China 
Africa 
Explore chapters and articles related to this topic
Prediction of Heart Disease Using Machine Learning
Published in Monika Mangla, Subhash K. Shinde, Vaishali Mehta, Nonita Sharma, Sachi Nandan Mohanty, Handbook of Research on Machine Learning, 2022
Subasish Mohapatra, Jijnasee Dash, Subhadarshini Mohanty, Arunima Hota
The heart is the most important organ present in the left-center of the human body, though it is small in size that is the same as the size of our fist, it has a vital role to make a human life. Any disorder that affects the normal functionality of the heart is known as heart disease. Under the term heart illness, it consists of blood vessel diseases, such as coronary artery problems, heart rhythm problems (arrhythmias) and heart faults you’re born with (congenital heart problem), and many more [1]. Insufficient or less blood flow can affect a healthy heart by not getting proper oxygen it requires and affects other body parts with insufficient oxygen. Types of heart diseases are there with various symptoms that can be different for men and women [2]. In blood vessel (atherosclerotic) heart disease, men are likely to get chest pain, pain in the upper abdomen or back during heavy work or exercise, whereas women can get chest discomfort, nausea, fatigue, and shortness of breath, weakness, etc.
Comparative Assessment of Machine-Learning Based Methodologies and Algorithms with Accuracy, Sensitivity and Specificity for Prediction of Heart Disease
Published in Durgesh Kumar Mishra, Nilanjan Dey, Bharat Singh Deora, Amit Joshi, ICT for Competitive Strategies, 2020
Rahul Kumar Jha, Santosh Kumar Henge
Myocardial infarction (MI), known as heart attack occurs due to abrupt behaviour of blood flow to a part of heart causing damage to the heart muscle, is a medical emergency requiring immediate attention and cure (Myocardial infarction n.d.). Owing to blockage of coronary artery fully or partially due to accretion of cholesterol plaque in the inner artery, blood flow rate diminishes to the heart tissue, causing tissues around the artery to die because of insufficient oxygen supply thereby afilters heart conduction (4 Steps of Cardiac Conduction n.d.), causing to cardiac blockage which may leads to immense circumstances even to sudden death. Symptoms includes disquieting pain in chest, arms, left shoulder, elbows, jaw or back; sweating; breathing problem; dizziness; high blood pressure; nausea and fatigue which causes due to chain smoking, excessive alcohol intake, lack of exercise, high level of cholesterol, diabetes, obesity, unhealthy diet and can be prevented addressing these (Strategies to prevent heart disease n.d.). Early diagnosis of heart disease is very important to cure the disease and many parameters can be used to detect the disease at early stage i.e. heart rate HR), pulse rate, sugar level, cholesterol, blood pressure (BP), body temperature (BT), oxygen level (SpO2), electrocardiogram (ECG) signals and echocardiography.
Cardiovascular Molecular Imaging: Overview of Cardiac Reporter Gene Imaging
Published in Robert J. Gropler, David K. Glover, Albert J. Sinusas, Heinrich Taegtmeyer, Cardiovascular Molecular Imaging, 2007
Joseph C. Wu, Sanjiv S. Gambhir
In recent years, stem cell therapy has replaced gene therapy as the most promising treatment avenue for ischemic heart disease. Several phase 1 clinical studies have shown that the implantation of skeletal myoblasts (73), endothelial progenitor cells (74), or bone marrow stem cells (75) into the infarcted myocardium can result in improved function. The mechanisms may be related to stem cells secreting paracrine factors, providing a mechanical scaffold, or recruiting other peripheral or resident cardiac stem cells (76). However, the analysis of stem cells, just like gene therapy, often relies on postmortem histology to identify their presence. The ability to study stem cell survival and proliferation in the context of the intact living body rather than postmortem histology would yield better insight into stem cell biology and physiology.
Data Analytics for Risk of Hospitalization of Cardiac Patients
Published in IETE Journal of Research, 2023
M. Chandralekha, N. Shenbagavadivu
The onset of chronic disease especially in patients with heart disease is mostly influenced by the lifestyle and predicting heart disease early could save cost and life. Heart disease refers to problems that are associated with blood vessels, circulatory system, disease related to tissues and structural units. The symptoms of heart disease vary for men and women. Men experience chest pain while women experience shortness of breath, chest discomfort. However, the common symptom includes chest pain, breathlessness and palpitations. Other symptoms include that pain that migrates from chest towards arm, back, jaw, heavy sweating, nausea, dizziness. Abnormal heartbeats or arrhythmia have symptoms like fluttering feeling in the chest, high heart beat, low heart beat, dizziness, shortness of breath and dizziness. There are number of factors that can cause heart disease such as genetic factors, heart muscle damages, heart valve disorders, pumping conditions and life style. The main risk factors for developing heart disease are age, sex, family history, smoking, diet that have high salt, fat, sugar, high blood pressure, diabetes, high cholesterol levels, stress and anxiety.
Identifying heart disease risk factors from electronic health records using an ensemble of deep learning method
Published in IISE Transactions on Healthcare Systems Engineering, 2023
Linkai Luo, Yue Wang, Daniel Y. Mo
Heart disease is one of the leading causes of death worldwide. In the United States, heart disease and related diseases account for more than 600,000 deaths annually (CDC, 2022). The annual total cost due to heart diseases has been reported to reach 108.9 billion dollars, including medications, medical services, and lost productivity (Heidenreich et al., 2011). The development of heart disease is complicated and depends on numerous risk factors. The World Health Organization (WHO) defines these as “any attribute, characteristic or exposure of an individual that increases the likelihood of developing a disease or injury” (WHO, 2023). Medical research has indicated that risk factors related to heart disease include lifestyle factors such as smoking, hereditary factors such as family history of heart disease, and specific clinical conditions such as coronary artery disease (CAD), diabetes, obesity, hyperlipidemia, and hypertension (Dokken, 2008). Identifying and reducing potential risk factors are critically important for early prevention and treatment and to reduce the incidence of heart disease worldwide.
Exploring the use of association rules in random forest for predicting heart disease
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2023
Khalidou Abdoulaye Barry, Youness Manzali, Rachid Flouchi, Youssef Balouki, Khadija Chelhi, Mohamed Elfar
Heart disease is a disease that affects the heart and damages it over time. It is gaining ground day by day and killing all over the world. This is why researchers are developing models using machine learning algorithms to predict diseases to assist healthcare workers. In this research work, we have proposed a novel method that consists in improving the performance of the random forest technique by adding association rules to its training procedure. This novel method and five other classifiers namely Random Forest, Decision Tree, Support Vector Machine, Naïve Bayes, and XGBoost are programmed and tested in the same dataset which is the heart dataset Cleveland. Then, the comparison was made between them based on parameters such as model accuracy, model sensitivity, model specificity, model AUC, and log loss. The results showed that the novel method measured with these metrics performs better than the other five classifiers. It reaches 83.50% accuracy, specificity with 80.70%, sensitivity with 89.10%, 90.50% AUC, and 0.405 log loss. In addition, the classical random forest technique took the second position after the proposed model with 82.80% accuracy, specificity with 80.50%, sensitivity with 87.80%, 89.50% AUC, and 0.421 log loss.