Artificial intelligence-based framework for early detection of heart disease using enhanced multilayer perceptron

Area of Science:

• Cardiology
• Machine Learning
• Artificial Intelligence in Healthcare

Background:

• Cardiac disease is a leading cause of global mortality, with manual detection methods facing limitations.
• Accurate and timely diagnosis of heart conditions is crucial for preventing heart failure and improving patient outcomes.
• Machine learning algorithms present a promising approach to overcome the subjectivity and variability of traditional cardiac disease detection.

Purpose of the Study:

• To introduce a novel Enhanced Multilayer Perceptron (EMLP) framework for improved cardiac disease detection.
• To enhance predictive accuracy in classifying patients with heart conditions.
• To evaluate the efficacy of the proposed EMLP model against existing methods.

Main Methods:

• Development of a novel Enhanced Multilayer Perceptron (EMLP) framework.
• Implementation of data refinement techniques to optimize the classification model.
• Assessment of the EMLP model using the CDC cardiac disease dataset.

Main Results:

• The Enhanced Multilayer Perceptron (EMLP) model achieved a classification accuracy of 92%.
• The proposed framework demonstrated superior performance compared to traditional cardiac disease detection methods.
• EMLP showed higher accuracy, precision, F1-score, and recall in experimental results.

Conclusions:

• The Enhanced Multilayer Perceptron (EMLP) framework shows significant potential for the early detection and prediction of cardiac-related diseases.
• The study underscores the efficacy of the EMLP model in accurately identifying cardiac conditions.
• This machine learning approach offers a dependable alternative for enhancing patient survival rates through prompt diagnosis.