Data Science for Effective Healthcare Systems (Chapman & Hall/CRC Internet of Things)

Data Science for Effective Healthcare Systems has a prime focus on the importance of data science in the healthcare domain. Various applications of data science in the health care domain have been studied to find possible solutions. In this period of COVID-19 pandemic data science and allied areas plays a vital role to deal with various aspect of health care. Image processing, detection & prevention from COVID-19 virus, drug discovery, early prediction, and prevention of diseases are some thrust areas where data science has proven to be indispensable. Key Features: The book offers comprehensive coverage of the most essential topics, including: Big Data Analytics, Applications & Challenges in Healthcare Descriptive, Predictive and Prescriptive Analytics in Healthcare Artificial Intelligence, Machine Learning, Deep Learning and IoT in Healthcare Data Science in Covid-19, Diabetes, Coronary Heart Diseases, Breast Cancer, Brain Tumor The aim of this book is also to provide the future scope of these technologies in the health care domain. Last but not the least, this book will surely benefit research scholar, persons associated with healthcare, faculty, research organizations, and students to get insights into these emerging technologies in the healthcare domain. Cover Half Title Series Page Title Page Copyright Page Table of Contents Preface Editor 1. Big Data in Healthcare: Applications and Challenges 1.1 Introduction 1.2 Types of Data in Healthcare 1.2.1 Business, Organizational, and External Data 1.2.2 Patient Sentiment and Behavior Data 1.2.3 Clinical Information and Notes 1.2.4 Web-and Social Networking–Based Data 1.2.5 Genomic Data 1.3 Big Data 5 V's in Healthcare 1.3.1 Volume 1.3.2 Velocity 1.3.3 Veracity 1.3.4 Variety 1.3.5 Value 1.4 Big Data Analysis in Healthcare Industry 1.4.1 Data Acquisition 1.4.2 Data Storage 1.4.3 Data Management 1.4.4 Data Analytics 1.4.5 Data Visualization 1.5 Big Data Analytics Tools in Healthcare 1.6 Applications of Big Data in Healthcare 1.6.1 Data Analytics in COVID-19 1.6.2 Hadoop-Based Applications 1.6.3 Big Data in Public Health and Behavior Research 1.6.4 Source of Valuable Data 1.6.5 Big Data in Medical Experiment 1.6.6 Medical Research Using Big Data 1.7 Challenges with Healthcare Data Management 1.7.1 Challenges Associated with Manpower 1.7.2 Challenges in Data and Process 1.7.3 Overall Organizational Challenges 1.8 Conclusion References 2. Impact Analysis of COVID-19 on Different Countries: A Big Data Approach 2.1 Introduction 2.2 Processing Steps of Big Data 2.2.1 Data Collection and Recording 2.2.2 Data Cleaning 2.2.3 Data Integration 2.2.4 Data Modeling 2.2.5 Data Interpretation 2.3 Challenges of Big Data Analysis 2.3.1 Heterogeneity and Incompleteness 2.3.2 Scalability 2.3.3 Timeliness 2.3.4 Analytics of Big Data 2.4 Current Scenario in Top Five Countries Affected by Pandemic 2.5 Process Adopted to Carry Out the Analysis 2.6 Major Factors that Can Majorly Affect the Result of Analysis 2.7 Conclusion References 3. Overview of Image Processing Technology in Healthcare Systems 3.1 Introduction 3.2 Computer-Based Technology 3.3 Image Recognition, Analysis, and Enhancements 3.4 Role of Machine Learning and DL in the Field of Medical Diagnosis 3.5 Development in Remote Healthcare with Mobile Phone and Telemedicine Systems 3.6 Applications in Health Research 3.7 Conclusion References 4. Artificial Intelligence to Fight against COVID-19 Coronavirus in Bharat 4.1 Introduction 4.2 Viral Gene Sequencing Based on AI 4.3 Diagnosis of New Coronary Pneumonia Based on Machine Vision 4.4 New Coronary Drug Screening Based on AI+ Big Data 4.5 Using Computer Vision to Detect Coronavirus Infection 4.6 AI in Other Areas 4.7 Conclusions References 5. Classification-Based Prediction Techniques Using ML: A Perspective for Health Care 5.1 Introduction 5.2 Related Work 5.3 Unlocking the Power of Classification and Prediction Techniques using ML in Health Care 5.3.1 Machine Learning 5.3.2 ML in Health Care 5.4 ML in Disease Prediction and Detection 5.4.1 ML in Diabetes Prediction 5.4.2 ML in Cancer Prediction 5.4.3 ML in Heart Disease Prediction 5.5 Applications of Classification in Health Care 5.6 Challenges and Opportunities for ML in Health Care 5.6.1 Challenges in Health Care System 5.6.2 Unlocking the Opportunities of ML in Health Care 5.7 Conclusion References 6. Deep Learning for Drug Discovery: Challenges and Opportunities 6.1 Introduction 6.2 Principles of DL 6.3 DL Methods for Drug Discovery 6.3.1 DNN 6.3.2 CNN 6.3.3 RNN 6.3.4 AEs 6.3.5 DBN 6.4 Opportunities and Challenges 6.4.1 Drug Safety 6.4.2 Integration of Biomedical Information with Computational Methodologies 6.4.3 Genetically Analysis of Data and Customized Medication 6.4.4 Building and Getting Knowledge from Databases 6.4.5 ML Methods for Genetics and Genomics 6.5 Applications of DL in Drug Discovery 6.5.1 Drug Properties Prediction 6.5.2 De Novo Drug Design 6.5.3 Drug–Target Interaction Prediction 6.6 Conclusion References 7. Issues and Challenges Associated with Machine Learning Tools for Health Care System 7.1 Introduction 7.2 Machine-Learning–Based Prediction Schemes for Healthcare Industry 7.3 Automated Decision Support System 7.4 Drug Discovery and Human Trials using Machine Learning 7.5 Surgical Operations with Machine Learning Assistance 7.6 Conclusion References 8. Real-Time Data Analysis of COVID-19 Vaccination Progress Over the World 8.1 Introduction 8.2 Literature Review 8.3 Methodology 8.3.1 Data Collection 8.3.2 Data Preprocessing 8.3.3 Feature Engineering 8.4 Data Analysis 8.4.1 World Data Analysis 8.4.2 Vaccines Used by Different Countries 8.4.3 Vaccination of World's Top 30 Countries 8.4.4 Top Ten Vaccinated Countries' Vaccination Information 8.4.5 Top Vaccinated Countries and Vaccines Used 8.4.6 Daily Vaccination in Bangladesh 8.5 Conclusions References 9. Descriptive, Predictive, and Prescriptive Analytics in Healthcare 9.1 Introduction 9.2 Descriptive Analytics 9.3 Predictive Analytics 9.4 Prescriptive Analytics 9.5 Analytics Techniques in Healthcare 9.5.1 Supervised Learning 9.5.1.1 Classification 9.5.1.2 Regression 9.5.2 Unsupervised Learning 9.5.2.1 Clustering 9.5.2.2 Dimension Reduction 9.6 Healthcare Analytics Life Cycle 9.7 Proposed Architecture for Healthcare Analytics 9.8 Conclusion References 10. IoT Enabled Worker Health, Safety Monitoring and Visual Data Analytics 10.1 Introduction 10.2 Connected Assets 10.2.1 Connected People 10.2.2 Connected Vehicles 10.3 Protection of the Environment and Conservation of Water 10.4 Mine Planning 10.5 Proposed Connected Mining Solution 10.5.1 Application and Visualization 10.5.2 Core Platform and Services 10.5.3 IoT Platform and Services 10.5.4 Communication Network and Protocols 10.5.5 Devices and Connectivity Characteristics 10.6 Development and Deployment 10.6.1 Application Dashboard 10.6.2 Intrusion Detection and Worker's Health Dashboard 10.7 Conclusion References 11. Prevalence of Nomophobia and Its Association with Text Neck Syndrome and Insomnia in Young Adults during COVID-19 11.1 Introduction 11.2 Aim of the Study 11.3 Hypotheses 11.4 Review of Literature: Nomophobia 11.5 Review of Literature: TNS 11.6 Review of Literature: Insomnia 11.7 Methodology 11.8 Result 11.8.1 Part I: Demographic Characteristics of Subjects 11.8.2 Part II: Hypothesis Testing 11.8.2.1 TNS v/s Nomophobia 11.8.2.2 AIS v/s Nomophobia 11.8.2.3 AIS v/s TNS 11.8.3 Part III: Odds Ratio and Relative Risk Ratio Analysis 11.8.3.1 AIS v/s Nomophobia 11.8.3.2 AIS v/s Nomophobia 11.8.3.3 AIS v/s TNS 11.9 Discussion 11.10 Conclusion 11.11 Future Scope References 12. The Role of AI, Fuzzy Logic System in Computational Biology and Bioinformatics 12.1 Introduction 12.1.1 Bioinformatics 12.1.2 Challenges in Bioinformatics 12.2 Computational Biology and Bioinformatics: A Comparison 12.3 Machine Learning Approach 12.4 Artificial Neural Network Approach 12.5 BLAST Algorithm 12.6 Advancement of Deep Learning Architectures in Bioinformatics 12.7 Fuzzy Logic in Bioinformatics 12.8 Bioinformatics in COVID-19 12.9 Fuzzy Rough Set Theory on Cancer Diagnosis 12.9.1 Dataset Description 12.9.2 Result and Analysis 12.10 Conclusion with Future Opportunity References 13. Analysis for Early Prediction of Diabetes in Healthcare Using Classification Techniques 13.1 Introduction 13.2 Literature Survey 13.3 Materials and Methods 13.3.1 Data Preprocessing 13.4 ML Techniques 13.4.1 SVM 13.4.2 KNN 13.4.3 Logistic Regression 13.4.4 Ensemble Method (Random Forest) 13.4.5 Gaussian Naive Bayes 13.5 Results and Discussion 13.6 Conclusion References 14. Nomenclature of Machine Learning Algorithms and Their Applications 14.1 Introduction 14.2 Related Work 14.3 A Brief Overview of the Five ML Algorithms 14.3.1 Support Vector Machine (SVM) 14.3.2 KNN 14.3.3 NB 14.3.4 DT 14.3.5 Logistic Regression 14.4 Proposed Methodology 14.4.1 Performance Evaluation Metrics 14.5 Results and Discussion 14.6 Conclusions References 15. Breast Cancer Prognosis Using Machine Learning Approaches 15.1 Introduction 15.1.1 Breast Cancer 15.2 Role of Machine Learning 15.2.1 ML Methods 15.2.2 ML Algorithms for Breast Cancer Prognosis 15.2.2.1 Naïve Bayes Classifier 15.2.2.2 Decision Trees 15.2.2.3 Support Vector Machine 15.2.2.4 KNN 15.2.2.5 K-Means 15.2.2.6 Random Forest 15.2.2.7 Logistic Regression 15.2.2.8 ANN 15.2.3 ML Approach for Breast Cancer Prognosis 15.3 Experimental Summary 15.4 Challenges 15.5 Conclusion References 16. Machine Learning-Based Active Contour Approach for the Recognition of Brain Tumor Progression 16.1 Introduction 16.2 Literature Survey 16.2.1 Solutions for Automated Diagnosis 16.2.2 Classification-Based solutions 16.2.3 SVM-Based solutions 16.2.4 CNN-Based solutions 16.2.5 Active Contour–Based Solutions 16.2.6 Feature-Extraction–Based Solutions 16.3 ML-Based Active Contour Approach 16.4 Simulation and Performance Analysis 16.5 Conclusion References 17. A Deep Neural Networks-Based Cost-Effective Framework for Diabetic Retinopathy Detection 17.1 Introduction 17.2 Related Work 17.3 Methodology 17.3.1 Proposed Computational CNN 17.3.1.1 Preprocessing of Dataset 17.3.1.2 Functionality of Proposed Convolutional Network 17.3.2 Framework User Interface 17.4 Results and Discussion 17.5 Conclusion References Index "Data Science for Effective Healthcare Systems has a prime focus on the importance of data science in the healthcare domain. Various applications of data science in the health care domain have been studied to find possible solutions. In this period of COVID-19 pandemic data science and allied areas plays a vital role to deal with various aspect of health care. Image processing, detection & prevention from COVID-19 virus, drug discovery, early prediction, and prevention of diseases are some thrust areas where data science has proven to be indispensable. The aim of this book is also to provide the future scope of these technologies in the health care domain. Last but not the least, this book will surely benefit research scholar, persons associated with healthcare, faculty, research organizations, and students to get insights into these emerging technologies in the healthcare domain"-- Provided by publisher