Heart-Disease-Classification

This project aims to build a heart disease classification system using the Extreme Learning Machine (ELM) method. With this system, medical personnel can more easily identify patients at high risk of heart disease based on clinical data. The dataset used consists of 1190 patient data with 12 clinical features, including age, blood pressure, cholesterol level, maximum heart rate, blood sugar level, and history of angina. The data was processed with MinMaxScaler normalization to ensure uniform feature scale, as well as One-Hot Encoding to convert the labels into a format that can be understood by the model. The dataset can be accessed via the link: https://github.com/rikhuijzer/heart-disease-dataset?tab=readme-ov-file.

goals :

1. Analyzing patterns in patient data to understand factors contributing to heart disease risk.
2. Identify characteristics of high-risk patients based on available clinical variables.
3. Assist medical personnel in decision-making by providing data-driven insights from patients who have a high likelihood of developing heart disease.

insights :

1. Patients with high blood pressure and abnormal cholesterol levels tend to have a higher risk of heart disease.
2. A lower maximum heart rate can be one of the important indicators in detecting heart disease risk.
3. A history of frequent angina correlates with a greater likelihood of developing cardiovascular problems.
4. Patients who have high blood sugar levels tend to show a higher risk of heart disease, especially in the elderly age group.

Advices :

1. Add other more specific features such as family history, smoking habits, and physical activity levels for a more comprehensive analysis.
2. Conduct patient segmentation analysis based on age groups or certain risk factors to see more specific patterns.
3. Integrating the data with electronic medical records (EHR) to enable real-time prediction and provide recommendations to medical personnel more accurately.

This project provides deep insights into the factors that influence heart disease based on patient data and may form the basis for the development of better prediction systems in the future. Thank you for taking part in this research. For feedback, further questions, or deeper discussion, please feel free to contact me via email at dimasariyanto830@gmail.com or via LinkedIn at https://www.linkedin.com/in/dimas-ariyanto-a72038327/.

python #HeartDisease #classification #ELM #minmaxscaler