China
Africa
Explore chapters and articles related to this topic
Deep Learning for IoT-Healthcare Based on Physiological Signals
Published in Jacques Bou Abdo, Jacques Demerjian, Abdallah Makhoul, 5G Impact on Biomedical Engineering, 2022
Joseph Azar, Raphaël Couturier
An electrocardiogram (ECG) tracks the heart's electrical activity using electrodes placed upon the body. Typically the ECG signal is periodic, consisting of three parts: P wave, QRS complex, and T wave. It is one of the most used signals in healthcare research as it explicitly represents heart activity, which is clearly influenced by changes in the autonomic nervous system. The most typical and useful features computed with an ECG are heart rate variability and inter-beat intervals. ECG applications are various, such as biological parameters monitoring, and the detection of potential damage to the heart's muscle cells or conduction system, drowsiness and energy, heart failure, and the effects of heart drugs [32].
Flexible Electronic Technologies for Implantable Applications
Published in Muhammad Mustafa Hussain, Nazek El-Atab, Handbook of Flexible and Stretchable Electronics, 2019
The heart is a small four-chambered muscular lump that receives and pumps blood to the systemic and pulmonary circulatory system of the human body. The pumping mechanism of the heart is regulated by cardiac muscle cells that are of two kinds—pacemaker cells and non-pacemaker cells. The pacemaker cells have no resting cell membrane potential, but depolarize instantaneously, whereas non-pacemaker cells have resting potential that depolarizes quickly on application of electrical stimuli. Pacemaker cells in the heart are responsible for causing the heart muscles to rhythmically contract and relax at regular intervals, providing the necessary pumping force to pump blood around the circulating system of body. Electrocardiogram (ECG) measurements allow physicians to have a closer look at the patients’ heart, and it can be used to detect arrhythmias and heart attacks (myocardial infarctions). For instance, a leadless cardiac pacemaker has been presented by Reddy et al. which has notable extremely low power consumption of 64 nW, which raises the bar in terms of power budgets (Miller et al. 2015; Neuzil and Reddy 2015; Sideris et al. 2017). Nevertheless, it does not allow for continuous monitoring, as it only stores abnormal events into the memory for posterior wireless relaying. Status-quo of implantable devices used for continuous monitoring are discussed in later sections.
ANFIS-Based Cardiac Arrhythmia Classification
Published in Archana Mire, Vinayak Elangovan, Shailaja Patil, Advances in Deep Learning for Medical Image Analysis, 2022
Alka Barhatte, Manisha Dale, Rajesh Ghongade
The electrocardiogram (ECG) is a cardiac signal representing the recording of the electrical activity of the heart. Information such as heart rate, rhythm, and morphology in the form of conduction disturbances can be extracted from the ECG signal. The significance of the ECG is notable in that coronary heart diseases are major causes of mortality worldwide. The ECG varies between different individuals, due to the anatomy of the heart, and differences in size, position, age, etc. Thus, the ECG yields highly distinctive characteristics, suitable for various applications and diagnosis. This chapter focuses on cardiac arrhythmia classification. Cardiac arrhythmia is a heart disorder displaying an irregular heartbeat due to malfunction in the cells of the heart’s electrical system. During cardiac arrhythmia, the heartbeat can have an irregular rhythm. Sometimes it is too fast – >90 beats/min – and this is called tachycardia; when the heartbeat is too slow – <60 beats/min – this is called bradycardia. Thus, there are many types of cardiac arrhythmia based on heart rate and site of origin. Some are frequently benign, although several may be a sign of significant heart disease, stroke, or surprising heart failure. At some stage in cardiac arrhythmia, the heart may not be capable of pumping enough blood to the body. Lack of blood flow can damage organs like the brain and heart. Thus, to enable appropriate survival measures, an accurate classification is required of cardiac arrhythmia that leads to heart rate variations. This chapter introduces the classification of six types of cardiac arrhythmias based on the adaptive neuro-fuzzy inference system (ANFIS).
ECG denoising and feature extraction techniques – a review
Published in Journal of Medical Engineering & Technology, 2021
Haroon Yousuf Mir, Omkar Singh
The electrocardiogram (ECG) is an important biomedical signal that describes the electrical activity of the heart; its analysis has been used for the diagnosis of various cardiac diseases. ECG is generated by contraction and relaxation of atrial and ventricular muscles of the heart. The ECG signal consists of the PQRST complex. Where P wave is formed due to atrial depolarisation, the QRS complex is originated due to atrial depolarisation and ventricular repolarization and T wave is produced by ventricular repolarization. The intervals usually measured on an ECG are the PR, QRS interval, QT interval and RR interval. The electrocardiogram (ECG) signal is acquired by placing electrodes on the body surface which conveys information about the cardiac health condition. Various cardiac abnormalities can be studied by analysing the ECG signal properly by using different signal processing techniques. Signal processing techniques extracts some important features from a recorded biomedical signal which helps in the diagnosis of the corresponding physical system. Generally, a recorded biomedical signal conveys irrelevant information as well as the information of interest but by using proper Signal processing techniques irrelevant information can be removed easily. The approach used for diagnosis generally involves four vital processes to arrive at accurate and quick decisions about the kind of heart disease a patient suffers from. They are data acquisition, Denoising, Feature Extraction, and Classification [1,2].
Genetic particle filter improved fuzzy-AEEMD for ECG signal de-noising
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2021
Electrocardiogram (ECG) signal records the electrical conduction activity of heart. These are very small signals in strength with narrow bandwidth of 0.05–120 Hz. Physicians especially cardiologists use these signals for diagnosis of the heart’s condition or heart diseases. ECG signal is contaminated with various artifacts such as power-line interference (PLI), Patient-electrode motion artifacts, electrode-pop or contact noise, and baseline wandering and electromyographic (EMG) noise during acquisition. Analysis of ECG signals becomes difficult to inspect the cardiac activity in the presence of such unwanted signals. So, de-noising of ECG signal is extremely important to prevent misinterpretation of patient’s cardiac activity. Various methods are available for de-noising the ECG signal such as hybrid technique (Pradeep Kumar et al. 2009), empirical mode decomposition (Chacko and Ari 2012), un-decimated wavelet transform (Naga Prudhvi Raj and Venkateswarlu 2011), Hilbert-Hung transform (Zhang et al. 2010), morphological filtering (Liu et al. 2011), noise invalidation techniques (Nikvand et al. 2010), non-local means technique (Tracey and Miller 2012), S-transform (Alarka et al. 2012), adaptive filtering (Ying and An 2011), and FIR filtering (Ying and An 2011), etc.
Towards assisted electrocardiogram interpretation using an AI-enabled Augmented Reality headset
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2021
P. Lampreave, G. Jimenez-Perez, I. Sanz, A. Gomez, O. Camara
An electrocardiogram (ECG) is a clinical test used to measure the heart’s rhythm and electrical activity. Information provided by an ECG is used in the diagnosis and monitoring of different heart illnesses such as blocked arteries or pathological arrhythmias. The test involves the use of electrodes, cables that conduct the small signals recorded and an electrocardiogram machine that is able to amplify the signal, filter out any undesired noise and display (on a monitor) or print on paper (López Farré and Macaya Miguel 2009) the recorded ECG waves. A major issue in ECG interpretation is the high inter-patient and inter-operator variability of the captured signal due to the placement of the electrodes, the morphology of the heart, the type of pathology and the patient (Rajaganeshan et al. 2008). This issue is partly circumvented if a highly experienced physician carries out the interpretation; however, this is not always possible and some ECG features might go unnoticed to non-specialists or even when an expert cardiologist is available, especially when analysing multiple leads for several heart cycles or in stress-related situations. Although most ECG acquisition systems include basic signal processing algorithms that provide an initial interpretation, these methods analyse ECG signals as they are acquired, lacking global vision of the entire trace and producing generally unreliable results; hence, clinicians tend to ignore them. As a result, high-quality assisted ECG interpretation is still an unmet need and may be crucial to enable reliable and fast readings for correct clinical decisions.