Artificial Intelligence for Health 4.0: Challenges and Applications

Description:

Healthcare is one of the major success stories of our times. Medical science has improved rapidly, raising life expectancy around the world. However, as longevity increases, healthcare systems face growing demands for their services, rising costs, and a workforce that is struggling to meet the needs of its patients. Healthcare is one of the most critical sectors in the broader landscape of big data because of its fundamental role in a productive, thriving society. Building on automation, artificial intelligence (AI) has the potential to revolutionize healthcare and help address some of the challenges set out above. The application of AI to healthcare data can literally be a matter of life and death. AI can assist doctors, nurses, and other healthcare workers in their daily work. AI in healthcare can enhance preventive care and quality of life, produce more accurate diagnoses and treatment plans, and lead to better patient outcomes overall. This book gives insights into the latest developments of applications of AI in biomedicine, including disease diagnostics, pharmaceutical processing, patient care and monitoring, biomedical information, and biomedical research. It also presents an outline of the recent breakthroughs in the application of AI in healthcare, describes a roadmap to building effective, reliable, and safe AI systems, and discusses the possible future direction of AI augmented healthcare systems. AI has countless applications in healthcare. Whether it’s being used to discover links between genetic codes, to power surgical robots or even to maximize hospital efficiency; AI has been a boon to the healthcare industry.

Table of contents :

Cover
Title Page
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Acknowledgment
List of Contributors
List of Figures
List of Tables
List of Abbreviations
Chapter 1: Healthcare 4.0: A Systematic Review and Its Impact Over Conventional Healthcare System
1.1: Introduction
1.1.1: Application scenarios of healthcare 4.0
1.1.2: The architecture of healthcare 4.0
1.1.3: Requirements and characteristics of healthcare 4.0
1.2: Evolution of Healthcare
1.3: Need of Healthcare 5.0
1.4: Advances in the Healthcare Industry
1.4.1: M-Healthcare
1.4.2: Healthcare data of patients
1.4.3: IoT and healthcare
1.4.4: Blockchain technology and healthcare
1.4.5: Big data analytics and healthcare
1.5: Telemedicine Services
1.5.1: Big data and IoT for healthcare 4.0
1.5.2: Blockchain and healthcare 4.0
1.5.3: AI and healthcare 4.0
1.5.4: Cyber–physical system and healthcare 4.0
1.5.5: Smart medical devices
1.6: Opportunities and Challenges Involved in Healthcare
1.7: Future Scope and Trends
1.8: Conclusion
1.9: Acknowledgment
1.10: Funding
1.11: Conflict of Interest
References
Chapter 2: Data Imaging, Clinical Studies, and Disease Diagnosis using Artificial Intelligence in Healthcare
2.1: Introduction
2.1.1: Classifications of artificial intelligence
2.1.1.1: Machine learning: Deep learning and neural network
2.1.1.2: Rule-based expert systems
2.1.1.3: Physical robots and software robotics
2.2: Machine Learning for Typical Biomedical Data Types
2.2.1: Data from multiple omics
2.2.2: Integration based on data
2.2.3: Incorporating models
2.2.4: Data on behavior
2.2.5: Data from video and conversations
2.2.6: Mobile sensor data
2.2.7: Data on the environment
2.2.8: Pharmaceutical research and development data
2.2.8.1: Chemical compounds
2.2.8.2: Clinical trials
2.2.9: Unintentional reports
2.2.10: Literature in biomedicine data
2.3: Application of AI
2.3.1: Biomedical information processing
2.3.2: AI for living support
2.3.3: Biomedical research
2.3.4: Medicine
2.3.5: Cancer and miscellaneous
2.4: Assessment of AI Applications in Healthcare
2.4.1: Phase 0
2.4.2: Phase 1
2.4.3: Phase 2
2.4.4: Phase 3
2.4.5: Phase 4
2.5: Artificial Intelligence’s Challenges in the Use of Pharmaceutical R&D Data
2.6: Future Directions for AI in Healthcare
2.6.1: Analytical integration
2.6.2: Transparency in models
2.6.3: Model security
2.6.4: Learning that is federated
2.6.5: Data errors
2.7: Conclusion
2.8: Acknowledgment
2.9: Funding
2.10: Conflicts of Interest
References
Chapter 3: Leveraging Artificial Intelligence in Patient Care
3.1: Introduction
3.2: Advancement in Artificial Intelligence
3.2.1: AI spring: artificial intelligence’s inception
3.2.2: AI summer and winter: Artificial intelligence’s highs and lows
3.2.3: AI’s fall: The harvest
3.2.4: The future: The importance of regulation
3.3: Artificial Intelligence’s Health Benefits
3.3.1: Advantages
3.4: Application
3.4.1: Cardiology
3.4.2: Applications of artificial intelligence in the medical field
3.4.3: Image and disease diagnosis using artificial intelligence
3.5: Recent Advancements in the Field of Artificial Intelligence
3.5.1: For medical imaging, the use of artificial intelligence is essential
3.5.2: Artificial intelligence science and technology
3.6: Artificial Intelligence and its Applications in Diagnostics
3.6.1: Sets of data
3.6.2: A medical image’s preprocessing
3.6.3: Optimization of models and parameters based on improved data
3.6.4: The principal component analysis (PCA)
3.6.5: Analyzing medical images using artificial intelligence
3.6.6: Imaging the brain via artificial intelligence
3.6.7: Chest imaging with artificial intelligence
3.6.8: In breast imaging, artificial intelligence is being used
3.6.9: The use of AI in cardiac imaging
3.6.10: Artificial intelligence in bone imaging
3.6.11: The use of Artificial Intelligence (AI) in stroke imaging
3.6.12: Using AI to treat diseases of the lungs
3.6.13: Artificial intelligence in the treatment of cancer
3.7: Conclusion
3.8: Acknowledgment
3.9: Funding
3.10: Conflicts of Interest
References
Chapter 4: Patient Monitoring Through Artificial Intelligence
4.1: Introduction
4.2: Purpose of Patient Monitoring
4.2.1: Patient monitoring involvement in today’s healthcare
4.2.2: Improving healthcare outcomes by using patient monitoring
4.3: Wearable Patient Monitoring Sensors
4.3.1: Wireless health monitoring specifications
4.3.2: Different types of sensors
4.4: Involvement of AI in Patient-Monitoring
4.4.1: Mobility aids the living environment
4.4.2: Clinical decision-making assistance
4.4.3: Smartphones, apps, sensors, and devices
4.4.4: Processing of text language
4.4.5: Healthcare applications of text processing technology
4.4.6: Using consumer technology to its full potential
4.4.7: AI’s function in diabetes forecasts and management
4.4.7.1: Apps and technologies for diabetes monitoring
4.5: AI-Assisted Monitoring of the Heart
4.5.1: AI in cardiology with virtual applications
4.5.2: Supporting system in clinical decisions
4.5.3: Augmented reality (AR), virtual reality (VR), and virtual assistants
4.5.4: Automated analysis with data
4.6: Neural Applications Linked to AI and Patient Monitoring
4.6.1: AI for dementia patients
4.6.2: Dementia monitoring
4.6.3: Supporting dementia patients
4.7: AI for Migraine Patients
4.8: Conclusion
4.9: Acknowledgment
4.10: Funding
4.11: Conflict of Interest
References
Chapter 5: Artificial Intelligence: A Promising Approach Toward Targeted Drug Therapy in Cancer Treatment
5.1: Introduction
5.2: AI, Machine Learning, and Deep Learning
5.3: Drug Development Process
5.3.1: Role of AI in chemotherapy
5.3.2: Role of AI in radiotherapy
5.3.3: Role of AI in cancer drug development
5.3.4: Role of AI in immunotherapy
5.4: Monoclonal Antibodies (mAbs) used in Cancer Treatment
5.5: MOA of mAbs
5.6: Future Prospects
5.7: Conclusion
5.8: Acknowledgment
5.9: Funding
5.10: Conflicts of Interest
References
Chapter 6: Artificial-Intelligence-Based Cloud Computing Techniques for Patient Data Management
6.1: Introduction of Artificial Intelligence Based Cloud Computing Techniques
6.2: Cloud Computing: A New Economic Computing Model
6.2.1: Infrastructure as a service (IaaS)
6.2.2: Platform as a service (PaaS)
6.2.3: Software as a service (SaaS)
6.3: The US National Institute of Standards and Technology (NIST) has Identified four Models for Cloud Computing Deployment
6.3.1: Public cloud
6.3.2: Community cloud
6.3.3: Private cloud
6.3.4: Hybrid cloud
6.4: Cloud Computing from the Perspective of Management, Security, Technology, and Legality
6.4.1: Management aspect
6.4.2: Technology aspect
6.4.3: Security aspect
6.4.4: Legal aspect
6.5: Cloud Computing Strategic Planning
6.5.1: Stage I – Identification
6.5.2: Stage II – Evaluation
6.5.3: Stage III – Action
6.5.3.1: Step 1: Determination of cloud service and deployment model
6.5.3.2: Step 2: Obtain confirmation from a chosen cloud provider
6.5.3.3: Step 3: Take consideration in migration of future data
6.5.3.4: Step 4: Start of implementation of pilot
6.5.4: Stage IV – Follow-up
6.6: Cloud Computing Research Utilization in Healthcare
6.6.1: Cloud computing in telemedicine/teleconsultation
6.6.2: Cloud computing in public health and patient self-management
6.6.3: Cloud computing in hospital management/clinical information systems
6.6.4: Cloud computing in therapy
6.6.5: Cloud computing in secondary use of data
6.7: Conclusion
6.8: Acknowledgment
6.9: Funding
6.10: Conflict of Interest
References
Chapter 7: Role of Artificial Intelligence and Robotics in Healthcare
7.1: Introduction
7.1.1: History of artificial intelligence
7.1.2: The need for AI
7.1.3: How did AI change the way medicine was practiced in the past?
7.1.4: Types of AI
7.2: AI in Healthcare
7.2.1: AI tool
7.2.2: Natural language processing
7.2.3: Machine learning
7.2.4: Algorithms
7.2.5: Artificial neural network
7.2.6: Support vector machine
7.2.7: Deep learning
7.3: Integrating AI into Healthcare Delivery
7.3.1: Patient monitoring
7.3.2: Disease diagnostics and prediction
7.3.3: Precision medicine
7.3.4: Drug discovery
7.3.5: Dermatology
7.3.6: Coronavirus
7.3.7: AI in ophthalmology
7.3.8: Design of the treatment
7.4: The Present State of AI and Its Future
7.4.1: Benefits
7.4.2: Difficulties of AI in healthcare
7.5: Role of Robotics in Modern Healthcare
7.5.1: Drug research and development
7.5.2: Dispensing in pharmacies
7.5.3: Logistics at the hospital
7.6: Robotic Healthcare Is More Advance than Conventional Dispensing
7.6.1: Increased effectiveness
7.6.2: Medical dispensing in an error-free environment
7.6.3: Pharmaceutical operations efficiency
7.6.4: Confidentiality
7.6.5: A toxin-free and secure setting
7.6.6: Advantages of robotics in healthcare systems
7.7: Acceptance and Implementation of Robots in the Healthcare Business
7.8: AI Robotics Emerging Together to Transform the Healthcare System
7.8.1: Error rates reduction
7.8.2: Improving the health of patients
7.8.3: Early detection
7.8.4: Improving decision-making
7.8.5: Research and development
7.8.6: Treatment
7.8.7: End-of-life care regeneration
7.9: Categories of AI Robotic Systems used in the Healthcare System
7.9.1: Assistants to surgeons
7.9.2: Pharmabiotics
7.9.3: Telehealthcare
7.9.4: Robotics with exoskeletons
7.9.5: Robots for cleaning and decontamination
7.10: Robotic Programming
7.11: Conclusion
7.12: Acknowledgment
7.13: Funding
7.14: Conflict of Interest
References
Chapter 8: Artificial Intelligence and Machine Learning Approach for Development and Discovery of Drug
8.1: Introduction
8.2: Tools of AI used to Emphasize Pharmacy
8.2.1: The robot pharmacy
8.2.2: The MEDi robot
8.2.3: The erica robot
8.2.4: The TUG robots
8.3: Applications
8.3.1: Modifying drug release
8.3.2: Product development
8.4: Benefits
8.5: AI-Integrated Medicine Development
8.6: Role of Active Learning and Machine Learning in Drug Discovery
8.7: Explainable AI
8.8: Computational Approaches for Explainable AI
8.8.1: Feature attribution
8.8.2: Instance-based approach
8.8.3: Graph convolution-based approach
8.8.4: Self-explaining
8.8.5: Uncertainty estimation
8.8.6: In silico molecular modeling
8.9: AI Networks and Associated Tools
8.9.1: AlphaFold
8.9.2: DeepChem
8.9.3: ODDT
8.9.4: Cyclica
8.9.5: DeepTox
8.9.6: Deep neural net QSAR
8.9.7: Organic
8.9.8: PotentialNet
8.9.10: Hit dexter
8.10: Technical Obstacles and Prospects
8.11: Conclusion
8.12: Acknowledgment
8.13: Funding
8.14: Conflicts of Interest
References
Chapter 9: Artificial Intelligence in Boosting the Development of Drug
9.1: Artificial Intelligence
9.2: Computer-Based Intelligence in the Lifecycle of Drug Items
9.3: Drug Development
9.4: The Drug Development Process
9.5: In Drug Discovery, Artificial Intelligence
9.6: Artificial Intelligence in Drug Screening
9.6.1: The expectation of the physicochemical properties
9.6.2: Forecast of bioactivity
9.6.3: Expectation of poisonousness
9.7: Artificial Intelligence in Planning Drug Particles
9.7.1: The expectation of the objective protein structure
9.7.2: Foreseeing drug-protein communications
9.8: Artificial Intelligence in Propelling Drug Item Advancement
9.9: Artificial Intelligence in Drug Fabricating
9.10: Artificial Intelligence in Quality Assurance and Control
9.11: Artificial Intelligence in a Clinical Trial Plan
9.12: Artificial Intelligence in Drug Item Execution
9.12.1: Artificial intelligence in market situating
9.12.2: Artificial intelligence in market expectation and investigation
9.13: Artificial Intelligence in the Item Cost
9.14: Conclusion
9.15: Acknowledgment
9.16: Funding
9.17: Conflict of Interest
References
Chapter 10: Artificial Intelligence in Medical Image Processing
10.1: Introduction
10.2: Magnetic Resonance Imaging (MRI)
10.2.1: Alzheimer’s disease (AD)
10.2.2: Skeletal issues
10.2.3: Brain illness diagnosis
10.2.4: Cancer and other disease analysis
10.3: Radiography-Based COVID-19 Diagnosis
10.3.1: ML-based approach
10.3.2: DNN algorithms for diagnosis
10.3.2.1: DNN and chest CT scan
10.3.2.2: DNN and chest X-ray
10.3.2.3: New DNN models on chest CT scan
10.3.2.4: New DNN models on chest X-ray
10.3.3: Transfer learning (TL) approach
10.3.3.1: Implementing TL approach on chest CT scan
10.3.3.2: Implementing TL approach on chest X-ray
10.3.3.3: Smartphone apps
10.4: Echocardiogram Analysis and Classification using AI
10.5: AI-Based Ultrasound Imaging Analysis
10.6: Conclusion
10.7: Acknowledgment
10.8: Funding
10.9: Conflict of Interest
References
Chapter 11: Advancement of AI in Cancer Management: Role of Big Data
11.1: Introduction
11.1.1: Big data
11.2: The Source and Type of Big Data, and Their Concern
11.2.1: The challenge of big data
11.3: Big Data Sources and Platforms
11.3.1: The national population-based cancer database
11.3.2: Commercial and private cancer databases
11.3.3: Cancer biological science and various “Omic” databases
11.4: Data Collection in Big Data for Oncology Treatment
11.4.1: Data management and aggregation in big data
11.4.2: The data sources for big data in medicine
11.5: Therapy Plan for Cancer
11.5.1: Big data will aid in the development of novel cancer therapies
11.5.2: A cancer treatment plan that is tailored to each patient
11.6: Big Data Powers the Design of “Smart” Cell Therapies for Cancer
11.6.1: Instructions are inserted into the cells
11.7: Future and Challenges of Big Data in Oncology
11.7.1: Challenges
11.8: Perspectives for the Future
11.9: Conclusion
11.10: Acknowledgment
11.11: Funding
11.12: Conflict of Interest
References
Chapter 12: Targeted Drug Delivery in Cancer Tissues by Utilizing Big Data Analytics: Promising Approach of AI
12.1: Introduction
12.2: Tools and Techniques for Targeted Drug Discovery and Delivery
12.2.1: Data sources available for drug discovery
12.2.2: Anticancer drug target discovery and validation
12.3: Sources of Big Data in Drug Discovery and Delivery
12.3.1: COSMIC-3D
12.3.2: The cancer genomic atlas
12.3.3: Gene expression omnibus (GEO)
12.3.4: Human protein atlas
12.4: Big Data Analytics
12.5: Future Prospects of “Big Data Analytics”
12.6: Challenges in the Field of “Big Data Analytics”
12.7: Conclusion
12.8: Acknowledgment
12.9: Funding
12.10: Conflict of Interest
References
Index
About the Authors
About the Editors