Scribd
Upload
8 views10 pages

Colourful Retro Maths Solving Linear Equations Presentation

The document discusses the use of machine learning algorithms, particularly Decision Trees, SVM, and Random Forest, for predicting heart disease, which is a leading cause of death globally. It highlights the limitations of traditional prediction models and emphasizes the advantages of using wearable health technology for real-time data monitoring. The findings suggest that SVM, especially when combined with innovative algorithms, can significantly enhance prediction accuracy and facilitate early detection and prevention of heart disease.

Uploaded by

Shubham Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views10 pages

Colourful Retro Maths Solving Linear Equations Presentation

The document discusses the use of machine learning algorithms, particularly Decision Trees, SVM, and Random Forest, for predicting heart disease, which is a leading cause of death globally. It highlights the limitations of traditional prediction models and emphasizes the advantages of using wearable health technology for real-time data monitoring. The findings suggest that SVM, especially when combined with innovative algorithms, can significantly enhance prediction accuracy and facilitate early detection and prevention of heart disease.

Uploaded by

Shubham Gupta
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

Heart Diseases

Prediction
Using Decision Tree, SVM & Random Forest
Introduction
Heart disease is the leading cause of death
worldwide.
Traditional prediction models use static factors like
age and cholesterol.
Wearable health tech provides real-time data.
Improved prediction accuracy enables early
detection and proactive management.
Problem Statement
Heart disease remains a leading cause of death due to
late diagnosis.
Traditional risk assessments lack accuracy.
Wearable tech enables real-time, personalized
monitoring.
Our system enhances early detection and prevention.
LITERATURE SURVEY
Machine learning improves heart disease prediction
accuracy.
Combining multiple algorithms enhances
performance.
Arifuddin's study found SVM outperforms Decision
Trees.
SVM showed better accuracy, precision, recall, and
F1-score.
LITERATURE SURVEY
Building on this, Behera developed CCPSOSVM, a
revolutionary hybrid algorithm that combines
Cauchy mutation,
Crazy Particle Swarm Optimization, and
SVM
resulting in amazing accuracy rates of 92.59% for heart
disease and 97.41% for liver disease.
Advantages
Interpretability: Easy to understand and explain to non-
technical users.
Handles Non-linearity: Captures complex, non-linear
relationships in data.
No Feature Scaling: No need for normalization or
standardization of data.
Outlier Robustness: Less affected by outliers due to
threshold-based splits.
2 Algorithm Used

Decision Tree SVM Random Forest

Tree-based Optimal hyperplane Ensemble of


algorithm for for data decision trees for
predictive classification. accuracy.
decisions
Accuracy of algorithm in our
project
Methodology

Collect a heart disease dataset with key health variables.


Preprocess data: handle missing values, convert
categories, standardize.
Train and test a decision tree model using Scikit-learn.
Evaluate performance and build a real-time prediction UI.
Conclusion
SVMs are effective in heart disease
prediction.
Performance depends on feature selection,
data quality, and tuning.
Ongoing research can improve accuracy.
Enhanced models aid in early detection.

You might also like