1. Heart failure prediction using machine learning.
- Author
-
Gandla, Vengala Rao, Mallela, David Vinay, and Chaurasiya, Rahul
- Subjects
- *
HEART failure , *SUPPORT vector machines , *RANDOM forest algorithms , *HEART diseases , *MACHINE learning , *FORECASTING - Abstract
Over 17.3 million people are dying because of cardio-vascular disease. In past, predicting heart failure (HF) disease was a challenging task. In the modern era, we have relevant training data for HF prediction. Using state-of-the-art machine learning (ML) models, the HF can be predicted with high precision. In this paper, by employment of different ML algorithms, we predict whether a person has cardio-vascular disease (CVD) or not using relevant symptoms of the person. This research predicts the heart failure chances using discriminative attributes that are collected from the patients. A standard dataset from the university of California at Irvine (UCI) that contains 14 parameters related to heart disease has been examined in this study. Our machine learning models are trained using five different classification techniques. The algorithms are logistic regression, k-nearest neighbours (KNN), support vector machines (SVM), random forest, and gradient boosting. The SVM classifier has shown the highest accuracy of 86.84%. The accuracy of predictions has also been enhanced by suitable data pre-processing and cross validation techniques. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF