Clustering-based binary Grey Wolf Optimisation model with 6LDCNNet for prediction of heart disease using patient data

Area of Science:

• Cardiology
• Medical Data Science
• Artificial Intelligence in Healthcare

Background:

• Heart disease is a leading cause of death, with complications like dementia.
• Early detection and treatment of cardiovascular issues are crucial for mitigation.
• Healthcare data systems are expanding, enabling trend identification and preventative care.

Purpose of the Study:

• To propose a two-stage medical data classification and prediction model for cardiac ailments.
• To leverage healthcare data for improved diagnosis and intervention in heart disease.
• To develop an innovative deep learning model for cardiac condition classification.

Main Methods:

• Utilized Binary Grey Wolf Optimization (BGWO) for feature clustering.
• Developed a 6-layered deep convolutional neural network (6LDCNNet) for classification.
• Employed an improved optimization method for hyper-parameter tuning of the 6LDCNNet.

Main Results:

• The model achieved 96% convergence on the Cleveland dataset for severity assessment.
• The model demonstrated 98% convergence on an echocardiography imaging dataset.
• The proposed approach shows promising performance in classifying cardiac conditions.

Conclusions:

• The developed model can assist physicians in diagnosing cardiac disease severity.
• Early intervention facilitated by this model can significantly reduce cardiovascular mortality.
• This AI-driven approach holds potential for advancing cardiac care and patient outcomes.