The Internet of Medical Things: Enabling technologies and emerging applications

by Gianluigi Ferrari, Henry Wang, Priyadarsan Patra, Radoslava Kraleva, Subhendu Kumar Pani

Length: 400 pages
Edition: 1
Language: English
Publisher: The Institution of Engineering and Technology
Publication Date: 2022-02-26
ISBN-10: 1839532734
ISBN-13: 9781839532733
Sales Rank: #0 (See Top 100 Books)

The Internet of Medical Things (IoMT) allows clinicians to monitor patients remotely via a network of wearable or implantable devices. The devices are embedded with software or sensors to enable them to send and receive data via the internet so that healthcare professionals can monitor health data such as vital statistics, metabolic rates or drug delivery regimens, and can provide advice or treatment plans based on this real-world, real-time data. This edited book discusses key IoT technologies that facilitate and enhance this process, such as computer algorithms, network architecture, wireless communications, and network security.

Providing a systemic review of trends, challenges and future directions of IoMT technologies, the book examines applications such as breast cancer monitoring systems, patient-centric systems for handling, tracking and monitoring virus variants, and video-based solutions for monitoring babies. The book discusses machine learning techniques for the management of clinical data and includes security issues such as the use of blockchain technology.

Written by a range of international researchers, this book is a great resource for computer engineering researchers and practitioners in the fields of data mining, machine learning, artificial intelligence and the IoT in the healthcare sector.

Cover
Title
Copyright
Contents
About the editors
Chapter 1 Internet of medical things (IoMT): a systematic review of applications, trends, challenges, and future directions
    1.1 Introduction
        1.1.1 Internet of medical things
    1.2 Internet of medical things (IoMT) applications
        1.2.1 Role of IoMT during COVID-19
    1.3 Security aspects in IoMT
    1.4 Challenges and future directions
    1.5 Conclusion
    References
Chapter 2 Non-invasive psycho-physiological driver monitoring through IoT-oriented systems
    2.1 Introduction
    2.2 Heterogeneous driver monitoring
        2.2.1 Wearable and inertial sensors
        2.2.2 Camera sensors
    2.3 In-vehicle IoT-oriented monitoring architecture
        2.3.1 Experimental setup
        2.3.2 HRV analysis
    2.4 Experimental performance evaluation
        2.4.1 Operating protocol for data collection
        2.4.2 HR and HRV data
        2.4.3 Experimental results
    2.5 Conclusions and future works
    Acknowledgments
    References
Chapter 3 IoT-based biomedical healthcare approach
    3.1 Introduction
    3.2 IoT-based healthcare biomedical applications
    3.3 IoT-based biomedical communication architecture
    3.4 Wireless body area networks
    3.5 RFID IoT-based biomedical communication protocol
    3.6 Problem statement
    3.7 IoT and biomedical healthcare system interconnection
    3.8 Examples of IoT-based biomedical healthcare devices
        3.8.1 Glucose monitoring
        3.8.2 Bluetooth-enabled blood labs
        3.8.3 Connected inhalers
        3.8.4 Blood coagulation testing
        3.8.5 Connected cancer treatment
        3.8.6 Robotic surgery
        3.8.7 IoT-connected contact lenses
        3.8.8 A smartwatch app that monitors depression
        3.8.9 Connected wearables
    3.9 A summary of associated research
    3.10 Conclusion
    3.11 Future work
    References
Chapter 4 Impact of world pandemic “COVID-19” and an assessment of world health management and economics
    4.1 Introduction
    4.2 Impact on societies
        4.2.1 Impact of social manner on COVID-19
        4.2.2 Impact on healthcare facilities
        4.2.3 Worldwide impact
        4.2.4 Impact on low- and moderate-income countries
        4.2.5 Impact on international healthcare facilities based on medical services
        4.2.6 Emergency caring
        4.2.7 Constructive response reduction strategies
    4.3 Impact of health on the emerging COVID-19 pandemic
        4.3.1 Social determinants of health
    4.4 Health in the clinical system
        4.4.1 Clinical knowledge
        4.4.2 Access to medical- and primary-care doctor
    4.5 Role of health disease
        4.5.1 Food deserts on cardiovascular disease (CVD)
        4.5.2 Role of food deserts on hypertension and chronic kidney disease
        4.5.3 Role of SDOH on obesity
    4.6 Social setting
        4.6.1 Determination
        4.6.2 Active part of the community
        4.6.3 Make surrounding foods
    4.7 Academy
        4.7.1 High school graduation
        4.7.2 Psycholinguistics and literacy
    4.8 Stable, predictable employment
    4.9 The impact of the COVID-19 pandemic on firms
        4.9.1 Time-saving method
        4.9.2 Data gathering
        4.9.3 Computations and statistical review
        4.9.4 Statistical results
    4.10 Healthcare, social and economic challenges in Bangladesh
        4.10.1 Methodology
        4.10.2 Analysis of basic healthcare
        4.10.3 Precarious living
        4.10.4 Social distancing
        4.10.5 Groups with special needs
        4.10.6 Discussion
    4.11 Conclusions
    References
Chapter 5 Artificial intelligence in healthcare
    5.1 Introduction
    5.2 Healthcare data sources
    5.3 Legal and ethical obstacles of artificial intelligence-driven healthcare
    5.4 Types of healthcare data
        5.4.1 Structured data
        5.4.2 Unstructured data
    5.5 AI techniques developed for structured and unstructured data
        5.5.1 Machine learning
        5.5.2 Neural networks
        5.5.3 Natural language processing
    5.6 Major disease areas
    5.7 Applications of AI in healthcare system
        5.7.1 Solutions based on genetics
        5.7.2 Development and discovery of drug
        5.7.3 Support in clinical decisions
        5.7.4 Robotics and artificial intelligence-powered devices
    5.8 Examples of AI used in healthcare
    References
Chapter 6 Blockchain in IoT healthcare: case study
    6.1 Overview
    6.2 Existing models to secure IoT healthcare
    6.3 Blockchain to secure IoT healthcare
        6.3.1 Proposed system
        6.3.2 System implementation
    6.4 Conclusions
    References
Chapter 7 Adaptive dictionary-based fusion of multi-modal images for health care applications
    7.1 Introduction
    7.2 Learning a dictionary
    7.3 Experimental setup and analysis
    7.4 Overview of fusion scheme
    7.5 Simulation results and discussion
        7.5.1 Results on standard multimodal medical data sets
        7.5.2 Objective analysis of standard medical image pairs
    7.6 Summary
    References
Chapter 8 Artificial intelligence for sustainable e-Health
    8.1 Introduction
    8.2 Reduction in margin of error in healthcare
    8.3 EPRs, EHRs, and clinical systems
    8.4 Barriers in an EHR system
    8.5 Getting over interoperability issues
    8.6 Barriers in EHR interoperability
    8.7 UK-NHS model: characteristics and enhancements
    8.8 MNC/MNE characteristics
    8.9 UK-NHS model or the MNC organizational model
    8.10 e-Health and AI
    8.11 Sustainable healthcare
    8.12 Sustainable healthcare in the aftermath of COVID-19
    8.13 Sustainability in staff and clinical practice during pandemic
    8.14 Broadening health-care facilities at home during the COVID-19 pandemic
    8.15 Sustainable development groups
    8.16 Futuristic research directions
    8.17 Role of AI in diabetes care—a case study
    8.18 Artificial intelligence and its area of applications
        8.18.1 Diagnosis
        8.18.2 Interpretation
        8.18.3 Monitoring
        8.18.4 Control
        8.18.5 Treatment planning
        8.18.6 Drug design
    8.19 Conclusion
    References
Chapter 9 An innovative IoT-based breast cancer monitoring system with the aid of machine learning approach
    9.1 Introduction
    9.2 Related works
    9.3 Proposed solution
        9.3.1 Concept of iTBra
        9.3.2 Dataset
        9.3.3 Feature ranking with support vector machines
        9.3.4 SMO algorithm
        9.3.5 Reforms of the SMO algorithm
        9.3.6 Breast cancer prediction proposed predictive framework
    9.4 Study and discussion of experimental findings
        9.4.1 Preprocessing for the dataset
        9.4.2 Results of SVM-RFE experiment
        9.4.3 Results of SMO classification
    9.5 Conclusion
    References
Chapter 10 Patient-centric smart health-care systems for handling COVID-19 variants and future pandemics: technological review, research challenges, and future directions
    10.1 Introduction
    10.2 Internet of Things (IoT) network for patient-centric health-care system
        10.2.1 IoT and its applications for health-care sector
        10.2.2 Industrial IoT (IIoT) for smart health-care system
        10.2.3 Resourceful and resource constraint device-based smart health-care developments
        10.2.4 Research challenges and future direction of IoT in patient-centric smart health-care system
    10.3 Blockchain technology and IoT for patient-centric health-care system
        10.3.1 Need for the blockchain and IoT integration
        10.3.2 Role of Internet of Things in health-care system
    10.4 Cybersecurity and IoT for patient-centric health-care system
        10.4.1 IoT and cybersecurity
        10.4.2 Recent developments in ensuring confidentiality, integrity, and availability (CIA) properties in IoT networks for smart health-care system
        10.4.3 IoT cyberspace and data handling processes for information and network security
        10.4.4 Research challenges and future direction of IoT in patient centric smart health-care system
    10.5 Parallel and distributed computing architecture using IoT network for patient-centric health-care system
        10.5.1 Cloud computing architectures using IoT network for health-care system
    10.6 Artificial intelligence and machine learning approaches in IoT for smart health-care system
        10.6.1 Healthcare, COVID-19, and future pandemic-related datasets for smart health-care systems
        10.6.2 Artificial intelligence in smart health-care system
        10.6.3 Machine learning aspects in smart health-care system
    10.7 Virtualization and IoT in IoT for smart health-care system
        10.7.1 Operating system and storage virtualization for desktop- and mobile-based smart health-care applications
    10.8 IoT and quantum computing for smart health-care system
        10.8.1 Introduction to IoT and quantum computing
        10.8.2 Quantum computing and smart health-care system
        10.8.3 Challenges of quantum computing to health-care data and data security
    10.9 Post-quantum cryptography solutions for futuristic security in smart health-care system
        10.9.1 Code-based cryptography for health-care data and system
        10.9.2 Lattice-based cryptography for health-care data and system
        10.9.3 Hash-based cryptography for health-care data and system
        10.9.4 Multivariate cryptography for health-care data and system
        10.9.5 Supersingular cryptography for health-care data and system
        10.9.6 Post-quantum cryptography application and research challenges for smart health-care system
    10.10 Drone and robotics operation management using IoT network for smart health-care system
        10.10.1 Medical robots and recent developments
        10.10.2 Drone and IoT network for health-care operations
        10.10.3 Robot, drone, and IoT network integrations for health-care applications
        10.10.4 Recent developments and future directions
    10.11 Conclusion and future scope
    References
Chapter 11 Application of intelligent techniques in health-care sector
    11.1 Introduction
    11.2 Evolution of AI in health-care informatics
    11.3 Healthcare in India
    11.4 Health-care dataset
        11.4.1 Electronic medical records
        11.4.2 Reluctant to adopt EMR/digitalization of medical procedures
    11.5 AI in healthcare
        11.5.1 What could be achieved using AI in healthcare?
        11.5.2 Challenges of using AI and possible solutions
        11.5.3 Future scope
        11.5.4 Current status of AI in healthcare
    References
Chapter 12 Managing clinical data using machine learning techniques
    12.1 Introduction
    12.2 Related work
    12.3 Clinical data analysis
        12.3.1 Dataset 1
        12.3.2 Dataset 2
        12.3.3 Dataset 3
        12.3.4 Dataset 4
    12.4 Conclusion
    References
Chapter 13 Use of IoT and mobile technology in virus outbreak tracking and monitoring
    13.1 Introduction
    13.2 IoT in healthcare
    13.3 IoT health-care applications
        13.3.1 Glucose level sensing
        13.3.2 Electrocardiogram monitoring
        13.3.3 Blood pressure monitoring
        13.3.4 Blood temperature monitoring
        13.3.5 Oxygen saturation monitoring
        13.3.6 Rehabilitation system
        13.3.7 Medication management
        13.3.8 Wheelchair management
        13.3.9 Imminent health-care solutions
        13.3.10 Health-care solutions using smartphones
    13.4 Benefits
        13.4.1 Simultaneous reporting and monitoring
        13.4.2 Data assortment and analysis
        13.4.3 Tracking and alerts
    13.5 Challenges
        13.5.1 Data security and privacy
        13.5.2 Cost
        13.5.3 Data overload and accuracy
    13.6 Use of IoT in virus outbreak and monitoring
        13.6.1 Using IoT to dissect an outbreak
        13.6.2 Using IoT to manage patient care
    13.7 Use of mobile apps in healthcare
        13.7.1 Mobile report
        13.7.2 Saving human resources
    13.8 Healthcare IoT for virus pandemic management
    13.9 Evolution of healthcare (pandemic)-based IoT
    13.10 Increase availability of social networks
        13.10.1 Improve efficiency of health services
        13.10.2 Improve patients health condition
        13.10.3 Enhances physician efficiency
    13.11 Data privacy and security is a significant concern
        13.11.1 Lack of information control
        13.11.2 Digital divide among patients
    13.12 Conclusion
    Further reading
Chapter 14 Video-based solutions for newborn monitoring
    14.1 Introduction
    14.2 Vital signs monitoring
    14.3 Video processing systems for neonatal disorder detection
        14.3.1 Single sensor
        14.3.2 Multiple sensors
    14.4 Seizure detection
        14.4.1 Performance in seizure detection
    14.5 Apnea detection
        14.5.1 Performance in apnea detection
    14.6 Conclusion
    References
Chapter 15 IoT sensor networks in healthcare
    List of abbreviations
    15.1 Introduction
    15.2 Wireless sensor networks (WSN) and Internet of Things (IoT)
    15.3 Role of Internet of Things (IoT) sensor networks in healthcare
    15.4 Communication technologies for health-care IoT sensor networks
    15.5 Challenges in the implementation of H-IoT and related research
    15.6 Contemporary technologies to overcome the challenges on IoT sensor networks for healthcare
        15.6.1 Cloud/fog/edge computing for H-IoT sensor networks
        15.6.2 Software-defined networking for H-IoT sensor networks
    15.7 Conclusion
    References
Chapter 16 Machine learning for Healthcare 4.0: technologies, algorithms, vulnerabilities, and proposed solutions
    16.1 Introduction
    16.2 Healthcare 4.0
        16.2.1 Main technologies of Healthcare 4.0
        16.2.2 Health 4.0 objective
        16.2.3 Health 4.0 application
    16.3 Machine learning algorithms
        16.3.1 Linear regression
        16.3.2 Logistic regression
        16.3.3 Support vector machines
        16.3.4 Artificial neural network
        16.3.5 Decision tree
        16.3.6 Random forests
        16.3.7 K means
        16.3.8 Naïve Bayes
        16.3.9 Dimensionality reduction algorithm
        16.3.10 Gradient boosting algorithm and AdaBoosting algorithm
    16.4 Machine learning for Healthcare 4.0
    16.5 Vulnerabilities for ML in Healthcare 4.0
        16.5.1 Vulnerabilities in data collection
        16.5.2 Vulnerabilities due to data annotation
        16.5.3 Vulnerabilities in model training
        16.5.4 Vulnerabilities in deployment phase
        16.5.5 Vulnerabilities in testing phase
    16.6 ML-based solutions for Healthcare 4.0
        16.6.1 Privacy preservation
        16.6.2 Differential privacy
        16.6.3 Federated learning
    16.7 Conclusion
    References
Chapter 17 Big data analytics and data mining for healthcare and smart city applications
    17.1 Introduction
    17.2 Theoretical background of smart cities
        17.2.1 Smart people
        17.2.2 Smart economy
        17.2.3 Smart governance
        17.2.4 Smart mobility
        17.2.5 Smart environment
        17.2.6 Smart living
    17.3 Computational infrastructures for smart cities big data analytics
        17.3.1 Cloud computing
        17.3.2 Fog computing
        17.3.3 Edge computing
        17.3.4 Big data based on machine learning
    17.4 Mining methods for big data
        17.4.1 Classification
        17.4.2 Clustering
        17.4.3 Frequent pattern mining
        17.4.4 Another mining method
    17.5 Advances in healthcare sector
        17.5.1 Big data for healthcare
        17.5.2 Data mining for healthcare
    17.6 Conclusion
    References
Index