Biomedical Data Mining for Information Retrieval

Sujata Dash received her PhD in Computational Modeling from Berhampur University, Orissa, India in 1995. She is an associate professor in P.G. Department of Computer Science & Application, North Orissa University, at Baripada, India. She has published more than 80 technical papers in international journals, conferences, book chapters and has authored 5 books. Subhendu Kumar Pani received his PhD from Utkal University Odisha, India in 2013. He is working as Professor in the Krupajal Computer Academy, BPUT, Odisha, India. S. Balamurugan is the Director-Research and Development, Intelligent Research Consultancy Services(iRCS), Coimbatore, Tamilnadu, India. His PhD is in Infomation Technology and he has published 45 books, 200+ international journals/conferences and 35 patents. Ajith Abraham received PhD in Computer Science from Monash University, Melbourne, Australia in 2001. He is Director of Machine Intelligence Research Labs (MIR Labs) which has members from 100+ countries. Ajith’s research experience includes over 30 years in the industry and academia. He has authored / co-authored over 1300+ publications (with colleagues from nearly 40 countries) and has an h-index of 86+.

• Preface xv1 Mortality Prediction of ICU Patients Using Machine Learning Techniques 1Babita Majhi, Aarti Kashyap and Ritanjali Majhi1.1 Introduction 21.2 Review of Literature 31.3 Materials and Methods 81.3.1 Dataset 81.3.2 Data Pre-Processing 81.3.3 Normalization 81.3.4 Mortality Prediction 101.3.5 Model Description and Development 111.4 Result and Discussion 151.5 Conclusion 161.6 Future Work 16References 172 Artificial Intelligence in Bioinformatics 21V. Samuel Raj, Anjali Priyadarshini, Manoj Kumar Yadav, Ramendra Pati Pandey, Archana Gupta and Arpana Vibhuti2.1 Introduction 212.2 Recent Trends in the Field of AI in Bioinformatics 222.2.1 DNA Sequencing and Gene Prediction Using Deep Learning 242.3 Data Management and Information Extraction 262.4 Gene Expression Analysis 262.4.1 Approaches for Analysis of Gene Expression 272.4.2 Applications of Gene Expression Analysis 292.5 Role of Computation in Protein Structure Prediction 302.6 Application in Protein Folding Prediction 312.7 Role of Artificial Intelligence in Computer-Aided Drug Design 382.8 Conclusions 42References 433 Predictive Analysis in Healthcare Using Feature Selection 53Aneri Acharya, Jitali Patel and Jigna Patel3.1 Introduction 543.1.1 Overview and Statistics About the Disease 543.1.1.1 Diabetes 543.1.1.2 Hepatitis 553.1.2 Overview of the Experiment Carried Out 563.2 Literature Review 583.2.1 Summary 583.2.2 Comparison of Papers for Diabetes and Hepatitis Dataset 613.3 Dataset Description 703.3.1 Diabetes Dataset 703.3.2 Hepatitis Dataset 713.4 Feature Selection 733.4.1 Importance of Feature Selection 743.4.2 Difference Between Feature Selection, Feature Extraction and Dimensionality Reduction 743.4.3 Why Traditional Feature Selection Techniques Still Holds True? 753.4.4 Advantages and Disadvantages of Feature Selection Technique 763.4.4.1 Advantages 763.4.4.2 Disadvantage 763.5 Feature Selection Methods 763.5.1 Filter Method 763.5.1.1 Basic Filter Methods 773.5.1.2 Correlation Filter Methods 773.5.1.3 Statistical & Ranking Filter Methods 783.5.1.4 Advantages and Disadvantages of Filter Method 803.5.2 Wrapper Method 803.5.2.1 Advantages and Disadvantages of Wrapper Method 823.5.2.2 Difference Between Filter Method and Wrapper Method 823.6 Methodology 843.6.1 Steps Performed 843.6.2 Flowchart 843.7 Experimental Results and Analysis 853.7.1 Task 1—Application of Four Machine Learning Models 853.7.2 Task 2—Applying Ensemble Learning Algorithms 863.7.3 Task 3—Applying Feature Selection Techniques 873.7.4 Task 4—Appling Data Balancing Technique 943.8 Conclusion 96References 994 Healthcare 4.0: An Insight of Architecture, Security Requirements, Pillars and Applications 103Deepanshu Bajaj, Bharat Bhushan and Divya Yadav4.1 Introduction 1044.2 Basic Architecture and Components of e-Health Architecture 1054.2.1 Front End Layer 1064.2.2 Communication Layer 1074.2.3 Back End Layer 1074.3 Security Requirements in Healthcare 4.0 1084.3.1 Mutual-Authentications 1094.3.2 Anonymity 1104.3.3 Un-Traceability 1114.3.4 Perfect—Forward—Secrecy 1114.3.5 Attack Resistance 1114.3.5.1 Replay Attack 1114.3.5.2 Spoofing Attack 1124.3.5.3 Modification Attack 1124.3.5.4 MITM Attack 1124.3.5.5 Impersonation Attack 1124.4 ICT Pillar’s Associated With HC4.0 1134.4.1 IoT in Healthcare 4.0 1144.4.2 Cloud Computing (CC) in Healthcare 4.0 1154.4.3 Fog Computing (FC) in Healthcare 4.0 1164.4.4 BigData (BD) in Healthcare 4.0 1174.4.5 Machine Learning (ML) in Healthcare 4.0 1184.4.6 Blockchain (BC) in Healthcare 4.0 1204.5 Healthcare 4.0’s Applications-Scenarios 1214.5.1 Monitor-Physical and Pathological Related Signals 1214.5.2 Self-Management, and Wellbeing Monitor, and its Precaution 1244.5.3 Medication Consumption Monitoring and Smart-Pharmaceutics 1244.5.4 Personalized (or Customized) Healthcare 1254.5.5 Cloud-Related Medical Information’s Systems 1254.5.6 Rehabilitation 1264.6 Conclusion 126References 1275 Improved Social Media Data Mining for Analyzing Medical Trends 131Minakshi Sharma and Sunil Sharma5.1 Introduction 1325.1.1 Data Mining 1325.1.2 Major Components of Data Mining 1325.1.3 Social Media Mining 1345.1.4 Clustering in Data Mining 1345.2 Literature Survey 1365.3 Basic Data Mining Clustering Technique 1405.3.1 Classifier and Their Algorithms in Data Mining 1435.4 Research Methodology 1475.5 Results and Discussion 1515.5.1 Tool Description 1515.5.2 Implementation Results 1525.5.3 Comparison Graphs Performance Comparison 1565.6 Conclusion & Future Scope 157References 1586 Bioinformatics: An Important Tool in Oncology 163Gaganpreet Kaur, Saurabh Gupta, Gagandeep Kaur, Manju Verma and Pawandeep Kaur6.1 Introduction 1646.2 Cancer—A Brief Introduction 1656.2.1 Types of Cancer 1666.2.2 Development of Cancer 1666.2.3 Properties of Cancer Cells 1666.2.4 Causes of Cancer 1686.3 Bioinformatics—A Brief Introduction 1696.4 Bioinformatics—A Boon for Cancer Research 1706.5 Applications of Bioinformatics Approaches in Cancer 1746.5.1 Biomarkers: A Paramount Tool for Cancer Research 1756.5.2 Comparative Genomic Hybridization for Cancer Research 1776.5.3 Next-Generation Sequencing 1786.5.4 miRNA 1796.5.5 Microarray Technology 1816.5.6 Proteomics-Based Bioinformatics Techniques 1856.5.7 Expressed Sequence Tags (EST) and Serial Analysis of Gene Expression (SAGE) 1876.6 Bioinformatics: A New Hope for Cancer Therapeutics 1886.7 Conclusion 191References 1927 Biomedical Big Data Analytics Using IoT in Health Informatics 197Pawan Singh Gangwar and Yasha Hasija7.1 Introduction 1987.2 Biomedical Big Data 2007.2.1 Big EHR Data 2017.2.2 Medical Imaging Data 2017.2.3 Clinical Text Mining Data 2017.2.4 Big OMICs Data 2027.3 Healthcare Internet of Things (IoT) 2027.3.1 IoT Architecture 2027.3.2 IoT Data Source 2047.3.2.1 IoT Hardware 2047.3.2.2 IoT Middleware 2057.3.2.3 IoT Presentation 2057.3.2.4 IoT Software 2057.3.2.5 IoT Protocols 2067.4 Studies Related to Big Data Analytics in Healthcare IoT 2067.5 Challenges for Medical IoT & Big Data in Healthcare 2097.6 Conclusion 210References 2108 Statistical Image Analysis of Drying Bovine Serum Albumin Droplets in Phosphate Buffered Saline 213Anusuya Pal, Amalesh Gope and Germano S. Iannacchione8.1 Introduction 2148.2 Experimental Methods 2168.3 Results 2178.3.1 Temporal Study of the Drying Droplets 2178.3.2 FOS Characterization of the Drying Evolution 2198.3.3 GLCM Characterization of the Drying Evolution 2208.4 Discussions 2248.4.1 Qualitative Analysis of the Drying Droplets and the Dried Films 2248.4.2 Quantitative Analysis of the Drying Droplets and the Dried Films 2278.5 Conclusions 231Acknowledgments 232References 2329 Introduction to Deep Learning in Health Informatics 237Monika Jyotiyana and Nishtha Kesswani9.1 Introduction 2379.1.1 Machine Learning v/s Deep Learning 2409.1.2 Neural Networks and Deep Learning 2419.1.3 Deep Learning Architecture 2429.1.3.1 Deep Neural Networks 2439.1.3.2 Convolutional Neural Networks 2439.1.3.3 Deep Belief Networks 2449.1.3.4 Recurrent Neural Networks 2449.1.3.5 Deep Auto-Encoder 2459.1.4 Applications 2469.2 Deep Learning in Health Informatics 2469.2.1 Medical Imaging 2469.2.1.1 CNN v/s Medical Imaging 2479.2.1.2 Tissue Classification 2479.2.1.3 Cell Clustering 2479.2.1.4 Tumor Detection 2479.2.1.5 Brain Tissue Classification 2489.2.1.6 Organ Segmentation 2489.2.1.7 Alzheimer’s and Other NDD Diagnosis 2489.3 Medical Informatics 2499.3.1 Data Mining 2499.3.2 Prediction of Disease 2499.3.3 Human Behavior Monitoring 2509.4 Bioinformatics 2509.4.1 Cancer Diagnosis 2509.4.2 Gene Variants 2519.4.3 Gene Classification or Gene Selection 2519.4.4 Compound–Protein Interaction 2519.4.5 DNA–RNA Sequences 2529.4.6 Drug Designing 2529.5 Pervasive Sensing 2529.5.1 Human Activity Monitoring 2539.5.2 Anomaly Detection 2539.5.3 Biological Parameter Monitoring 2539.5.4 Hand Gesture Recognition 2539.5.5 Sign Language Recognition 2549.5.6 Food Intake 2549.5.7 Energy Expenditure 2549.5.8 Obstacle Detection 2549.6 Public Health 2559.6.1 Lifestyle Diseases 2559.6.2 Predicting Demographic Information 2569.6.3 Air Pollutant Prediction 2569.6.4 Infectious Disease Epidemics 2579.7 Deep Learning Limitations and Challenges in Health Informatics 257References 25810 Data Mining Techniques and Algorithms in Psychiatric Health: A Systematic Review 263Shikha Gupta, Nitish Mehndiratta, Swarnim Sinha, Sangana Chaturvedi and Mehak Singla10.1 Introduction 26310.2 Techniques and Algorithms Applied 26510.3 Analysis of Major Health Disorders Through Different Techniques 26710.3.1 Alzheimer 26710.3.2 Dementia 26810.3.3 Depression 27410.3.4 Schizophrenia and Bipolar Disorders 28110.4 Conclusion 285References 28611 Deep Learning Applications in Medical Image Analysis 293Ananya Singha, Rini Smita Thakur and Tushar Patel11.1 Introduction 29411.1.1 Medical Imaging 29511.1.2 Artificial Intelligence and Deep Learning 29611.1.3 Processing in Medical Images 30011.2 Deep Learning Models and its Classification 30311.2.1 Supervised Learning 30311.2.1.1 RNN (Recurrent Neural Network) 30311.2.2 Unsupervised Learning 30411.2.2.1 Stacked Auto Encoder (SAE) 30411.2.2.2 Deep Belief Network (DBN) 30611.2.2.3 Deep Boltzmann Machine (DBM) 30711.2.2.4 Generative Adversarial Network (GAN) 30811.3 Convolutional Neural Networks (CNN)—A Popular Supervised Deep Model 30911.3.1 Architecture of CNN 31011.3.2 Learning of CNNs 31311.3.3 Medical Image Denoising using CNNs 31411.3.4 Medical Image Classification Using CNN 31611.4 Deep Learning Advancements—A Biological Overview 31711.4.1 Sub-Cellular Level 31711.4.2 Cellular Level 31911.4.3 Tissue Level 32311.4.4 Organ Level 32611.4.4.1 The Brain and Neural System 32611.4.4.2 Sensory Organs—The Eye and Ear 32911.4.4.3 Thoracic Cavity 33011.4.4.4 Abdomen and Gastrointestinal (GI) Track 33111.4.4.5 Other Miscellaneous Applications 33211.5 Conclusion and Discussion 335References 33612 Role of Medical Image Analysis in Oncology 351Gaganpreet Kaur, Hardik Garg, Kumari Heena, Lakhvir Singh, Navroz Kaur, Shubham Kumar and Shadab Alam12.1 Introduction 35212.2 Cancer 35312.2.1 Types of Cancer 35412.2.2 Causes of Cancer 35512.2.3 Stages of Cancer 35512.2.4 Prognosis 35612.3 Medical Imaging 35712.3.1 Anatomical Imaging 35712.3.2 Functional Imaging 35812.3.3 Molecular Imaging 35812.4 Diagnostic Approaches for Cancer 35812.4.1 Conventional Approaches 35812.4.1.1 Laboratory Diagnostic Techniques 35912.4.1.2 Tumor Biopsies 35912.4.1.3 Endoscopic Exams 36012.4.2 Modern Approaches 36112.4.2.1 Image Processing 36112.4.2.2 Implications of Advanced Techniques 36212.4.2.3 Imaging Techniques 36312.5 Conclusion 375References 37613 A Comparative Analysis of Classifiers Using Particle Swarm Optimization-Based Feature Selection 383Chandra Sekhar Biswal, Subhendu Kumar Pani and Sujata Dash13.1 Introduction 38413.2 Feature Selection for Classification 38513.2.1 An Overview: Data Mining 38513.2.2 Classification Prediction 38713.2.3 Dimensionality Reduction 38713.2.4 Techniques of Feature Selection 38813.2.5 Feature Selection: A Survey 39213.2.6 Summary 39413.3 Use of WEKA Tool 39513.3.1 WEKA Tool 39513.3.2 Classifier Selection 39513.3.3 Feature Selection Algorithms in WEKA 39513.3.4 Performance Measure 39613.3.5 Dataset Description 39813.3.6 Experiment Design 39813.3.7 Results Analysis 39913.3.8 Summary 40113.4 Conclusion and Future Work 40113.4.1 Summary of the Work 40113.4.2 Research Challenges 40213.4.3 Future Work 404References 404Index 409