AI and Blockchain in Healthcare

Description:
This book presents state-of-the-art blockchain and AI advances in health care. Healthcare service is increasingly creating the scope for blockchain and AI applications to enter the biomedical and healthcare world. Today, blockchain, AI, ML, and deep learning are affecting every domain. Through its cutting-edge applications, AI and ML are helping transform the healthcare industry for the better. Blockchain is a decentralization communication platform that has the potential to decentralize the way we store data and manage information. Blockchain technology has potential to reduce the role of middleman, one of the most important regulatory actors in our society. Transactions are simultaneously secure and trustworthy due to the use of cryptographic principles. In recent years, blockchain technology has become very trendy and has penetrated different domains, mostly due to the popularity of cryptocurrencies. One field where blockchain technology has tremendous potential is health care, due to the need for a more patient-centric approach in healthcare systems to connect disparate systems and to increase the accuracy of electronic healthcare records (EHRs).

See more medical ebooks here:

Blockchain Technology in e-Healthcare Management

Trends of Artificial Intelligence and Big Data for E-Health

Artificial Intelligence for Disease Diagnosis and Prognosis in Smart Healthcare

Artificial Intelligence in the Clinical Laboratory | CBR60

Practical Artificial Intelligence for Internet of Medical Things

Preface

In today’s scenario, humankind has entered the domain of the Industrial revolution requirements with advanced tools and techniques. Artificial intelligence (AI) plays a pivotal role in the simulation of human intelligence to process, especially in computing systems. The performance of AI has various applications to apply in expert systems, natural language processing, speech recognition, machine vision, and more. In addition, some specific applications need special attention to deploy because AI helps data to process intelligently and outer protection coverage with some technology, like Blockchain. We have considered one of the Blockchain technologies to apply its principles to AI. This book provides basic concepts and applications of state-of-the-art Blockchain and AI research in healthcare. Its primary focus is on challenges and solutions to apply for the most-intensive application protections with AI techniques as a human safety integration with the healthcare area.

In this digital age, for all of our daily life, security and privacy are the most crucial parts. Dealing with tools and technologies is one of the significant challenges because so many attacks are reported on all kinds of computer systems and networks. It is becoming increasingly important to develop more robust, adaptive, scalable, reliable, private, and secured mechanisms for applications in their related areas. In relation to the same, it is imperative to understand the fundamentals of how AI is applicable with security principles, vulnerabilities protection, handful solutions & optimized solutions applicability use as defense mechanisms.

The objective of this book is to collect and address a variety of problems related to Healthcare Mechanisms, because, in the fast-growing environment, the research trends in this area are always having great demand in the form of prospective mechanisms. The contributors address theoretical and practical aspects of the challenges and opportunities of the application to strengthen the development of platforms. This book aids readers in gaining insight and knowledge about providing security and solutions to different challenges in healthcare using AI and Blockchain technology.

Therefore, we have an attempt to provide a significant effort in the form of a present book entitled “AI and Blockchain in Healthcare”. The book contains fourteen chapters (14).

Chapter 1 covers drug discovery and manufacturing with machine learning (ML), which is used at each phase of drug development to speed up research on reducing risk and minimizing the cost in clinical trials. The ML techniques discussed herein are expected to increase the ML roles in drug discovery and manufacturing processes to a new level with the aid of advanced computer intelligence.

Chapter 2 discusses finding one of the best strategies with the Analytical Network Process (ANP) approach, whose results will help epidemiologists and healthcare center workers to take relevant measures. In addition, a case study is presented to confirm the measures extracted in the healthcare centers of Qeshm Island.

Chapter 3 discusses the Era of Blockchain in Healthcare, which is one of the most important application areas where Blockchain is expected to have a significant impact on other applications. It has allowed for more effective and efficient patient care administration. Blockchain helped this sector due to its useful characteristics: peer-to-peer, protected, and transparent technologies.

Chapter 4 presents Securing Healthcare records, Applications, and Challenges using Blockchain with the benefits of adopting blockchain technology for securing healthcare data and emphasizes its important characteristics. The work also lists the challenges impeding blockchain implementation in the healthcare sector.

Chapter 5 discusses the authentication schemes for healthcare data using emerging computing technologies, where results show the main interests while presenting data security and verification techniques, as well as validating the focus of past studies towards authentication schemes using the applications of emerging computing techniques.

Chapter 6 discusses biomedical data classification using fuzzy clustering designed for problems where the very nature of data is unclear and uncertain. It also focuses on the impact of related technologies on human life that has made a tremendous impact in enforcing acceptance of such smart intelligence technologies in various aspects of our lives.

Chapter 7 presents a case study of lung cancer diagnosis through deep learning. The literature for lung cancer detection employs features using deep residual networks, and a comparison between existing techniques is presented and discussed.

Chapter 8 endeavors the machine and deep learning models experimented on cardiotocograph (CTG) data. It has played a huge role in understanding the data and corresponding requirements of data preprocessing. It is also classified into various models that are used in experimenting the data augmentation with clear benefits in terms of performance analysis.

Chapter 9 focuses on the Blockchain framework, applications of Blockchain and machine learning in clinical research for health and well-being, impact, and future prospects of the healthcare ecosystem. The security issues of e-healthcare systems and various Security Protocols have been discussed.

Chapter 10 discusses a breast cancer-based recommendation system. It will provide insights into recommendation scenarios and recommendation approaches. The examples are from the prediction and treatment of breast cancer and recommendation for drug and rehabilitation. Finally, the challenges concerning the development of recommender systems in the future are discussed.

Chapter 11 concentrates on Real-Time Data Mining-Based Cancer Disease Classification Using the KEGG (Kyoto Encyclopedia of Genes and Genomes) Gene Dataset. This study’s goal is to develop an effective computational strategy for identifying the sort of cancer tumors that will develop to find a wide variety of cancerrelated disorders, their examination, and training of bioinformatics, as well as the memorization of knowledge about genomics, met genomics, and metabolomics.

Chapter 12 introduces the solution architecting on remote medical monitoring with AWS cloud and IoT. The findings use amazon web services while patientsdoctors are online in the healthcare industry by cutting response time. The data is collected via an IoT that takes care of most of the concerns.

Chapter 13 this chapter presents a domain-oriented framework for the prediction of diabetes disease and the classification of diet. The proposed approach is available for Diabetic Prediction and Diet using Machine Learning Techniques with 10-fold cross-validation. The collected data is from the PIMA database for its classification.

Chapter 14 proposes an implementation to identify the most widely spread illness globally, known as swine flu, using a database of treatment patients. Swine flu is a respiratory sickness requiring a large number of tests from the patient to identify an illness. In order to justify this, it is proposed that the situation may be remedied with the use of advanced information mining techniques.

We hope that the works published in this book will be able to serve the concerned communities working in the fields of Healthcare, AI, Blockchain, Security, and IoT

Table of contents :
Preface
Contents
Part I Role of AI and Blockchain in Healthcare
1 Machine Learning for Drug Discovery and Manufacturing
1.1 Introduction
1.2 Machine learning (ML)
1.2.1 Artificial Intelligence (AI)
1.2.2 Machine Learning Techniques (MLTs)
1.2.3 Classification of ML
1.3 ML for Drug Discovery and Manufacturing
1.3.1 ML and Drug Discovery
1.3.2 MLTs Role in Drug Discovery
1.3.3 Examples of MLTs in Drug Discovery
1.3.4 Support Vector Machine
1.3.5 Random Forest
1.3.6 Multilayer Perceptron
1.3.7 Deep Learning
1.4 ML Applications in Drug Production
1.5 Challenges and Risks
1.6 Conclusions and Future Perspectives
References
2 Knowledge Strategies Influencing on the Epidemiologists Performance of the Qeshm Island’s Health Centers
2.1 Introduction
2.2 Literature Review
2.3 Qeshm Island
2.4 Research Methodology
2.4.1 Analytical Network Process (ANP)
2.4.2 ANP-Proposed Algorithm
2.5 Results and Discussion
2.6 Conclusion
References
3 Healthcare: In the Era of Blockchain
3.1 Introduction
3.2 Related Work
3.3 Application Areas of Blockchain in Healthcare
3.4 Limitations and Challenges in the Adoption of Blockchain in Healthcare
3.5 Conclusion
References
4 Securing Healthcare Records Using Blockchain: Applications and Challenges
4.1 Introduction
4.2 Why Blockchain?
4.3 Applications
4.4 Limitations
References
5 Authentication Schemes for Healthcare Data Using Emerging Computing Technologies
5.1 Introduction
5.2 Related Work
5.3 Text Analytics of Related Studies Using Word Cloud
5.3.1 Proposed Method
5.3.2 Data Collection
5.3.3 Data Analysis
5.3.4 Discussion
5.4 Conclusion
References
6 Biomedical Data Classification Using Fuzzy Clustering
6.1 Introduction
6.2 Fuzzy Logic and Biomedical Data
6.3 Need for Fuzzy Logic in Biomedical Domain
6.4 Various Types of Clustering on Biomedical Data
6.4.1 Fuzzy c-Means Algorithm (FCM)
6.4.2 Hierarchical Clustering
6.4.3 K-means Clustering Algorithm
6.5 Conclusion
References
Part II Application of AI and Blockchain in Healthcare
7 Applications of Machine Learning in Healthcare with a Case Study of Lung Cancer Diagnosis Through Deep Learning Approach
7.1 Introduction
7.2 Related Work
7.3 Background
7.3.1 Convolutional Neural Network
7.3.2 Deep Learning
7.3.3 Applications of Machine Learning
7.3.4 Lung Cancer Causes
7.4 Conclusion
References
8 Fetal Health Status Prediction During Labor and Delivery Based on Cardiotocogram Data Using Machine and Deep Learning
8.1 Introduction
8.2 Related Work
8.3 Methodology
8.3.1 Machine Learning Models
8.3.2 Deep Learning Models
8.4 Experimental Evaluation and Result Discussion
8.4.1 Brief Dataset Description
8.4.2 Performance Metrics
8.4.3 Data Visualization and Data Pre-processing
8.4.4 Performance Evaluation—Machine Learning Models
8.4.5 Performance Evaluation—Deep Learning Models
8.5 Conclusion
References
9 Blockchain and AI: Disruptive Digital Technologies in Designing the Potential Growth of Healthcare Industries
9.1 Introduction
9.2 Review of AI in Health Care
9.3 Applications of AI in Health Care
9.4 Review of Blockchain and AI in Health Care
9.5 Blockchain Framework
9.6 Applications of Blockchain in Health Care
9.6.1 Health Records
9.6.2 Supply Chains
9.6.3 Genomic Market
9.7 Metaverse
9.8 Metaverse for Health and Wellbeing
9.9 Limoverse, The Blockchain and AI Revolution in Health Care
9.10 Impact of Blockchain and AI in Health Care
9.11 Future Prospects of Blockchain and AI in the Healthcare Ecosystem
9.12 Conclusion
References
10 Recommendation Systems for Cancer Prognosis, Treatment and Wellness
10.1 Introduction
10.2 Cancer Diagnoses, Treatment and Rehabilitation
10.3 Applications of Computer Based System in Cancer Study
10.4 Recommendation Systems: History and Introduction
10.5 Recommendation SystemsAlgorithms for Cancer Study
10.5.1 Predicting Cancer Drug Response Using a Recommender System
10.5.2 Recommender System for Breast Cancer Patients
10.5.3 Personal Health Information Recommender for Empowering Cancer Patients
10.5.4 Gene Based Recommendation Algorithm to Recommend Genes for Cancer Patients
10.6 Recommendation System with Blended Approach for Breast Cancer Diagnosis-BC Recommender
10.6.1 Methodology
10.7 Observations and Discussion
10.8 Challenges and Future Work
References
11 Real-Time Data Mining-Based Cancer Disease Classification Using KEGG Gene Dataset
11.1 Introduction
11.2 Literature Survey
11.3 CFARM-KEGG Architecture
11.4 Results
11.5 Conclusion
References
12 Solution Architecting on Remote Medical Monitoring with AWS Cloud and IoT
12.1 Introduction
12.2 Literature Review
12.3 Internet of Things (IoT)
12.4 Cloud Healthcare Management
12.4.1 Infrastructure as a Service (IaaS)
12.4.2 Platform as a Service (PaaS)
12.4.3 Software as a Service (SaaS)
12.4.4 Deployment Models
12.4.5 Cloud
12.4.6 Hybrid
12.4.7 On-Premises
12.5 AWS
12.6 Conclusion
References
13 A Domain Oriented Framework for Prediction of Diabetes Disease and Classification of Diet Using Machine Learning Techniques
13.1 Introduction
13.1.1 Machine Learning
13.2 Literature Survey
13.3 Framework for Diabetic Prediction and Diet Using Machine Learning
13.3.1 Data Set Collection
13.3.2 Data Preprocessing
13.3.3 Data Distribution
13.3.4 Data Exploring and Cleaning
13.4 Machine Learning Classification
13.5 Algorithms for Food Recommendation to Diabetic Patients by Using Machine Learning
13.5.1 Diet Recommendations for Diabetic Patients
13.5.2 Characteristics of Diabetes
13.5.3 Fruit Consumption and Diabetes Prevention
13.5.4 How Does Fruit Consumption Help to Avoid Diabetes
13.6 Experimental Setup
13.7 Result and Analysis
13.8 Conclusion and Future Work
References
14 An Accurate Swine Flu Prediction and Early Prediction Using Data Mining Technique
14.1 Introduction
14.2 Literature Survey
14.3 Existing Methods
14.4 Conclusion
14.5 Future Work
References