International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
Estimation of Prediction for Heart Failure Chances Using Various Machine Learning Algorithms Ashwin Chavan1, Bhairavi Chitnavis2, Poorva Wadkar3, Md. Ubaid Khan4 BE Students, Department of Computer Engineering, Dr. D. Y. Patil College of Engineering, Ambi, Pune, Maharashtra, India ----------------------------------------------------------------------***-----------------------------------------------------------------------2014, which is a risk factor for heart disease. Like this, other Abstract- The human heart is certainly the most important organ in our body. Our body cannot function normally if our heart cannot circulate enough blood to all our internal organs. Abnormalities in pumping blood causes heart failure. Though the term was coined in the 17th century it remains a global pandemic affecting over 26 million people worldwide. Hence predicting this deadly disease beforehand can do wonders for an individual as they can look after their health and fitness. Medical professionals find it difficult to come up with a scalable solution to predict the chances of heart failure. This is where advanced technologies like Machine learning can be used. With the help of Machine learning models, we can estimate if a person has chances of heart failure in the coming 10 years. In this study, we use a variety of machine learning methods to accurately predict heart failure. Here, we examined a dataset on heart failure that included significant pertinent medical data on 4238 patients. We have included the most crucial factors which play an important role in predicting if a person has chance of suffering from heart failure. We have implemented prediction models using various machine learning classification Algorithms. According to the findings of our study, in contrast with different machine learning algorithms, Random Forest had the greatest Accuracy = 96% as well as AUC = 99% when estimating the likelihood that patients would experience heart failure.
variables like obesity, poor nutrition, high cholesterol, and insufficient exercise can result in heart disease. As a result, prevention is essential. It's essential to comprehend heart diseases to prevent them. The fact that almost 47% of fatalities take place outside of a hospital shows how frequently warning signs are disregarded.
The diagnosis of heart conditions is a big barrier. Finding out if someone has a heart condition or not might be difficult. Even though there are devices that can forecast heart disease, they are either prohibitively expensive or inefficient at predicting the likelihood of heart disease in people. There has been extensive research done in this field because, according to a World Health Organization (WHO) report, only 67% of cardiac diseases can be predicted by medical professionals. In rural areas of India, there is a serious lack of access to hospitals and high-quality medical care. Only 58% of doctors in urban areas and 19% in rural areas have medical degrees, according to a 2016 WHO report.
Keywords: Random Forest, machine learning model, heart failure prediction, Disease Prediction, Accuracy
To anticipate any heart disease in people, machine learning may be a promising option. Heart disorders are a serious challenge for medical science. Neural networks, decision trees, KNNs, and other methods can be used to forecast heart disorders. We will learn how to utilize Random Forest to find the accuracy for heart disease later in this study. Additionally, it demonstrates how ML will help us fight heart disease in the future.
I. INTRODUCTION-
II. RELATED WORK -
Since a few years ago, the prevalence of cardiovascular diseases has been rising quickly throughout the world. Even though these diseases have been identified as the leading cause of death, they have also been identified as the most controllable and preventable diseases. Heart stroke is mostly brought on by artery obstruction. It happens when the heart cannot effectively pump blood throughout the body.
The literature is full of research studies on utilizing machine learning to diagnose cardiac problems. Here is a basic overview of that.
One of the major contributing factors to developing heart disease is high blood pressure. According to a report, 35% of people worldwide had hypertension between 2011 and
© 2023, IRJET
|
Impact Factor value: 8.226
|
According to a study by Montu Saw, Tarun Saxena, Sanjana Kaithwas, Rahul Yadav, and Nidhi Lal that was released in January 2020 and titled "Estimation of Prediction for Getting Heart Disease Using Logistic Regression Model of Machine Learning," they achieved 87% accuracy using the logistic regression technique. According to their research, men tend
ISO 9001:2008 Certified Journal
|
Page 1698