Proceedings of The International Conference on Emerging Trends in Artificial Intelligence and Smart Systems, THEETAS 2022, 16-17 April 2022, Jabalpur, India

Research Article

Cardiovascular Disease Predictor

Download304 downloads
  • @INPROCEEDINGS{10.4108/eai.16-4-2022.2318172,
        author={Daksh  Jain and Vardan  Yadav and Manavi  Kumari and Kundan  Chandravansi and Gurakonda Konda Reddy and Jeba Nega Cheltha},
        title={Cardiovascular Disease Predictor},
        proceedings={Proceedings of The International Conference on Emerging Trends in Artificial Intelligence and Smart Systems, THEETAS 2022, 16-17 April 2022, Jabalpur, India},
        publisher={EAI},
        proceedings_a={THEETAS},
        year={2022},
        month={6},
        keywords={cardiovascular disease prediction gaussiannb knn random forest decisiontree ridgeclassifier},
        doi={10.4108/eai.16-4-2022.2318172}
    }
    
  • Daksh Jain
    Vardan Yadav
    Manavi Kumari
    Kundan Chandravansi
    Gurakonda Konda Reddy
    Jeba Nega Cheltha
    Year: 2022
    Cardiovascular Disease Predictor
    THEETAS
    EAI
    DOI: 10.4108/eai.16-4-2022.2318172
Daksh Jain1,*, Vardan Yadav1, Manavi Kumari1, Kundan Chandravansi1, Gurakonda Konda Reddy1, Jeba Nega Cheltha1
  • 1: School of Computer Science and Engineering, Lovely Professional University, Punjab, India
*Contact email: jaindaksh58@gmail.com

Abstract

Heart disease is a very common disease that kills many people every year regardless of age. So, machine learning is used to predict if a person has cardiovascular disease. The classification models used here are KNN, Ridge Classifier, Decision Tree, Random Forest and GaussianNB. The dataset used is the Cleveland heart dataset. In this paper, we firstly pre-process the data. After that, the dataset is branched into two parts, the training and the testing parts. After that, we fit the data in the models and get an initial idea prediction. Then, we apply hyperparameter tuning to increase the accuracy of the models. After hyperparameter tuning, we find that KNN performed best with the roc_auc score of 93.2%. This accuracy is an improvement over previous work. A web application using Flask is also created to provide GUI to users.