Related Experiment Videos

Ensemble fuzzy multilayer neural perceptron with optimized feature selection for cardiac disease prediction using MRI

J K Kiruthika1, P Thangaraj2

  • 1Department of Computer Science and Engineering, KPR Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India.

Insights

A new ensemble-based fuzzy multilayer neural perceptron (EFMLNP) model significantly improves cardiovascular disease prediction using MRI data. This advanced machine learning approach achieves high accuracy, offering a more reliable method for diagnosing cardiac conditions.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Healthcare
  • Cardiovascular Research

Background:

  • Cardiovascular disease is a leading cause of mortality globally.
  • Accurate prediction of cardiac disease is complex due to numerous influencing factors.
  • Current diagnostic methods using ECG and MRI data have limitations in performance and accuracy.

Purpose of the Study:

  • To develop and evaluate an advanced machine learning model for improved cardiovascular disease prediction.
  • To address the limitations of existing diagnostic approaches for cardiac conditions.

Main Methods:

  • Utilized an ensemble-based fuzzy multilayer neural perceptron (EFMLNP) model for cardiac disease prediction.
  • Pre-processed MRI data using a median box filter (MBF) and adaptive mean gray segmentation (AMGS).
  • Employed recursive spectral spider optimization (RSSO) for feature selection and a machine learning feature-extraction model.

Main Results:

  • The EFMLNP model achieved a high accuracy of 98.3%.
  • Key performance metrics included precision (97.15%), recall (98.43%), F1-score (96.34%), and ROC (0.96).
  • The proposed method demonstrated superior performance in diagnosing cardiac disease compared to existing techniques.

Conclusions:

  • The EFMLNP model offers a highly accurate and reliable method for cardiovascular disease prediction.
  • This AI-driven approach can aid specialists in assessing cardiac disease risk more effectively.
  • The study highlights the potential of advanced machine learning in improving cardiac diagnostics.

Related Concept Videos