1st Edition

Swarm Intelligence and Evolutionary Algorithms in Healthcare and Drug Development

Edited By Sandeep Kumar, Anand Nayyar, Anand Paul Copyright 2020
    168 Pages 24 B/W Illustrations
    by Chapman & Hall

    168 Pages 24 B/W Illustrations
    by Chapman & Hall

    Healthcare sector is characterized by difficulty, dynamism and variety. In 21st century, healthcare domain is surrounded by tons of challenges in terms of Disease detection, prevention, high costs, skilled technicians and better infrastructure. In order to handle these challenges, Intelligent Healthcare management technologies are required to play an effective role in improvising patient’s life. Healthcare organizations also need to continuously discover useful and actionable knowledge to gain insight from tons of data for various purposes for saving lives, reducing medical operations errors, enhancing efficiency, reducing costs and making the whole world a healthy world.

    Applying Swarm Intelligence and Evolutionary Algorithms in Healthcare and Drug Development is essential nowadays. The objective of this book is to highlight various Swarm Intelligence and Evolutionary Algorithms techniques for various medical issues in terms of Cancer Diagnosis, Brain Tumor, Diabetic Retinopathy, Heart disease as well as drug design and development. The book will act as one-stop reference for readers to think and explore Swarm Intelligence and Evolutionary Algorithms seriously for real-time patient diagnosis, as the book provides solutions to various complex diseases found critical for medical practitioners to diagnose in real-world.

    Key Features:

    • Highlights the importance and applications of Swarm Intelligence and Evolutionary Algorithms in Healthcare industry.
    • Elaborates Swarm Intelligence and Evolutionary Algorithms for Cancer Detection.
    • In-depth coverage of computational methodologies, approaches and techniques based on Swarm Intelligence and Evolutionary Algorithms for detecting Brain Tumour including deep learning to optimize brain tumor diagnosis.
    • Provides a strong foundation for Diabetic Retinopathy detection using Swarm and Evolutionary algorithms.
    • Focuses on applying Swarm Intelligence and Evolutionary Algorithms for Heart Disease detection and diagnosis.
    • Comprehensively covers the role of Swarm Intelligence and Evolutionary Algorithms for Drug Design and Discovery.

    The book will play a significant role for Researchers, Medical Practitioners, Healthcare Professionals and Industrial Healthcare Research and Development wings to conduct advanced research in Healthcare using Swarm Intelligence and Evolutionary Algorithms techniques.

     CONTENTS

    Preface, xi

    About the Editors, xv

    Contributors, xix

    Abbreviations, xxi

    CHAPTER 1 ■ Swarm Intelligence and Evolutionary

    Algorithms in Disease Diagnosis—Introductory

    Aspects 1

    BHUSHAN INJE, SANDEEP KUMAR, AND ANAND NAYYAR

    1.1 INTRODUCTION 1

    1.2 TERMINOLOGIES 2

    1.2.1 Swarm Intelligence 2

    1.2.1.1 Merits of Swarm Intelligence 3

    1.2.1.2 Classifications and Terminology 4

    1.2.2 Evolutionary Computation 5

    1.2.3 Evolutionary Computation Paradigms 6

    1.3 IMPORTANCE OF SWARM INTELLIGENCE IN

    DISEASE DIAGNOSIS 7

    1.4 IMPORTANCE OF EVOLUTIONARY ALGORITHMS

    IN DISEASE DIAGNOSIS 10

    1.5 CONCLUSION 14

    CHAPTER 2 ■ Swarm Intelligence and Evolutionary

    Algorithms for Cancer Diagnosis 19

    BANDANA MAHAPATRA AND ANAND NAYYAR

    2.1 INTRODUCTION 19

    2.2 CLASSIFICATION OF CANCER 21

    2.3 CHALLENGES IN CANCER DIAGNOSIS 26

    2.3.1 Methods of Cancer Detection 26

    2.3.2 Issues and Challenges Faced While Cancer

    Detection Process 27

    2.4 APPLYING SWARM INTELLIGENCE ALGORITHM

    FOR CANCER DIAGNOSIS 28

    2.4.1 SI Algorithms for Detection of Lung Cancer 29

    2.4.2 Swarm Intelligence for Breast Cancer 30

    2.4.3 Swarm Intelligence for Ovarian Cancer 30

    2.4.4 SI Algorithm for Early Detection of Gastro Cancer 30

    2.4.5 Swarm Intelligence for Treating Nano-Robots 31

    2.5 APPLYING EVOLUTIONARY ALGORITHM FOR

    CANCER DETECTION 34

    2.6 CONCLUSION 40

    CHAPTER 3 ■ Brain Tumour Diagnosis 45

    DHANANJAY JOSHI, NITIN CHOUBEY, AND RAJANI KUMARI

    3.1 INTRODUCTION 45

    3.2 APPLYING EVOLUTIONARY ALGORITHMS FOR

    BRAIN TUMOR DIAGNOSIS 50

    3.2.1 Evolutionary Algorithm 50

    3.2.2 Conceptual Framework 1: Applying Evolutionary

    Algorithm for Brain Tumor Diagnosis. 52

    3.3 APPLYING SWARM INTELLIGENCE ALGORITHMS

    FOR BRAIN TUMOR DIAGNOSIS 54

    3.3.1 Swarm Intelligence (SI) - Based Algorithms 54

    3.3.2 Self-Organization: 55

    3.3.3 Division of Labor: 55

    3.3.4 Particle Swarm Optimization 55

    3.3.5 Particle Swarm Optimization Algorithm 56

    3.3.6 Conceptual Framework 2: Applying Swarm

    Intelligence Based Algorithm for Brain Tumor

    Diagnosis 57

    3.4 APPLYING SWARM INTELLIGENCE AND

    EVOLUTIONARY ALGORITHMS TOGETHER FOR

    DIAGNOSIS OF BRAIN TUMOR 58

    3.5 APPLYING SWARM INTELLIGENCE, EVOLUTIONARY

    ALGORITHM AND INCORPORATING TOPOLOGICAL

    DATA ANALYSIS (TDA) FOR BRAIN TUMOR

    DIAGNOSIS 59

    3.5.1 Topological Data Analysis 59

    3.6 CONCLUSION 59

    CHAPTER 4 ■ Swarm Intelligence and Evolutionary

    Algorithms for Diabetic Retinopathy

    Detection 65

    SACHIN BHANDARI, RADHAKRISHNA RAMBOLA, AND RAJANI KUMARI

    4.1 INTRODUCTION 65

    4.1.1 Classification of Diabetic Retinopathy 66

    4.1.2 Swarm Optimization and Evolutionary

    Algorithms 69

    4.1.3 Objectives and Contributions 71

    4.2 FEATURE OF DIABETIC RETINOPATHY 72

    4.2.1 Microaneurysms 72

    4.2.2 Haemorrhages 73

    4.2.3 Hard Exudates 73

    4.2.4 Soft Exudates 73

    4.2.5 Neo-Vascularization 74

    4.2.6 Macular Edema 74

    4.3 DETECTION OF DIABETIC RETINOPATHY BY

    APPLYING SWARM INTELLIGENCE AND

    EVOLUTIONARY ALGORITHMS 74

    4.3.1 Genetic Algorithm 75

    4.3.2 Particle Swarm Optimization 79

    4.3.3 Ant Colony Optimization 81

    4.3.4 Cuckoo Search 84

    4.3.5 Bee Colony Optimization 85

    4.4 CONCLUSION 87

    CHAPTER 5 ■ Swarm Intelligence and Evolutionary

    Algorithms for Heart Disease Diagnosis 93

    RAJALAKSHMI KRISHNAMURTHI

    5.1 INTRODUCTION 93

    5.2 PREDICTION AND CLASSIFICATION OF HEART

    DISEASE USING MACHINE LEARNING/SWARM

    INTELLIGENCE 95

    5.2.1 Decision Support System 95

    5.2.2 Clinical Decision Support System 96

    5.2.3 Heart Disease Datasets 97

    5.3 PREDICTING HEART ATTACKS IN PATIENTS

    USING ARTIFICIAL INTELLIGENCE METHODS

    (FUZZY LOGIC) 98

    5.3.1 Fuzzy Logic Approach for Heart Disease Diagnosis 99

    5.3.2 Fuzzy Rule Base 101

    5.3.3 Fuzzy Inference Engine 102

    5.3.4 Defuzzification 102

    5.4 PREDICTING HEART DISEASE USING GENETIC

    ALGORITHMS 103

    5.5 SWARM INTELLIGENCE BASED OPTIMIZATION

    PROBLEM FOR HEART DISEASE DIAGNOSIS 105

    5.5.1 Ant Colony Optimization 105

    5.5.2 Particle Swarm Optimization 106

    5.6 HEART DISEASE PREDICTION USING DATA MINING

    TECHNIQUES 108

    5.7 PERFORMANCE METRICS 110

    5.8 CONCLUSION 113

    CHAPTER 6 ■ Swarm Intelligence and Evolutionary

    Algorithms for Drug Design and

    Development 117

    BANDANA MAHAPATRA

    6.1 INTRODUCTION 117

    6.2 DRUG DESIGN AND DEVELOPMENT: PAST, PRESENT

    AND FUTURE 119

    6.3 ROLE OF SWARM INTELLIGENCE IN DRUG DESIGN

    AND DEVELOPMENT 123

    6.4 ROLE OF EVOLUTIONARY ALGORITHMS IN DRUG

    DESIGN AND DEVELOPMENT 126

    6.5 QSAR MODELLING USING SWARM INTELLIGENCE

    AND EVOLUTIONARY ALGORITHMS 128

    6.6 PREDICTION OF MOLECULE ACTIVITY SWARM

    INTELLIGENCE AND EVOLUTIONARY ALGORITHMS 131

    6.6.1 Particle Swarm Optimization 135

    6.7 CONCLUSION 136

    INDEX, 141

    Biography

    Sandeep Kumar, Anand Nayyar, Anand Paul