Cardiac Disease Prediction System Using Machine Learning

EasyChair Preprint 10014

Abstract

Heart disease prediction system is using machine learning algorithms. The system utilizes a combination of demographic, lifestyle, and medical data to predict the likelihood of an individual developing heart disease. The machine learning algorithms used in the system were trained on a large dataset of patient records and were validated using standard performance metrics. The results of the study showed that the proposed system was able to accurately predict heart disease with an average accuracy of 85%. Supervised machine learning algorithms, such as decision trees, random forests, and support vector machines, to build models that can predict the likelihood of heart disease based on a patient's demographic and medical information. The algorithms learn from a large dataset of patients, both with and without heart disease, to identify patterns and relationships in the data that are indicative of heart disease.

Keyphrases: Fasting blood sugar, K nearest neighbour algorithm, Random Forest Algorithm., Restecg, Support Vector Machine, Thalach, Trestbps, chest pain, cholesterol

@booklet{EasyChair:10014,
  author    = {A Peter Soosai Anandaraj and Adusumalli Lakshmi and Kona Venkatajahnavi and Panuganti Kumar Sanjay},
  title     = {Cardiac Disease Prediction System Using Machine Learning},
  howpublished = {EasyChair Preprint 10014},
  year      = {EasyChair, 2023}}