Heart Disease Prediction

This project uses machine learning algorithms to predict heart disease.

Our Research Paper

Data

The data used in this project is the Cleveland Heart Disease dataset, which is available from the UCI Machine Learning Repository. The dataset contains 303 observations and 14 features. The features are:

• Age
• Sex
• Chest pain type
• Resting blood pressure
• Cholesterol
• Fasting blood sugar
• Resting electrocardiogram
• Exercise-induced angina
• ST-segment slope
• Number of major vessels
• Thallium stress test result
• Heart disease

Algorithms

The following algorithms are used to predict heart disease:

• Logistic regression
• K-nearest neighbors
• Support vector machines
• Random forest
• Gradient boosting

Results

The results of the experiments are shown in the following table:

Algorithm	Accuracy
Logistic regression	0.85
K-nearest neighbors	0.89
Support vector machines	0.875
Random forest	0.875
Gradient boosting	0.875

The best-performing algorithm is KNN (k-nearest neighbor).

Conclusion

This project has shown that machine learning algorithms can be used to predict heart disease with a high degree of accuracy. This information can be used to help doctors diagnose and treat heart disease.

Installation

Steps:
1. Clone the repository: `git clone https://github.com/g39team/Advanced-Heart-Health-Assessment-through-Machine-Learning-Using-KNN-Algorithm.git`
2. Navigate to the project directory: `cd Advanced-Heart-Health-Assessment-through-Machine-Learning-Using-KNN-Algorithm`
3. Install the required packages: `pip install -r requirements.txt`

References

• UCI Machine Learning Repository
• Machine Learning with Python