Engineering and Technology for Healthcare

Contributors 1.1. Introduction ix 1.2. Bibliography xv 2. Maximising the value of engineering and technology research in healthcare: development-focused health technology assessment 2.1. Introduction 2.2. What is HTA? 2.3. What is development-focused HTA? 2.4. Illustration of features of development-focused HTA? 2.4.1. Use-focused HTA? 2.4.2. Development-focused HTA? 2.5. Activities of development-focused HTA? 2.6. Analytical methods of development-focused HTA 2.6.1. Clinical value assessment 2.6.2. Economic value assessment 2.6.3. Evidence generation 2.7. What are the challenges in the development and assessment of medical devices? 2.7.1. What are the medical devices? 2.7.2. Challenges common to all medical devices 2.7.2.1. Licencing and regulation 2.7.2.2. Adoption 2.7.2.3. Evidence 2.7.3. Challenges specific to some categories of device 2.7.3.1. Learning curve 2.7.3.2. Short lifespan and incremental improvement 2.7.3.3. Workflow 2.7.3.4. Indirect health benefit 2.7.3.5. Behavioural and other contextual factors 2.7.3.6. Budgetary challenge 2.8. The contribution of DF-HTA in the development and translation of medical devices 2.8.1. Case study 1 - Identifying and confirming needs 2.8.2. Case study 2 - What difference could this device make? 2.8.3. Case study 3 - Which research project has the most potential? 2.8.4. Case study 4 - What is the required performance to deliver clinical utility? 2.8.5. Case study 5 - What are the key param-eters for evidence generation? 2.9. Conclusion 3. Contactless Radar Sensing for health monitoring 3.3.1. Introduction: healthcare provision and radar technology 3.3.2. Radar and Radar Data Fundamentals 3.3.2.1. Principles of radar systems 3.3.2.2. Principles of radar signal processing for health applications 3.3.3. Principles of machine learning applied to radar data 3.3.4. Complementary approaches: passive radar and channel state information sensing 3.4. Radar technology in use for healthcare 3.4.1. Activities recognition and fall detection 3.4.2.Gait monitoring 3.4.3. Vital signs and sleep monitoring 3.5. Conclusion and outstanding challenges 3.6. Future Trends 4. Pervasive Sensing: Macro to Nanoscale 4.1 Introduction 4.2. The anatomy of a human skin 4.3. Chracteristic of human tissue 4.4 Tissue Sample Preparation 4.5. Measurement Apparatus 4.6. Simulating the human skin 4.6.1. Human body channel modelling 4.7. Networking and Communication Mech-anisms for Body-Centric WirelessNano-Networks 4.8. Concluding Remarks 5. Bio integrated Implantable Brain Devices 5.1. Background 5.2 Neural Device Interfaces 5.3. Implant Tissue Biointegration 5.4. MRI Compatibility of the NeuralDevices 5.5. Conclusion 6. Machine Learning for Decision Making in Healthcare 6.1. Introduction 6.2. Data Description 6.3. Proposed Methodology 6.3.1. Data collection 6.3.2. Window size selection 6.3.3. Feature Extraction 6.3.4. Feature Selection 6.3.5. Implementation of Machine learning Models 6.3.6. Model Evaluation 6.4. Results 6.5. Analysis and Discussion 6.5.1. Impact of Postures 6.5.2. Impact of Windows Size 6.5.2. Impact of Feature combination 6.5.3. Impact of Machine Learning algorithms 6.6. Conclusion 7. Information Retrieval from Electronic Health Records 7.1. Introduction 7.2. Methodology 7.2.1. Parallel LSI (PLSI) 7.2.2. Distributed LSI (DLSI) 7.3. Results and Analysis 7.4 Conclusion 8. Energy Harvesting for Wearable and Portable Devices 8.1. Introduction 8.2. Energy Harvesting Techniques 8.2.1. Photovoltaics 8.2.2. Piezoelectric Energy Harvesting 8.2.3. Thermal Energy Harvesting 8.2.3.1. Last Trends 8.2.4. RF Energy Harvesting 8.3. Conclusion 9. Wireless control for life-critical actions 9.1. Introduction 9.2. Wireless Control for Healthcare 9.3. Technical Requirements 9.3.1. Ultra-Reliability 9.3.2. Low Latency 9.3.3. Security and Privacy 9.3.4. Edge Artificial Intelligence 9.4. Design Aspects 9.4.1. Independent Design 9.4.2. Co-Design 9.5. Co-Design System Model 9.5.1. Control Fusion 9.5.2. Performance Evaluation Criterion 9.5.2.1. Control Performance 9.5.2.2. Communication Performance 9.5.3. Effects of Different QoS 9.5.4. Simulation Results 9.6. Conclusion 10. ROLE OF D2D COMMUNICATIONS INMOBILE HEALTH APPLICATIONS: SECURITY THREATS AND REQUIREMENTS 10.1. Introduction 10.2. D2D Scenarios for Mobile Health Applications 10.3. D2D Security Requirements and Standardisation 10.3.1. Security Issues on Configuration 10.3.1.1. Configuration of the ProSe enabled UE 10.3.1.2. Security Issues on Device Discovery 10.3.1.2.1. Direct Request and Response Discovery 10.3.1.2.2. Open Direct Discovery 10.3.1.2.3. Restricted Directory 10.3.1.2.4. Registration in network-based ProSe Discovery 10.3.2. Security Issues on One-to-Many Communications 10.3.2.1. One-to-many communications between UEs 10.3.2.2. Key distribution for group communications 10.3.3. Security Issues on One-to-One Communication 10.3.3.1. One-to-one ProSe direct communication 10.3.3.2. One-to-one ProSe direct communication 10.3.4. Security Issues on ProSe Relays 10.3.4.1. Maintaining 3GPP communication security through relay 10.3.4.2. UE-Network relay 10.3.4.3. UE-to-UE relay 10.4. Existing Solutions 10.4.1. Key Management 10.4.2. Routing 10.4.3. Social Trust and social ties 10.4.4. Access Control 10.4.5. Physical Layer Security 10.4.6. Network Coding 10.5. Conclusion 11. Automated diagnosis of skin cancer for healthcare: Highlights and Procedures 11.1. Introduction 11.2. Framework of Computer-aided Skin Cancer Classification Systems 11.2.1. Image Acquisition 11.2.2. Image Pre-processing 11.2.2.1. Color Contrast Enhancement 11.2.2.2. Artificial Removal 11.2.3. Image Segmentation 11.2.3.1. Thresholding-based Segmentation 11.2.3.2. Edge-based Segmentation 11.2.3.3. Region-based Segmentation 11.2.3.4. Active contours-based Segmentation 11.2.3.5. Artificial Intelligence-based Segmentation 11.2.4. Feature Extraction 11.2.4.1. Color-based Features 11.2.4.2. Dimensional Features 11.2.4.3. Textual-based Features 11.2.4.4. Dermoscopic Rules and Methods 11.2.4.4.1. ABCD Rule 11.2.4.4.2 Menzies Method 11.2.4.4.3 7-Point Checklist 11.2.5. Feature Selection 11.2.6. Classification 11.2.7. Classification Performance Evaluation 11.3. Conclusion 12. Conclusion