Intelligent Cardiovascular Disease Prediction Empowered with Gradient Descent Optimization.

Area of Science:

• Cardiology
• Medical Informatics
• Machine Learning

Background:

• Cardiovascular diseases are the leading global cause of death, claiming 17.9 million lives annually.
• Accurate and timely diagnosis of heart disease is critical for patient survival and effective treatment.
• Existing diagnostic methods can be enhanced with advanced computational approaches for improved outcomes.

Purpose of the Study:

• To develop an effective heart disease diagnosis system using machine learning algorithms.
• To optimize the diagnostic process for cardiovascular diseases through advanced algorithms.
• To evaluate the performance of various machine learning models in predicting heart disease.

Main Methods:

• Utilized the heart disease dataset from the UCI Machine Repository for analysis.
• Applied and compared several machine learning algorithms including Support Machine Vector (SVM), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Artificial Neural Network (ANN), and Random Forest (RF).
• Implemented and evaluated a Gradient Descent Optimization (GDO) model for enhanced cardiovascular disease prediction.

Main Results:

• The Gradient Descent Optimization (GDO) based model demonstrated superior performance compared to other classification algorithms.
• Achieved an accuracy of 98.54% for the GDO model during performance evaluation.
• Recorded high sensitivity (recall) of 99.43% and precision of 97.76% with the proposed GDO model.

Conclusions:

• The developed GDO-empowered system shows significant potential for accurate cardiovascular disease diagnosis.
• The model's high accuracy and sensitivity make it a satisfactory tool for clinical use.
• This research contributes a valuable system for the analysis and prediction of cardiovascular diseases.