Biomedical Signal Processing for Healthcare Applications

Varun Bajaj, G. R. Sinha, Chinmay Chakraborty, Varun Bajaj, G. R. Sinha, Chinmay Chakraborty

• Publisher: CRC Press
• Year: 2021
• Print ISBN: 9780367707545
• eBook ISBN: 9781000413359
• Edition: 1
• Topic: Technology & Engineering
• Subtopic: Biotechnology in Medicine
• Index: Technology & Engineering

This book examines the use of biomedical signal processing—EEG, EMG, and ECG—in analyzing and diagnosing various medical conditions, particularly diseases related to the heart and brain. In combination with machine learning tools and other optimization methods, the analysis of biomedical signals greatly benefits the healthcare sector by improving patient outcomes through early, reliable detection. The discussion of these modalities promotes better understanding, analysis, and application of biomedical signal processing for specific diseases.

The major highlights of Biomedical Signal Processing for Healthcare Applications include biomedical signals, acquisition of signals, pre-processing and analysis, post-processing and classification of the signals, and application of analysis and classification for the diagnosis of brain- and heart-related diseases. Emphasis is given to brain and heart signals because incomplete interpretations are made by physicians of these aspects in several situations, and these partial interpretations lead to major complications.

FEATURES

• 
  
  

• Examines modeling and acquisition of biomedical signals of different disorders

• 
  
  

• Discusses CAD-based analysis of diagnosis useful for healthcare

• 
  
  

• Includes all important modalities of biomedical signals, such as EEG, EMG, MEG, ECG, and PCG

• 
  
  

• Includes case studies and research directions, including novel approaches used in advanced healthcare systems

This book can be used by a wide range of users, including students, research scholars, faculty, and practitioners in the field of biomedical engineering and medical image analysis and diagnosis.

1 Automatic Sleep EEG Classification with Ensemble Learning Using Graph Modularity

Kamakhya Narain Singh

North Odisha University

Sudhansu Shekhar Patra and Swati Samantaray

KIIT Deemed to Be University

Sudarson Jena

Sambalpur University

Jibendu Kumar Mantri

North Odisha University

Chinmaya Misra

KIIT Deemed to Be University

Contents

1.1 Introduction

1.2 Related Work

1.3 Electroencephalography (EEG)

1.3.1 Waves in EEG

1.3.2 Types of Sleep

1.3.2.1 Sleep Cycle Stages

1.3.2.2 Physiological Changes between NREM and REM

1.3.2.3 Sleep Period over Life Span

1.3.2.4 Disorders in NREM and REM Sleep

1.4 The EEG Dataset

1.4.1 ISRUC-Sleep Database

1.4.2 Sleep-EDF Database

1.5 Graph Modularity

1.6 Ensemble Techniques

1.7 Methodology

1.7.1 Transforming the Statistical Features to Undirected Weighted Graph

1.7.2 Transformation of Statistical Features to Undirected Weighted Graph

1.8 Experimental Results

1.9 Conclusion

References

1.1 Introduction

Sleep, as we know, is one of the key activities of the brain. Throughout the sleeping duration, many neurons of the human body are inactive. Any disorderliness in the human sleep cycle may cause lifelong impediments related to the physical performances and mental health of an individual. According to some reputed health organizations of the United States, approximately 60–70 million populace endure sleep distracts like apnea and insomnia. The National Highway Traffic in the United States has reported that many traffic accidents occur due to sleep-related issues.

Sleep (a behavioral state that alternates with waking) has the following characteristics:

• Lying down posture
• Raised threshold to sensory simulation
• Low level of motor output
• Unparalleled behavior dreaming

Sleep scoring is a fundamental procedure in diagnosing sleep distracts, because it can compute the sleep quality in order to support experts in identifying the irregularities in a patient’s recording. The study of sleep is called polysomnography (PSG). The major recordings for PSG are as follows:

• Electroencephalography (EEG): Electroencephalogram (EEG) is a test used to evaluate the electrical activity in the brain. Brain cells communicate with each other through electrical impulses. EEG can be used to detect potential problems associated with this activity.
• Electrooculography (EOG): It is a technique for measuring the corneo-retinal standing potential that exists between the front and the back of the human eye. The resulting signal is called the electrooculogram. Primary applications are in ophthalmological diagnosis and in recording eye movements.
• Electromyography (EMG): It is an electrodiagnostic medicine technique for evaluating and recording the electrical activity produced by skeletal muscles. EMG is performed using an instrument called an electromyograph to produce a record called electromyogram.

Besides the above measures, the other recordings are as follows:

• SpO₂: Oxygen saturation (SpO₂) is a measurement of how much oxygen your blood is carrying as a percentage of the maximum it could carry. For a healthy individual, the normal SpO₂ should be between 96% and 99%. High altitudes and other factors may affect what is considered normal for a given individual.
• Electrocardiography (ECG): It records the electrical signal from our heart to check for different heart conditions. Electrodes are placed on our chest to record our heart’s electrical signals, which cause our heart to beat. The signals are shown as waves on an attached computer monitor or printer.
• Breathing functions: Breathing provides oxygen to the body parts and eliminates carbon dioxide resulting from cell metabolism. Major physiologic switches in breathing take place during the sleeping period linked to alterations in respiratory drive and musculature.

1.2 Related Work

According to Mora et al. [1], there should be an effective demarcation in the stages of human sleep for treating the sleep disorders including apnea, insomnia and narcolepsy. The sleep process is a physiological activity in recovering from irregularities with the restoration of the energy level in persons and by overruling the exhausting consequences of wakefulness [2]. Currently various biomedical signal analyses such as EEG, EMG, EOG and ECG are functional in clinical setups which are employed for identifying the sleep disorderliness with EEG signal as one of the nearly useful signals in the classification of sleep stages in addition to sleep disorders [3]. Sleep scoring is a process of identifying the sleep disorders ...

Table of contents

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Contents
• Preface
• Acknowledgements
• Editors
• Contributors
• Chapter 1 Automatic Sleep EEG Classification with Ensemble Learning Using Graph Modularity
• Chapter 2 Recognition of Distress Phase Situation in Human Emotion EEG Physiological Signals
• Chapter 3 Analysis and Classification of Heart Abnormalities
• Chapter 4 Diagnosis of Parkinson’s Disease Using Deep Learning Approaches: A Review
• Chapter 5 Classifying Phonological Categories and Imagined Words from EEG Signal
• Chapter 6 Blood Pressure Monitoring Using Photoplethysmogram and Electrocardiogram Signals
• Chapter 7 Investigation of the Efficacy of Acupuncture Using Electromyographic Signals
• Chapter 8 Appliance Control System for Physically Challenged and Elderly Persons through Hand Gesture-Based Sign Language
• Chapter 9 Computer-Aided Drug Designing – Modality of Diagnostic System
• Chapter 10 Diagnosing Chest-Related Abnormalities Using Medical Image Processing through Convolutional Neural Network
• Chapter 11 Recent Trends in Healthcare System for Diagnosis of Three Diseases Using Health Informatics
• Chapter 12 Nursing Care System Based on Internet of Medical Things (IoMT) through Integrating Non-Invasive Blood Sugar (BS) and Blood Pressure (BP) Combined Monitoring
• Chapter 13 Eye Disease Detection from Retinal Fundus Image Using CNN
• Index