Scribd Logo
Upload

Welcome to Scribd!

  • 33 views

    ICACCS 2023 - Presentataion Template - Sample

    Uploaded by

    Sai Devaraju V S
    This document presents a comparative analysis of machine learning methods for predicting cardiac diseases. Random forest, naive bayes, and logistic regression classifiers were tested on a real-world dataset containing 14 medical attributes. Random forest achieved the best accuracy of 92% for predicting heart diseases, outperforming the other methods. The random forest and naive bayes algorithms were also implemented using the Orange tool for visual model building and evaluation.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    ICACCS 2023 - Presentataion Template - Sample

    Uploaded by

    Sai Devaraju V S
    33 views11 pages
    This document presents a comparative analysis of machine learning methods for predicting cardiac diseases. Random forest, naive bayes, and logistic regression classifiers were tested on a real-world dataset containing 14 medical attributes. Random forest achieved the best accuracy of 92% for predicting heart diseases, outperforming the other methods. The random forest and naive bayes algorithms were also implemented using the Orange tool for visual model building and evaluation.

    Original Description:

    ICACCS presentation

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document presents a comparative analysis of machine learning methods for predicting cardiac diseases. Random forest, naive bayes, and logistic regression classifiers were tested on a real-world dataset containing 14 medical attributes. Random forest achieved the best accuracy of 92% for predicting heart diseases, outperforming the other methods. The random forest and naive bayes algorithms were also implemented using the Orange tool for visual model building and evaluation.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    33 views11 pages

    ICACCS 2023 - Presentataion Template - Sample

    Uploaded by

    Sai Devaraju V S
    This document presents a comparative analysis of machine learning methods for predicting cardiac diseases. Random forest, naive bayes, and logistic regression classifiers were tested on a real-world dataset containing 14 medical attributes. Random forest achieved the best accuracy of 92% for predicting heart diseases, outperforming the other methods. The random forest and naive bayes algorithms were also implemented using the Orange tool for visual model building and evaluation.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 11

    MACHINE LEARNING BASED CARDIAC DISEASE

    PREDICTION- A COMPARATIVE ANALYSIS

    MAVURI RAHUL KUMAR

    ECE(IOT)
    KARUNYA INSTITUTE OF TECHNOLOGY AND SCIENCES
    COIMBATORE , TAMIL NADU, INDIA
    [email protected]
    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 1
    Abstract
    In, living creatures cardiovascular diseases (CVDs), which are typically heart-related ailments,
    have been the leading cause of death globally for a number of years and are now acknowledged as
    the most serious disease in both India and the rest of the world. As a result, early detection of these
    illnesses is crucial for successful treatment, necessitating the development of a reliable, accurate,
    and practical approach. Researchers have recently made extensive use of machine learning
    algorithms to aid the medical community and professionals in the identification of heart-related
    disorders. In order to analyze a huge medical data machine learning methods play a prime role. In
    this work, a comparative analysis of machine learning methods are carried out to predict the heart
    diseases by using real time datasets. Logistic Regression, Naive Bayes, and Random Forest are
    used to predict the heart diseases in which random forest method produces better results in
    comparison with other methods

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 2
    Introduction
    Heart diseases are increasing daily at a rapid rate and it is alarming and vital to predict
    heart diseases early. The diagnosis of heart diseases is a challenging task i.e. it must be
    done accurately and proficiently. The aim of this study is to determine which patient is
    more likely to have heart disease based on a number of medical features . It is worrisome
    and crucial to predict cardiac problems early because they are spreading quickly and increasing
    daily. The prediction of heart disease is a difficult task because it needs to be carried out skillfully
    and properly. The purpose of this study is to predict the heart diseases based on a variety of
    medical characteristics of a patient. The heart diseases are more likely be suffered by the humans.It
    can be predicted automatically by artificial intelligence techniques.

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 3
    Literature
    To automatically and quickly identify cardiac disease, the major goal is to foresee when it will start to
    manifest. In a healthcare setting where professionals lack the most recent knowledge and abilities, the
    suggested methodology is essential. In order to determine a personhas heart disease, a number of medical
    factors are taken into consideration, including blood sugar levels, heart rate, age, and sex. Several
    algorithms are used to predict heart issues in the early phases of diagnosis with the use of a few
    parameters. A machine learning system predicts the outcome using the prediction models it has created
    using historical data when it gets new input. Machine learning is the process through which an algorithm
    may automatically learn from data, improve performance based on past performance, and predict future
    outcomes. Many algorithms used in machine learning work with enormous volumes of data. These
    algorithms are trained using data, and after training, they create a model and perform a certain task.
    Clustering, associations, forecasting, classification, regression, and other ML techniques enable the
    resolution of several business difficulties.

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 4
    Proposed approach

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 5
    Result and Discussion

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 6
    Implementation of Random forest in Orange
    tool

    2021 7th International Conference on Advanced Computing


    12/09/2023 7
    and Communication Systems (ICACCS).
    Implementation of Naïve bayes in Orange
    tool

    2021 7th International Conference on Advanced Computing


    12/09/2023 8
    and Communication Systems (ICACCS).
    Comparative analysis
    S.NO METHOD NAME ACCURACY IN TOOL ACCURACY IN CODE

    1. NAÏVE BAYES 82% -

    2. RANDOM FOREST 92% 83%

    3. LOGISTIC REGRESSION 81% -

    2021 7th International Conference on Advanced Computing


    12/09/2023 9
    and Communication Systems (ICACCS).
    Conclusion
    The cardiac diseases is one of the dangerous deadly diseases among mankind. the prediction of
    cardiac disease play a paramount task for all living creatures. This study deals about autonomous
    cardiac disease prediction by using the predictive learning techniques of naïve bayes, random
    forest and logistic regression. It is implemented for real time dataset with 14 input attributes. The
    entire data set is gathered, preprocessed, and experimented. The results of machine learning
    methods are assessed by the performance metric of accuracy in which random forest method
    produces better results in comparisonwith other methods.

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 10
    Reference
    • 1. Abu Nada, A. M., et al. (2020). "Age and Gender Prediction and Validation through Single User
    Images Using CNN." International Journal of Academic Engineering Research (IJAER) 4(8)
    • 2. Abu Nada, A. M., et al. (2020). "Arabic Text Summarization Using AraBERT Model Using
    Extractive Text Summarization Approach." International Journal of Academic Information
    Systems Research (IJAISR)
    • 3. Abu-Jamie, T. N., et al. (2022). "Six Fruits Classification Using Deep Learning." International
    Journal of Academic Information Systems Research (IJAISR) 6(1): 1-8. 4. Abu-Saqer, M. M., et
    al. (2020). "Type of Grapefruit Classification Using Deep Learning." International Journal of
    Academic Information Systems Research (IJAISR).
    • 4.Prediction of Heart Disease Using a Collection of Machine and Deep Learning Algorithms by
    Ali M. A. Barhoom1 , Abdelbaset Almasri1 , Bassem S. Abu-Nasser1 , Samy S. Abu-Naser2
    1University Malaysia of Computer Science & Engineering (UNIMY), Cyberjaya, Malaysia.
    2Department of Information Technology, Faculty of Engineering .

    12/09/2023 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS). 11

    You might also like