4 Majority Voting Ensemble (MVE)
4.3.2.4.1 Majority Voting Ensemble Result Analysis
4.4 Conclusion
References
Chapter 5: Machine Learning Algorithms for Industry Using Image Sensing
5.1 Introduction
5.2 What is Manufacturing Artificial Intelligence?
5.3 Defining the Industrial Internet of Things
5.4 IoT History
5.5 IIoT Architectures
5.6 Applications of IIoT
5.6.1 Smart Manufacturing
5.7 Securing the Internet of Things
5.7.1 Safety
5.7.2 Security
5.7.3 Privacy
5.8 Challenges and Opportunities
5.9 Future of IIoT
5.10 Communication 5G and Beyond
5.11 How Did AI Develop in Production?
5.11.1 AI in Manufacturing Current State
5.11.2 What is AI’s Future in Production?
5.12 Process and Factory Floors that are Flexible and Configurable
5.13 Manufacturing and AI: Applications and Benefits
5.14 Impact of COVID-19 on Industrial Internet of Things
5.15 Conclusion
References
Chapter 6: Solutions Using Machine Learning for COVID-19
6.1 Introduction
6.2 Application of ML and AI Methods to COVID-19
6.2.1 Screening and Diagnosis
6.2.1.1 Using the Patient’s Symptoms and Routine Tests
6.2.1.2 Using Chest X-rays and CT Images
6.2.2 Population Monitoring
6.2.2.1 Monitoring Patients
6.2.2.2 Contact Tracing
6.2.2.3 Avoiding Physical Contact
6.2.3 Models for Prediction and Forecasting of the Disease
6.2.3.1 An Example Model Predicting the Spread of COVID-19
6.2.4 Models of Vaccinations
6.2.4.1 An Example Model of Global Vaccination Drive
6.3 Conclusion
References
Chapter 7: Big Data Analytics in Healthcare Data Processing
7.1 Introduction
7.2 Big Data
7.2.1 Big Data Analytics in Healthcare
7.2.1.1 Big Data Characteristics in Healthcare: The 5 Vs
7.2.1.2 Demand for Big Data Analytics in Healthcare
7.2.1.3 Big Data Analytics Platforms and Tools in Healthcare
7.3 Big Data Analytics and Artificial Intelligence
7.3.1 Artificial Intelligence and its Uses in Healthcare
7.4 Big Data Analytics and Deep Learning
7.4.1 Convolutional Neural Networks (CNN)
7.4.2 Recurrent Neural Networks (RNN)
7.4.3 Long Short-Term Memory (LSTM)
7.5 Different Machine Learning Techniques Used in Healthcare
7.6 Advantages of Big Data in Healthcare
7.7 Application of Big Data Analytics in Healthcare
7.7.1 Healthcare Monitoring
7.7.2 Healthcare Risk Prediction
7.7.3 Behavioral Monitoring
7.7.4 Treatment of Cancer and Genomics
7.7.5 Detect and Prevent Fraud
7.7.6 Hospital Network
7.7.7 Clinical Decision Support System
7.7.8 Clinical Trials and Drug Development
7.7.9 Telediagnosis and Image Informatics
7.7.10 Healthcare Knowledge System
7.8 Challenges and Recommendations
7.8.1 Obtaining and Cleaning Huge Amounts of Health Data from Different Sources
7.8.2 Maintaining the Storage and Quality of Large Amounts of Health Data
7.8.3 Big Health Data Can Be Scaled Up or Down Depending on Need
7.8.4 Using Big Health Data to Make Faster and Better Decisions
7.9 Future Direction in Healthcare for Big Data
7.9.1 Issues in the Collection of Health Data
7.9.2 Data Governance
7.9.3 The Importance of Recent Technologies
7.9.4 Investigating the Success of Big Data Analytics
7.10 Conclusion
References
Chapter 8: Reliable Biomedical Applications Using AI Models
8.1 Introduction
8.2 Artificial Intelligence
8.2.1 The Benefits of Artificial Intelligence in the Biomedical Field
8.2.2 Machine Learning
8.2.2.1 Supervised Learning
8.2.2.2 Unsupervised Learning
8.2.2.3 Semi-Supervised Learning
8.2.2.4 Reinforcement Learning
8.2.3 Popular Machine Learning Techniques
8.2.3.1 K-Nearest Neighbor (KNN)
8.2.3.2 Naı̈ve Bayes
8.2.3.3 Support Vector Machines
8.2.3.4 Decision Tree Ensembles
8.2.3.5 Logistic Regression
8.2.4 Deep Learning
8.2.4.1 Convolutional Neural Networks
8.2.4.2 Recurrent Neural Networks
8.3 Applications
8.3.1 Omics
8.3.1.1 AI for Genomics
8.3.1.1.1 Genomic Sequencing
8.3.1.1.2 DNA Sequencing
8.3.1.1.3 DNA Methylation
8.3.1.2 AI For Protein Analysis
8.3.1.2.1 Protein Structure Prediction (PSP)
8.3.1.2.2 Protein Interaction Prediction (PIP)
8.3.2 AI in Drug Discovery
8.3.3 AI for Bio and Medical Imaging
8.3.4 AI in Radiology
8.3.5 AI for surgery optimization
8.3.6 Brain and Body Interface
8.4 Discussion and Challenges
8.5 Future Directions in Healthcare Using AI
8.5.1 Integrative Analysis
8.5.2 Federated Learning
8.5.3 Model Transparency
8.5.4 Model Security
8.5.5 Data Bias
8.6 Conclusion
References
Chapter 9: Plant Disease Detection Using Imaging Sensors, Deep Learning and Machine Learning for Smart Farming
9.1 Introduction
9.2 Imaging Sensors for Plant Disease Detection
9.3 Machine Learning in Plant Disease Detection
9.3.1 Deep Learning in Plant Disease Detection
9.3.2 RGB Imaging
9.3.3 Multispectral Sensors
9.3.4 Infrared Thermography (IRT)
9.3.5 Hyperspectral Sensors
9.4 Sensor Mechanisms
9.5 Statistical Analysis for Monitoring Plant Diseases
9.6 A General Framework for Monitoring Plant Diseases
9.7 Application of Sensors to Detection of Plant Diseases
9.8 Conclusion
References
Chapter 10: IoT Application for Healthcare
10.1 Introduction
10.2 IoT-Based Solutions for Healthcare
10.2.1 Chest disease
10.2.2 Retinal Imaging
10.2.3 Heart Disease Monitoring System
10.2.4 Intelligent Ambulance and Traffic Clearance Based on Internet of Things
10.2.5 IoT and Mental Health Support
10.3 Smart Hospital Based on Internet of Things
10.4 Related Work
10.5 IoT Key Components
10.6 Data Monitoring by IOT
10.7 System Design
10.8 IoT in the COVID-19 Pandemic
10.8.1 IoT Applications during COVID-19
10.8.2 Contact-Tracing Mechanisms
10.8.2.1 Trace Together
10.8.2.2 Decentralized Privacy-Preserving Proximity Tracing (DP3T)
10.8.2.3 Efficient Privacy-Preserving Contact Tracing (EPIC)
10.8.2.4 Contact Categorization
10.8.2.5 Privacy-Sensitive Protocols and Mechanisms for Mobile Contact Tracing (PACT)
10.8.3 Internet of Things for COVID-19 Diagnosis
10.8.4 Internet of Things for Telemedicine Services during Coronavirus Disease
10.8.5 IoT-Enabled Wearable Technologies for Predicting Coronavirus Disease
References
Chapter 11: Machine Learning Techniques for Prediction of Diabetes
11.1 Introduction
11.2 Review of Work
11.3 Methodology
11.3.1 Dataset
11.3.2 Predictive Indicators
11.3.2.1 Confusion Matrix
11.3.2.2 ROC curve
11.3.2.3 True positive rate (TPR)
11.3.2.4 False positive rate (FPR)
11.3.2.5 Accuracy
11.3.2.6 Precision
11.3.2.7 Sensitivity (recall)
11.3.2.8 F1 Score
11.3.2.9 Specificity (true negative rate)
11.3.2.10 False positive rate (FPR)
11.3.2.11 False negative rate (FNR)
11.3.2.12 False discovery rate (FDR)
11.3.2.13 Negative predictive value (NPV)
11.3.2.14 Matthews correlation coefficient (MCC)
11.3.3 Method of analysis
11.3.3.1 Number of Pregnancies
11.3.3.2 Glucose level
11.3.3.3 Blood pressure
11.3.3.4 Skin thickness
11.3.3.5 Insulin
11.3.3.6 Body mass index (BMI)
11.3.3.7 Diabetes pedigree function
11.3.3.8 Age
11.4 Machine Learning Algorithms
11.4.1 Random forest algorithm
11.4.2 XGBoost algorithm
11.4.3 Support vector machine (SVM)
11.4.4 Artificial neural network (ANN)
11.5 Result and Analysis
11.6 Conclusion
References
Chapter 12: Use of Machine Learning in Healthcare
12.1 Introduction
12.2 Literature Survey
12.2.1 Learning Insulin–Glucose Dynamics in the Wild
12.2.2 MRI-Based Diagnosis of Rotator Cuff Tears Using Deep Learning and Weighted Linear Combinations
12.2.3 Transferring Learning from Well Curated to Less Resourced Populations with HIV
12.2.4 Early Diagnosis of Epilepsy from EEG Data
12.2.5 Evaluation of Doctor Interpretability of Generalized Additive Models with Interactions
12.3 Conclusion
References
Index