Tele-Healthcare: Applications of Artificial Intelligence and Soft Computing Techniques

Description

TELE-HEALTHCARE This book elucidates all aspects of tele-healthcare which is the application of AI, soft computing, digital information, and communication technologies, to provide services remotely and manage one’s healthcare. Throughout the world, there are huge developing crises with respect to healthcare workforce shortages, as well as a growing burden of chronic diseases. As a result, e-health has become one of the fastest-growing service areas in the medical sector. E-health supports and ensures the availability of proper healthcare, public health, and health education services at a distance and in remote places. For the sector to grow and meet the need of the marketplace, e-health applications have become one of the fastest growing areas of research. However, to grow at a larger scale requires the following: The availability of user cases for the exact identification of problems that need to be visualized.A well-supported market that can promote and adopt the e-health care concept. Development of cost-effectiveness applications and technologies for successful implementation of e-health at a larger scale. This book mainly focuses on these three points for the development and implementation of e-health services globally. In this book the reader will find: Details of the challenges in promoting and implementing the telehealth industry.How to expand a globalized agenda of personalized telehealth in integrative medical treatment for disease diagnosis and its industrial transformation.How to design machine learning techniques for improving the tele-healthcare system. Audience Researchers and post-graduate students in biomedical engineering, artificial intelligence, and information technology; medical doctors and practitioners and industry experts in the healthcare sector; healthcare sector network administrators. Cover Half-Title Page Series Page Title Page Copyright Page Contents Preface 1 Machine Learning–Assisted Remote Patient Monitoring with Data Analytics 1.1 Introduction 1.1.1 Traditional Patient Monitoring System 1.1.2 Remote Monitoring System 1.1.3 Challenges in RPM 1.2 Literature Survey 1.2.1 Machine Learning Approaches in Patient Monitoring 1.3 Machine Learning in RPM 1.3.1 Support Vector Machine 1.3.2 Decision Tree 1.3.3 Random Forest 1.3.4 Logistic Regression 1.3.5 Genetic Algorithm 1.3.6 Simple Linear Regression 1.3.7 KNN Algorithm 1.3.8 Naive Bayes Algorithm 1.4 System Architecture 1.4.1 Data Collection 1.4.2 Data Pre-Processing 1.4.3 Apply Machine Learning Algorithm and Prediction 1.5 Results 1.6 Future Enhancement 1.7 Conclusion References 2 A Survey on Recent ComputerAided Diagnosis for Detecting Diabetic Retinopathy 2.1 Introduction 2.2 Diabetic Retinopathy 2.2.1 Features of DR 2.2.2 Stages of DR 2.3 Overview of DL Models 2.3.1 Convolution Neural Network 2.3.2 Autoencoders 2.3.3 Boltzmann Machine and Deep Belief Network 2.4 Data Set 2.5 Performance Metrics 2.6 Literature Survey 2.6.1 Segmentation of Blood Vessels 2.6.2 Optic Disc Feature 2.6.3 Lesion Detections 2.6.4 DR Classification 2.7 Discussion and Future Directions 2.8 Conclusion References 3 A New Improved Cryptography Method-Based e-Health Application in Cloud Computing Environment 3.1 Introduction 3.1.1 Contribution 3.2 Motivation 3.3 Related Works 3.4 Challenges 3.5 Proposed Work 3.6 Proposed Algorithm for Encryption 3.6.1 Demonstration of Encryption Algorithm 3.6.2 Flowchart for Encryption 3.7 Algorithm for Decryption 3.7.1 Demonstration of Decryption Algorithm 3.7.2 Flowchart of Decryption Algorithm 3.8 Experiment and Result 3.9 Conclusion References 4 Cutaneous Disease Optimization Using Teledermatology Underresourced Clinics 4.1 Introduction 4.2 Materials and Methods 4.2.1 Clinical Setting and Teledermatology Workflow 4.2.2 Study Design, Data Collection, and Analysis 4.3 Proposed System 4.3.1 Teledermatology in an Underresourced Clinic 4.3.2 Teledermatology Consultations from Uninsured Patients 4.3.3 Teledermatology for Patients Lacking Access to Dermatologists 4.3.4 Teledermatologist Management from Nonspecialists 4.3.5 Segment Factors of Referring PCPs and Their Patients 4.3.6 Teledermatology Operational Considerations 4.3.7 Instruction of PCPs 4.4 Challenges 4.5 Results and Discussion 4.5.1 Challenges of Referring to Teledermatology Services References 5 Cognitive Assessment Based on Eye Tracking Using Device-Embedded Cameras via Tele-Neuropsychology 5.1 Introduction 5.2 Materials and Methods 5.3 Framework Elements 5.3.1 Eye Tracker Camera 5.3.2 Test Construction 5.3.3 Web Camera 5.3.4 Camera for Eye Tracking 5.4 Proposed System 5.4.1 Camera for Tracking Eye 5.4.2 Web Camera 5.4.3 Scoring 5.4.4 Eye Tracking Camera 5.4.5 Web Camera Human-Coded Scoring 5.5 Subjects 5.5.1 Characteristics of Subject 5.6 Methodology 5.6.1 Analysis of Data 5.7 Results 5.8 Discussion 5.9 Conclusion References 6 Fuzzy-Based Patient Health Monitoring System 6.1 Introduction 6.1.1 General Problem 6.1.2 Existing Patient Monitoring and Diagnosis Systems 6.1.3 Fuzzy Logic Systems 6.2 System Design 6.2.1 Hardware Requirements 6.3 Software Architecture 6.3.1 The Data Acquisition Unit (DAQ) Application Programmable Interface (API) 6.3.2 Flowchart—API 6.3.3 Foreign Tag IDs 6.3.4 Database Manager 6.3.5 Database Designing 6.3.6 The Fuzzy Logic System 6.3.7 Designing a System in Fuzzy 6.4 Results and Discussion 6.4.1 Hardware Sensors Validation 6.4.2 Implementations, Testing, and Evaluation of the Fuzzy Logic Engine 6.4.3 Normal Group (NRM) 6.4.4 Low Risk Group 6.4.5 High Risk Group (HRG) 6.5 Conclusions and Future Work 6.5.1 Summary and Concluding Remarks 6.5.2 Future Directions References 7 Artificial Intelligence: A Key for Detecting COVID-19 Using Chest Radiography 7.1 Introduction 7.2 Related Work 7.2.1 Traditional Approach 7.2.2 Deep Learning–Based Approach 7.3 Materials and Methods 7.3.1 Data Set and Data Pre-Processing 7.3.2 Proposed Model 7.4 Experiment and Result 7.4.1 Experiment Setup 7.4.2 Comparison with Other Models 7.5 Results 7.6 Conclusion References 8 An Efficient IoT Framework for Patient Monitoring and Predicting Heart Disease Based on Machine Learning Algorithms 8.1 Introduction 8.2 Literature Survey 8.3 Machine Learning Algorithms 8.4 Problem Statement 8.5 Proposed Work 8.5.1 Data Set Description 8.5.2 Collection of Values Through Sensor Nodes 8.5.3 Storage of Data in Cloud 8.5.4 Prediction with Machine Learning Algorithms 8.5.5 Machine Learning Algorithms 8.6 Performance Analysis and Evaluation 8.7 Conclusion References 9 BABW: Biometric-Based Authentication Using DWT and FFNN 9.1 Introduction 9.2 Literature Survey 9.3 BABW: Biometric Authentication Using Brain Waves 9.4 Results and Discussion 9.5 Conclusion References 10 Autism Screening Tools With Machine Learning and Deep Learning Methods: A Review 10.1 Introduction 10.2 Autism Screening Methods 10.2.1 Autism Screening Instrument for Educational Planning—3rd Version 10.2.2 Quantitative Checklist for Autism in Toddlers 10.2.3 Autism Behavior Checklist 10.2.4 Developmental Behavior Checklist-Early Screen 10.2.5 Childhood Autism Rating Scale Version 2 10.2.6 Autism Spectrum Screening Questionnaire (ASSQ) 10.2.7 Early Screening for Autistic Traits 10.2.8 Autism Spectrum Quotient 10.2.9 Social Communication Questionnaire 10.2.10 Child Behavior Check List 10.2.11 Indian Scale for Assessment of Autism 10.3 Machine Learning in ASD Screening and Diagnosis 10.4 DL in ASD Diagnosis 10.5 Conclusion References 11 Drug Target Module Mining Using Biological Multifunctional Score-Based Coclustering 11.1 Introduction 11.2 Literature Study 11.3 Materials and Methods 11.3.1 Biological Terminologies 11.3.2 Functional Coherence 11.3.3 Biological Significances 11.3.4 Existing Approach: MR-CoC 11.4 Proposed Approach: MR-CoCmulti 11.4.1 Biological Score Measures for DTM 11.4.2 Multifunctional Score-Based Co-Clustering Approach 11.5 Experimental Analysis 11.5.1 Experimental Results 11.6 Discussion 11.7 Conclusion Acknowledgment References 12 The Ascendant Role of Machine Learning Algorithms in the Prediction of Breast Cancer and Treatment Using Telehealth 12.1 Introduction 12.1.1 Objective 12.1.2 Description and Goals 12.2 Literature Review 12.3 Architecture Design and Implementation 12.4 Results and Discussion 12.5 Conclusion 12.6 Future Work References 13 Remote Patient Monitoring: Data Sharing and Prediction Using Machine Learning 13.1 Introduction 13.1.1 Patient Monitoring in Healthcare System 13.2 Literature Survey 13.3 Problem Statement 13.4 Machine Learning 13.4.1 Introduction 13.4.2 Cloud Computing 13.4.3 Design and Architecture 13.5 Proposed System 13.6 Results and Discussions 13.7 Privacy and Security Challenges 13.8 Conclusions and Future Enhancement References 14 Investigations on Machine Learning Models to Envisage Coronavirus in Patients 14.1 Introduction 14.2 Categories of ML Algorithms in Healthcare 14.3 Why ML to Fight COVID-19? Tools and Techniques 14.4 Highlights of ML Algorithms Under Consideration 14.5 Experimentation and Investigation 14.6 Comparative Analysis of the Algorithms 14.7 Scope of Enhancement for Better Investigation References 15 Healthcare Informatics: Emerging Trends, Challenges, and Analysis of Medical Imaging 15.1 Emerging Trends and Challenges in Healthcare Informatics 15.1.1 Advanced Technologies in Healthcare Informatics 15.1.2 Intelligent Smart Healthcare Devices Using IoT With DL 15.1.3 Cyber Security in Healthcare Informatics 15.1.4 Trends, Challenges, and Issues in Healthcare IT Analytics 15.2 Performance Analysis of Medical Image Compression Using Wavelet Functions 15.2.1 Introduction 15.2.2 Materials and Methods 15.2.3 Wavelet Basis Functions 15.2.4 Compression Methods 15.3 Results and Discussion 15.3.1 Mean Square Error 15.3.2 Peak Signal to Noise Ratio 15.4 Conclusion 15.4.1 Summary References Index Also of Interest EULA