Monitoring Cardiovascular Problems in Heart Patients Using Machine Learning.

Area of Science:

• Cardiology
• Medical Informatics
• Machine Learning

Background:

• Heart disease is a leading global cause of death, with traditional diagnostic methods facing challenges like misdiagnosis and delayed treatment.
• Machine learning (ML) and artificial intelligence (AI) offer potential solutions to improve computer-aided diagnosis (CAD) and detection of cardiovascular disease.
• Accurate and timely diagnosis is crucial for effective cardiovascular disease management and reducing mortality rates.

Purpose of the Study:

• To develop and evaluate multiple machine learning models for the early detection of cardiovascular disease.
• To utilize the UCI machine learning heart disease dataset, focusing on individuals' medical attributes.
• To provide a tool that assists clinicians in making timely decisions for heart disease diagnosis.

Main Methods:

• Applied various machine learning techniques to the UCI heart disease dataset.
• Evaluated and reviewed the performance of different algorithms.
• Focused on classification algorithms like Random Forest and Extreme Gradient Boost.

Main Results:

• The Random Forest classifier achieved the highest accuracy at 96.72%.
• The Extreme Gradient Boost classifier demonstrated strong performance with 95.08% accuracy.
• The developed models show significant potential for aiding in the early detection of heart conditions.

Conclusions:

• Machine learning models can effectively aid in the early detection of heart disease.
• The proposed methods, particularly Random Forest, offer high accuracy in identifying potential cardiac issues.
• This technology can support clinical decision-making but is limited to detection, not severity assessment.