Intelligent Cardiovascular Disease Prediction Empowered with Gradient Descent Optimization

• Main Authors: Muhammad Saqib Nawaz, Bilal Shoaib, Muhammad Adeel Ashraf
• Format: Article
• Language: English
• Published: Elsevier 2021-05-01
• Series: Heliyon
• Subjects: Gradient descent: optimization; Prediction model; Cardiovascular disease
• Online Access: http://www.sciencedirect.com/science/article/pii/S2405844021010513

Disorders of the heart and blood vessels are named cardiovascular disease. 'The heart's proper functionality is of an utmost necessity for the survival of life. The death rate due to heart disease, has been increased rapidly. Cardiovascular illness is believed the deadliest cause of death across the globe. From the facts and figures shared by the WHO (World Health Organization) 17.9 Million human lost their lives due to cardiovascular diseases. This research is carried out for the effective diagnosis of heart disease using the heart disease dataset available on the UCI Machine Repository. Heart disease diagnosis with an optimization algorithm can be fruitful in terms of higher accuracy and sensitivity. Finding an acceptable optimal solution among multiple solutions for a specific problem is known as optimization. Different machine learning algorithms have been applied as Support Machine Vector (SVM), K-Nearest Neighbor (KNN), Naïve Bayes (NB), Artificial Neural Network (ANN), Random Forest (RF), and Gradient Descent Optimization (GDO). Intelligent Cardiovascular Disease Prediction Empowered with Gradient Descent Optimization model produces the optimal results among under consideration classification algorithms. 98.54 % accuracy has been achieved by the GDO based model while performance evaluation it. 99.43% sensitivity (recall) and 97.76% precision have also been recorded. From the prediction results of the system, it's satisfactory to utilize it for cardiovascular disease diagnosis. The proposed system will be helpful for the analysis of cardiovascular disease.