New frontiers of cardiovascular screening using unobtrusive sensors, AI, and IoT /

Detalles Bibliográficos
Clasificación:Libro Electrónico
Formato: eBook
Idioma:Inglés
Publicado: London : Academic Press, 2022.
Temas:
Cardiovascular system > Diseases > Diagnosis.
Medical screening.
Biomedical engineering.
Cardiovascular System.
Cardiovascular Diseases.
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Intro
  • New Frontiers of Cardiovascular Screening using Unobtrusive Sensors, AI, and IoT
  • Copyright
  • Dedication
  • Contents
  • Foreword
  • Preface
  • About the authors
  • Section 1: Sensors, AI and IoT in cardiovascular diseases
  • Chapter 1: Cardiovascular conditions: The silent killer
  • 1. Introduction
  • 2. Industrial revolution and Healthcare 4.0
  • 2.1. PhysioNet challenge
  • 3. Chronic diseases and cardiovascular issues
  • 4. Cardiovascular diseases: A silent killer
  • 4.1. Factors enhancing cardiac risks
  • 4.2. Heart rate, arrhythmia, and atrial fibrillation
  • 4.3. Coronary artery disease and ischemic heart diseases
  • 4.4. Cardiac fatigue and hypertension
  • 4.4.1. Cardiac fatigue
  • 4.4.2. Hypertension
  • 4.4.3. Regulation of blood pressure
  • 5. Sleep apnea and pulmonary conditions
  • 6. Need for early screening and diagnosis
  • 7. How sensing and AI can help
  • 8. Devices: Surgical implants for cardiovascular monitoring and management
  • 9. Analytics for screening and diagnosis
  • 10. Putting it all together
  • 11. Example of a real-world cardiovascular screening system
  • References
  • Further reading
  • Chapter 2: Proliferation of a new generation of sensors: Smartphones and wearables
  • 1. Introduction
  • 2. Unobtrusive digital sensing
  • 3. Electric or electromagnetic sensing
  • 3.1. Acoustic and mechanical sensing
  • 3.2. Biochemical sensing
  • 4. Sensing the heart: An engineers perspective
  • 4.1. Mechanical system
  • 4.2. Circulatory system
  • 4.3. Electrical system
  • 4.4. Control system
  • 4.5. Systems coming together
  • 5. Photoplethysmogram: pulse oximetry
  • 6. Phonocardiograms: digital stethoscope
  • 6.1. History of heart sounds
  • 6.2. Heart sounds
  • 6.3. Conventional stethoscope
  • 6.4. Digital stethoscope
  • 6.5. Future of the stethoscope
  • 7. ECG: Electrocardiograph.
  • 7.1. Origination and pathways of electrical charges in the heart
  • 7.2. 12 leads and Einthovens triangle
  • 7.3. Basic building blocks of an ECG machine
  • 8. Conclusion
  • References
  • Further reading
  • Chapter 3: Sensor signal analytics
  • 1. Introduction
  • 2. Preprocessing
  • 2.1. Signal conditioning
  • 2.1.1. Hardware filtering
  • 2.1.2. Amplification
  • 2.1.3. Attenuation
  • 2.2. Noise handling
  • 2.2.1. Noise sources
  • 2.2.2. Noise removal
  • 2.2.3. Signal reconstruction
  • 3. Decision making using AI
  • 3.1. Supervised machine learning
  • 3.2. Unsupervised machine learning
  • 3.3. Splitting of training and test data
  • 3.4. Feature engineering
  • 3.4.1. Dimensionality reduction using principal component analysis
  • 3.4.2. Independent component analysis
  • 3.5. Popular machine learning algorithms
  • 3.5.1. Logistic regression
  • 3.5.2. Support vector machine
  • 3.5.3. Decision tree
  • 3.6. Deep learning in biomedical engineering
  • 3.6.1. Neural network activation
  • Binary step activation function
  • Linear activation function
  • Sigmoid activation function
  • Hyperbolic tangent activation function (tanh)
  • Rectified linear unit activation function
  • Softmax function
  • 3.6.2. Network hyperparameters
  • 3.6.3. Recurrent neural networks
  • 3.7. Semisupervised learning in biomedical signal processing
  • 4. Further challenges
  • 4.1. Handling unbalanced data
  • 4.2. Clinical knowledge segmentation
  • 5. Conclusion
  • References
  • Section 2: Disease screening
  • Chapter 4: Abnormal heart rhythms
  • 1. Introduction
  • 2. Heart rate measurement using PPG and ECG
  • 2.1. Preprocessing: Smartphone, wearable, and nearable
  • 2.2. Frequency and time domain analysis
  • 3. Arrhythmia detection using PPG and ECG
  • 3.1. Signal conditioning
  • 3.2. Feature engineering
  • 4. Deep network for rhythm analysis
  • 5. Conclusion
  • References.
  • Further reading
  • Chapter 5: Heart blockage
  • 1. Introduction
  • 2. Correlation of heart blockage with ECG, PPG, and PCG
  • 3. AI-based detection of chronic ischemic heart disease
  • 3.1. Machine learning approaches
  • 3.2. Deep learning approaches
  • 4. Fusion of multiple sensors for classification
  • 5. Patient metadata-based knowledge modeling
  • 6. Conclusion
  • References
  • Further reading
  • Chapter 6: Hypertension and cardiac fatigue
  • 1. Introduction
  • 2. Screening of hypertension from PPG and ECG
  • 2.1. Electrical modeling of cardiovascular system
  • 2.2. Other lumped models for simulation of arterial blood pressure
  • 2.3. Regression modeling from PPG
  • 3. Pulse transit time analysis from PPG and ECG
  • 4. Cardiac fatigue from PPG and ECG
  • 4.1. Why investigating cardiac fatigue is important
  • 4.2. Sensing cardiac fatigue
  • 4.3. Some interesting early results and path to the future
  • 5. Conclusion
  • References
  • Chapter 7: Correlated diseases
  • 1. Introduction
  • 1.1. Sleep disorders
  • 1.2. Chronic obstructive pulmonary disease
  • 2. Sleep analysis
  • 2.1. Sleep studies
  • 2.1.1. Sleep stage classification
  • Preprocessing
  • Feature extraction
  • Feature selection and classification
  • 2.2. Sleep apnea and sleep arousal
  • 2.2.1. Detection techniques
  • 3. COPD
  • 3.1. Conventional machine learning
  • 3.2. Deep learning
  • 4. Conclusion
  • References
  • Further reading
  • Section 3: Future challenges
  • Chapter 8: Looking at the future
  • 1. Introduction
  • 2. Trends for physiological sensing
  • 2.1. Advances in noninvasive physiological sensing
  • 2.1.1. Flexible electronics-based wearables
  • 2.1.2. Implantables, ingestibles, and injectibles
  • 2.1.3. Using the human body as a communication medium
  • 2.1.4. Photoacoustic and hyperspectral sensing
  • 2.1.5. Radar sensing and computational imaging
  • 2.2. Nanobiosensing.
  • 2.3. Genomic analytics
  • 3. Trends for analytics and AI
  • 3.1. Technology trends
  • 3.1.1. AutoML
  • 3.1.2. Edge AI
  • 3.1.3. Neuromorphic computing
  • 3.1.4. Explainable AI
  • 3.2. Challenges
  • 3.2.1. Privacy, transparency, and trust
  • 3.2.2. Security
  • 4. Future vision for cardiovascular health
  • 4.1. A day in the life of a patient in 2030
  • 4.2. A day in the life of a cardiologist in 2030
  • References
  • Index.

Ejemplares similares