Machine Learning Improves Accuracy of Coronary Heart Disease Prediction

EasyChair Preprint no. 11904, version 1

Abstract

In recent years, there has been a growing expectation to analyze the available data, and obviously with the contribution of machine learning. Machine learning is increasingly applied in medical specialties. The impact of using data properly can have a positive impact on improving people's lives. The health sector is of particular interest. Initially, it is because it has been proven that solutions are given to health care problems as well as with the accurate interpretation of medical data it contributes to the early prediction of a disease that the patient has. It is still possible to detect early signs of the disease, which can be useful in controlling the symptoms as well as in the correct treatment. Our work is based on the medical database with actual measurements from the Framingham Heart Study. The final set that was created with the help of the study has 78001 records. The ultimate goal of this work is, through the help of intelligent knowledge mining algorithms, to create an expert Artificial Intelligence system which predicts the development of coronary heart disease. We created two intelligent systems that predict the progression of coronary heart disease. Specifically, we trained machine learning algorithms such as Random Forest from Decision Trees, as well as Neural Networks. In our experimental analysis, the Decision Tree and Neural Network achieved an accuracy of 90.08 % and 84.56 % respectively.

Keyphrases: Big Data, Coronary Heart Disease, intelligent algorithms, machine learning

@Booklet{EasyChair:11904,
  author = {Savina Mariettou and Constantinos Koutsojannis and Vassilios Triantafillou},
  title = {Machine Learning Improves Accuracy of Coronary Heart Disease Prediction},
  howpublished = {EasyChair Preprint no. 11904},

  year = {EasyChair, 2024}}