Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 23

PROJECT

Heart Disease prediction


COMPUTATIONAL INTELLIGENCE

PRESENTED BY PRESENTED TO

1. Sohail Afzal (SP20-BCS-164) Dr. Saeed UR Rehman


2. M. Usman (SP20-BCS-160)
INTRODUCTION

 Heart disease is the leading cause of death


 There are many risk factors for heart disease, including
 Age & Gender
 Family history
 Smoking & high blood pressure
 High cholesterol & Diabetes.

 Early detection and treatment of heart disease can help to


improve survival rates.
DATA SET

 The data set we used in this project was the Heart Disease Data
Set
 The data set contains 14 attributes, including
 Age & Gender
 Chest pain & Blood pressure
 Cholesterol etc.
 The target attribute also present in this data which represent
that whether or not the patient has heart disease.
METHODOLOGY

Figure 1
PROPOSED
MODEL

Figure 2
ALGORITHMS

We used six machine learning algorithms to predict the disease


 Logistic Regression
 Naïve Bayes
 SVM
 KNN
 Decision Tree
 Neural Networks
PREPROCESSING

Handling Handling
Feature Splitting the
Missing categorical
Values variables Selection Data
FEATURE SELECTION

 Process to select some important Feature from data set


 Goal is to Improve the accuracy of ML Algo’s
 Reduced Computational Cost
 Improved Understanding
DATA VISUALIZATION

 Process of representing Data in


Visual Format
 Communicate information more
effectively than text alone
 Better Decision making
 Increased Insights
DATA
VISUALIZATION

 Target=1 shows patients has


heart disease
 Target=0 shows patients has no
heart disease

Figure 3
DATA VISUALIZATION

SEX FEATURE ANALYZING

 2 Unique Features
 Feature 0
 Feature 1

Figure 4
LOGISTIC REGRESSION

Logistic regression is a statistical


algorithm.

It is commonly used in medical


research and prediction tasks, such
as heart disease prediction.

Figure 5(L.R Model)


NAÏVE BAYES ALGORITHM

Model Description

Training & Evaluation

Performance
SVM ALGORITHM

Model Description

Training & Evaluation

Performance SVM Testing & Performance


K-NEAREST NEIGHBOR KNN

Model Description

Training & Evaluation

Performance
NEURAL
NETWORKS

 Model Description
 Training & Evaluation
 Performance
DECISION TREE ALGORITHM

 Model Description
 Training & Evaluation
 Performance

Accuracy Score
MODELS EVALUATION

Models ACCURACY
Logistic Regression 86.34%
Naïve Bayes 85.37%
SVM 83.9%
KNN 72.2%
Decision Tree 100%
Neural Network 85.85%
Comparison Of Accuracy Score
MODELS EVALUATION

 In all the models which we


apply in our projects the
best and sufficient model is
the decision tree model
because it has the highest
accuracy rate which is 100%

Figure 6
CONCLUSION

 Machine learning algorithms can be used to


predict the likelihood of someone developing
heart disease with a high degree of accuracy.
 This information can be used to help doctors
identify patients who are at risk for heart
disease and to provide them with early
treatment.
 Early detection and treatment of heart
disease can help to improve survival rates.
REFERENCES

 Kaggle
 https://www.kaggle.com/datasets/johnsmith88/heart-disease-dataset/download?datas
etVersionNumber=2

 Research Article
 https://cse.anits.edu.in/projects/projects2021C3.pdf
THANK YOU

You might also like