Early Prediction of Cardio Vascular Disease (CVD) from Diabetic Retinopathy using improvised deep Belief Network...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Cardiology

Background:

• Cardiovascular Disease (CVD) is a leading cause of mortality, with prediction challenges exacerbated by inadequate early detection systems.
• Diabetic Retinopathy (DR) is linked to increased CVD risk, highlighting the importance of early DR diagnosis for CVD prevention.
• Existing classification models often neglect crucial aspects like feature selection and accuracy enhancement.

Purpose of the Study:

• To develop an improved model for early Cardio Vascular Disease (CVD) prediction.
• To enhance model performance and accuracy by focusing on feature selection and unbiased output generation.
• To leverage the connection between Diabetic Retinopathy (DR) and CVD risk factors for more effective prediction.

Main Methods:

• An Improvised Deep Belief Network (I-DBN) was developed for disease classification.
• Principal Component Analysis (PCA) was employed for effective feature extraction.
• Particle Swarm Optimization (PSO) algorithm was utilized for optimized feature selection.

Main Results:

• The proposed I-DBN model demonstrated superior performance compared to existing state-of-the-art methods.
• The model achieved a high prediction accuracy of 98.95% for Cardio Vascular Disease.
• Validation confirmed the reliability of I-DBN for clinical decision support.

Conclusions:

• The I-DBN model offers a significant advancement in the early prediction of CVD.
• Accurate CVD risk assessment, aided by DR indicators, can be achieved through advanced machine learning techniques.
• The developed model provides trustworthy recommendations for clinicians, improving patient treatment strategies.