You are on page 1of 11

Heart Disease

Prediction Using ML
Nidhi Shetty, TE-IT-B-68
Flow

1. Introduction
2. Proposed System
3. Data Design
4. GUI Design
5. Implementation/Testing
6. Results
7. Conclusion
Problem Definition
 Cardiovascular disease(CVD) is increasing daily in this modern world.
According to the World Health Organization(WHO), an estimated 17
million people die each year from cardiovascular disease, particularly heart
attacks and strokes. It is, therefore, necessary to record the most important
symptoms and health habits that contribute to CVD and take
precautionary measures from the start.
Introduction
 CVDs are the number 1 cause of death globally

 17.9 million people died from CVDs in 2016, representing 31% of all global
deaths. Of these deaths, 85% are due to heart attack and stroke.
 Over three quarters of CVD deaths take place in low- and middle-income
countries.
 People with cardiovascular disease or who are at high cardiovascular risk (due to
the presence of one or more risk factors such as hypertension, diabetes,
hyperlipidaemia or already established disease) need early detection and
management using counseling and medicines, as appropriate.
Literature Survey
Sr no Paper Title Author and Year Key findings Gap identified
(Techniques Used) (Accuracy Achieved)
1 Analysis of Heart Disease Prediction using M. Marimuthu, K- nearest neighbour, KNN 83.60%
Various Machine Learning Techniques S.Deivarani Naïve Bayes, support NB
  vector machine and
decision tree are used. 
Gayathri.R  
 
Year - 2019
2 Heart disease prediction system using data MeghaShahi et al SVM, Naïve Bayes, The paper explains that in some paper
mining techniques. Association rule, KNN, SVM effective and efficient accuracy
 
ANN and Decision Tree about 85% as compared to other data
Year - 2017 mining algorithms.
3 Heart disease prediction using data mining H. Benjamin Fredrick Random Forest, Decision Random Forest algorithm performs
techniques David and S. Antony Tree and Naïve Bayes best with 81% precision
Belcy
 
Year - 2019
Literature Survey
Sr no Paper Title Author and Key findings Gap identified
Year (Techniques Used) (Accuracy Achieved)
4 Heart Disease Prediction using Apurb Rajdhan Naive Bayes, Decision Random Forest algorithm has achieved the
Machine Learning Tree, Logistic highest accuracy of 90.16%
Milan Sai
Regression and Random
Avi Agarwal Forest.
Dundigalla Ravi
Dr. Poonam Ghuli
 
Year - 2020

5 Prediction of heart disease at early Salma banu N.K Naive Bayes, Decision Highest Accuracy - 84.1%
stage using data mining and big data Tree, SVM
 
analytics
Year - 2016
Proposed System
 Most CVDs can be prevented by addressing behavioral risk factors such as
tobacco use, unhealthy diet and obesity, physical inactivity and harmful use of
alcohol using population-wide strategies.
 Attributes - age, gender, cholesterol, chest pain type, thalach, resting blood
pressure, etc
 Machine learning approaches - Logistic Regression, K-nearest neighbors,
naive baiyes, support vector machine, random forest, and decision tree, etc
 Comparing to find the best.
 Dataset - kaggle.
GUI Design
Implementation

Dataset
Front End - Python Backend
(Tkinter)

Training & Testing


model
Testing
Results/Conclusion
 I conclude that there is a huge scope for machine learning algorithms in
predicting cardiovascular diseases.
 A lot of research can also be done on the correct ensemble of algorithms to use
for a particular type of data.

You might also like