International Research Journal of Engineering and Technology (IRJET) Volume: 09 Issue: 11 | Nov 2022
www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
A STUDY OF THE LITERATURE ON CARDIOVASCULAR DISEASE PREDICTION METHODS Dr.M.Deepa1, E.Tamizhan2, M.P. Venkat Vijay3, S. Sri Ranjani4, V. Sowmiya5 Professor, Dept. of Computer Science and Engineering, Paavai College of Engineering, Pachal, Namakkal-TamilNadu, India. 2, 3, 4, 5 Student, Dept. of Computer Science and Engineering, Paavai College of Engineering, Pachal, Namakkal-TamilNadu, India. ---------------------------------------------------------------------***--------------------------------------------------------------------1Associate
Abstract - Among the main causes of death in the modern
The structure of this article is as follows. Section 2 provides a comprehensive evaluation of the body of previous research. Conclusion and future work are presented in Section 3.
world is cardiovascular disease. An important clinical problem is the ability to forecast cardiac disease. In order to forecast cardiac disease, this study discusses several data mining, big data, and machine learning techniques. Designing a crucial model for a healthcare profession to forecast heart illness or cardiovascular disease uses data mining and machine learning. This paper includes an overview of the prior work and offers insight into the current algorithm.
2. LITERATURE REVIEW In healthcare institutions, a lot of progress has been made on illness prediction systems utilizing various data mining, machine learning, and algorithmic approaches.
Key Words:
Data mining, prediction, cardiovascular disease, heart disease, machine learning
Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques is a concept put out by Senthil Kumar Mohan et al. (2019) with the aim of enhancing the accuracy of cardiovascular disease prediction by identifying essential components by utilizing machine learning. With many combinations of highlights and a few well-known arranging techniques, the expectation model is produced. We develop a prediction model for heart disease with a precision level of 88.7% using a hybrid random forest with a linear model (HRFLM). They also received training on a variety of data mining techniques and expectation methods, including KNN, LR, SVM, NN, and Vote, which have recently gained considerable notoriety for their ability to distinguish and predict heart disease. [2].
1. INTRODUCTION One of the common diseases that might shorten a person's lifetime nowadays is heart disease. Heart disease claims the lives of 17.5 million individuals worldwide every year [1]. Heart disease symptoms are rising quickly every day, thus it's crucial and worrisome to predict any potential illnesses in advance. This diagnosis is a challenging process that requires accuracy and efficiency. Heart disease comes in many different forms. Heart Failure (HF) and Coronary Artery Disease are the two most comparable forms (CAD). Heart Failure (HF) is mostly brought on by a blockage or narrowing of the coronary arteries.
Using data mining techniques, Mamatha Alex P and Shaicy P Shaji (2019) created "Prediction and Diagnosis of Heart Disease Patients." KNN, Random Forest, Support Vector Machine, and Artificial Neural Network methods are used in this article. Artificial Neural Networks have a greater accuracy rating for identifying heart disease in data mining when compared to the previously described categorization techniques [3].
The signs of heart illness, such as high blood pressure, chest discomfort, hypertension, cardiac arrest, etc., can be used to diagnose the condition. Birth defects, high blood pressure, diabetes, smoking, narcotics, and alcohol are all causes of cardiovascular diseases. Oftentimes, infections that damage the inner mitochondrial of the heart can also cause symptoms including fever, tiredness, a dry cough, and skin rashes. There are now too many automated tools, such as data mining, machine learning, deep learning, etc., to identify cardiac disease. Therefore, we shall give a basic overview of machine learning approaches in this work. Using machine learning resources, we train the datasets in this. There are certain risk variables that are used to make predictions about heart disease. Age, sex, blood pressure, cholesterol level, diabetes, family medical history of coronary disease, smoking, alcohol use, being overweight, heart rate, and chest pain are risk factors.
© 2022, IRJET
|
Impact Factor value: 7.529
Bo Jin, Chao Che, and colleagues (2018) suggested a neural network-based model for "Predicting the Risk of Heart Failure With EHR Sequential Data Modeling." This study conducted an attempt to foretell congestive heart disease using electronic health record (EHR) data from real-world datasets connected to the condition. To represent the diagnostic events and predicted coronary failure events using the fundamental tenets of an extended memory network model, we typically utilize one-hot cryptography
|
ISO 9001:2008 Certified Journal
|
Page 751