Heart Disease Prediction Using Supervised Classifiers

Abstract

The effective working and functioning of our heart is absolutely essential to our survival. Heart Problems is one of the most popular diseases today, and an early detection of the problem is critical for many health care providers in order to protect their patients and save lives. Healthcare has embraced technology to the point where healthcare service providers have made better decisions on patient’s diagnoses and treatment options, which has led to an overall improvement of healthcare services. Technology like Machine Learning has churn out number of solutions in the prediction of heart diseases and are capable of the detecting disease at an early stage. Since there has been a large amount of development of machine learning-based Techniques, it has been shown that machine learning Techniques are more time demanding, require ongoing human intervention and does not work well with large amount of data. It has been observed that deep learning techniques works better with the large set of data and healthcare sector generates massive amount of data. Through this work, we intended to incorporate supervised classifiers and deep learning algorithms in an optimized manner to compare and analyse the accuracy of different algorithms. We employed a benchmark dataset of UCI Heart illness prediction for this research, which consists of 14 distinct factors linked to heart disease. we would be doing comparative analysis using supervised algorithms and deep learning techniques. We did comparative analysis using supervised machine learning classifiers and deep learning algorithms to eventually evaluate out which gives the most efficient results for our work. Deep learning Techniques proves to be the most efficient giving 94.01% accuracy.

Note:
Funding Information: This research received no funding support in the public, commercial, or not-for-profit sectors.

Conflict of Interests: The authors have no conflicts of interest to declare

Keywords: Artificial Neural Network, Machine Learning, Deep Learning, Heart disease Prediction, Rmsprop, Sgd, Adagrad