Diagnosis of Chronic Ischemic Heart Disease Using Machine Learning Techniques

Area of Science:

• Cardiology
• Artificial Intelligence
• Machine Learning

Background:

• Ischemic heart disease (IHD) is a leading cause of mortality globally, particularly in Pakistan.
• Existing models for IHD detection lack the necessary precision to significantly reduce fatalities.
• Accurate and precise diagnostic tools are crucial for mitigating deaths from heart disease.

Purpose of the Study:

• To develop and evaluate an artificial intelligence-based approach for precise diagnosis of ischemic heart disease.
• To compare the performance of different machine learning algorithms in predicting heart disease stages.
• To enhance the accuracy of heart disease detection to aid in reducing mortality rates.

Main Methods:

• The study employed machine learning algorithms including Logistic Regression (LR), Naive Bayes (NB), and Random Forest (RF).
• A dataset was utilized for training and testing the predictive models.
• The models were trained to categorize the current stage of heart disease.

Main Results:

• The Random Forest (RF) model achieved the highest accuracy at 99%.
• Logistic Regression (LR) demonstrated 98% accuracy, and Naive Bayes (NB) achieved 97% accuracy.
• The experimental outcomes indicate superior performance of the proposed strategy compared to existing methods.

Conclusions:

• The developed artificial intelligence models show high precision in diagnosing ischemic heart disease.
• The high accuracy achieved by the models, especially RF, suggests a potential to decrease annual deaths from IHD.
• This approach offers a promising tool for early and accurate detection of heart disease, aiding public health initiatives.