Trends of Artificial Intelligence and Big Data for E-Health

Description:

This book aims to present the impact of Artificial Intelligence (AI) and Big Data in healthcare for medical decision making and data analysis in myriad fields including Radiology, Radiomics, Radiogenomics, Oncology, Pharmacology, COVID-19 prognosis, Cardiac imaging, Neuroradiology, Psychiatry and others. This will include topics such as Artificial Intelligence of Thing (AIOT), Explainable Artificial Intelligence (XAI), Distributed learning, Blockchain of Internet of Things (BIOT), Cybersecurity, and Internet of (Medical) Things (IoTs). Healthcare providers will learn how to leverage Big Data analytics and AI as methodology for accurate analysis based on their clinical data repositories and clinical decision support. The capacity to recognize patterns and transform large amounts of data into usable information for precision medicine assists healthcare professionals in achieving these objectives. Intelligent Health has the potential to monitor patients at risk with underlying conditions and track their progress during therapy. Some of the greatest challenges in using these technologies are based on legal and ethical concerns of using medical data and adequately representing and servicing disparate patient populations. One major potential benefit of this technology is to make health systems more sustainable and standardized. Privacy and data security, establishing protocols, appropriate governance, and improving technologies will be among the crucial priorities for Digital Transformation in Healthcare.

See more medical ebooks at here:

The Internet of things enabling technologies, platforms, and use cases

Artificial Intelligence for Disease Diagnosis and Prognosis in Smart Healthcare

3D Printing for the Radiologist

Abdominal Imaging, Second Edition

Practical Artificial Intelligence for Internet of Medical Things

Introduction

In this book, we examine technologies that have significant impact to the healthcare sector. Some of those burgeoning technologies include: (1) artificial intelligence (AI); (2) Big Data; (3) Internet of Medical Things (IoMT); and (4) blockchain. The term e-health (digital or connected health) refers to the use of information and communication technologies (ICTs) in various healthcare-related activities, patient populations, healthcare providers, and medical systems. E-health also encompasses a set of digital applications aimed at disease diagnosis, prevention, and treatment that expected to provide more precise, real-time solutions aimed at overcoming challenges in modern medicine, particularly addressing the increasing burden of chronic diseases (cancer, drug discovery, heart failure, Covid-19, etc.) and aging patient populations. E-health also opens potential for real-time personalized interaction between patients and physicians, disease surveillance, resource management, and targeted treatment strategies (e.g., precision health). AI can be applied at multiple levels, from disease prevention to diagnoses, therapeutic surveillance, and medical research. By leveraging AI and Big Data in medicine, we may identify previously unknown links to underlying biological and pathological mechanisms of various diseases.

In this context, a key to success in the future medicine lies in Big Data for clinical decision support, incorporating topics such as predictive and preventive medicine, aimed at disease prevention as well as personalized and participatory medicine that promotes dynamic patient–physician–systems interactions. This will lead to more precise disease diagnosis, treatment, and new adaptations as diseases evolve or recur. Internet of Medical Things (IoMT), connected to cloud platforms for data storage, management, and analysis, will optimize the electronic health record (EHR) and enable globalization of telemedicine. This rise in digital healthcare data does raise concern for the security and privacy of patient and provider information. Here, AI, including Blockchain technologies, may also play a key role for preserving privacy, security maintenance, as well as neutralizing malicious activities in real time. Unlike a centralized system with inherent vulnerabilities for hacking or healthcare data leaks, a blockchain strategy may provide an honest broker to allow for safe data exchange, new approaches for data encryption for added security of sensitive data, auditability, and secure healthcare transactions. In recent years, the combined use of (IoT) and blockchain technologies has led to initiatives such as blockchain of IoMT (BIOMT) for improved security whereby (1) data does not pass through a cloud but sent directly to service platform; (2) hacking entry points are drastically reduced; (3) medical data are dematerialized, saving time; and (4) medical transactions occur with higher security and transparency.

Table of contents :

Introduction
Contents
About the Editors
1 AI and Big Data for Intelligent Health: Promise and Potential
1 Introduction
2 Artificial Intelligence
2.1 Machine Learning
3 Big Data
4 AI and Big Data in Healthcare
4.1 Core Messages
4.2 Short Expert Opinion
References
2 AI and Big Data for Cancer Segmentation, Detection and Prevention
1 Introduction
1.1 Big Data and Artificial Intelligence (AI)
1.2 Cancer Image Segmentation
1.3 Cancer Detection
1.4 Protein Structure Prediction
1.5 Cancer Prevention
2 Conclusions
References
3 Radiology, AI and Big Data: Challenges and Opportunities for Medical Imaging
1 Introduction
2 AI and Radiology
3 Radiology and Big Data Industry for Medical Imaging
3.1 Technologies and Tools
Case Example (RadMonitor, BigDataBench)
3.2 Radiology for Data Mining Radiology and Storage
3.3 Radiology and Dark Data Exploration
4 Radiology and Machine Learning
4.1 Explainable Artificial Intelligence (XIA) for Radiology
4.2 Artificial Intelligence of Things (AIoT) (AIOT) for Radiology
5 Conclusion
References
4 Neuroradiology: Current Status and Future Prospects
1 Introduction
2 AI in Neuroradiology
2.1 Overview of Articles and Main CNS Subjects
2.2 A Systematic Review of Applications Already Available
2.3 Main Review Articles Published
3 Conclusion
References
5 Big Data and AI in Cardiac Imaging
1 Introduction
2 Data Management
3 Algorithm Design
4 Validation and Implementation
5 Implementation in Cardiac Imaging
5.1 Echocardiography
5.2 Cardiac Magnetic Resonance Imaging
5.3 CT
6 Nuclear Medicine
7 Challenges and Pitfalls
8 Future Directions
References
6 Artificial Intelligence and Big Data for COVID-19 Diagnosis
1 Introduction
2 COVID-19 Therapy and Health Informatics: Promises and Challenges
3 COVID-19 Infrastructures and Technological Solutions
4 The Post-COVID-19 Era and e-Health
5 Medical Digital Transformation by the COVID-19 Pandemic
6 Artificial Intelligence (AI) and Supply IT Infrastructure During COVID-19
6.1 Classification for COVID-19
6.2 Segmentation for COVID-19
6.3 COVID-19 Risk Assessment and Prognosis
7 Big Data Management and IT Infrastructure During COVID-19
8 Conclusion
References
7 AI and Big Data for Drug Discovery
1 Introduction
2 Big Data in Drug Discovery
3 From Machine Learning to Deep Learning: AI Milestone
4 Recent Novel Targets by AI
4.1 PaccMann
4.2 INtERAcT
4.3 PIMKL
5 Deep Neural Networks
6 AI in 3D‑Pharmacophore Models
7 AI and Gene Profiling Analysis
8 AI and Drug Screening
9 AI and Drug Delivery
10 AI in Clinical Trials
11 Conclusions
References
8 Blockchain Technologies for Internet of Medical Things (BIoMT) Based Healthcare Systems: A New Paradigm for COVID-19 Pandemic
1 Introduction
2 IoMT Concept for COVID-19
3 Artificial Intelligence and Big Data Technology in IoMT for Covid-19 Management
4 Blockchain Concept for COVID-19
5 HealthBlock: A Secure Blockchain-Based Healthcare Data Management System
6 IOMT and Supply Chain for Covid-19 Patient Integration: Towards Chain of Medical Things (COMT)
7 Blockchain IoMT (BIoMT): A New Paradigm for Healthcare Security and Issues Related to the Internet of Things
8 Conclusion
References
9 AI and Big Data for Therapeutic Strategies in Psychiatry
1 Introduction
2 Artificial Intelligence in Psychiatric Disease
2.1 Machine Learning for Psychiatric Diseases
2.2 Opportunities
2.3 Challenges
2.4 Deep Learning Models for Psychiatric Disorders
3 Big Data in Psychiatry
3.1 Challenges of Big Data in Psychology
3.2 Opportunities of Big Data in Psychiatry
4 Datasets and Tools
5 Usage of AI Models in Psychiatry
6 Conclusions
References
10 Distributed Learning in Healthcare
1 Introduction
1.1 Caveats of Central Learning
1.2 Motivation for Distributed Learning
2 Distributed Learning Methods
2.1 Global Ensemble
2.2 Parameter Aggregation
2.3 Traveling Model
2.4 Split Learning
3 Challenges and Considerations
3.1 Heterogenous Data Distributions
3.2 Computational and Communication Costs
3.3 Privacy and Security
3.4 Model Interpretability and Fairness
4 Outlook
5 Core Messages
Acknowledgements
References
11 Cybersecurity in Healthcare
1 Introduction
2 Introduction to Health Information Technology (HIT)
2.1 The Electronic Health Record
2.2 Complicating Factors
2.3 Data
2.4 Trends
2.5 Health Information Technology
3 Regulatory Compliance and Standards
3.1 HIPAA
3.2 GDPR
3.3 Compliance
3.4 Security Controls
3.5 De-identification
3.6 Transfer
3.7 Devices
3.8 Labelling
4 Information Security and Data Privacy
4.1 Software Development
4.2 Third Parties
4.3 Privacy
4.4 Transformation
4.5 Industry Standards
4.6 Ethics
5 Hardware and Software-Based Security Models
5.1 Legacy Software
5.2 Identity Management
5.3 Network Security
5.4 Audit and Logging
5.5 Solutions
Distributed Privacy
Federated Learning
6 Security and Privacy Implications of Artificial Intelligence
6.1 Languages and Platforms
6.2 Testing
6.3 Implementation
7 Conclusion
References
12 Radiology and Radiomics: Towards Oncology Prediction with IA and Big Data
1 Introduction
2 Big Data for Oncology Management
3 Areas of Radiomics/Radiogenomics
4 Neuroradiology Applications
5 Breast Imaging Applications
6 Lung Imaging Applications
7 Gastrointestinal Tract Imaging Applications
8 Radiotherapy Implications
9 Conclusion
References
General Conclusion