• Mr. Hitarth D. Patel
• Mr.Govind V. Patel
• Mr. Mehul S. Patel,
• Mr. Jayesh M. Mevada

Coronary Artery Disease (CAD) is a major global cause of mortality for which it requires accurate and effective diagnostic techniques. Conventional angiography, even though accurate, has drawbacks like it being very expensive, having side effects, and relying on skilled interpretation, thus predisposing to misdiagnosis. In contrast to these drawbacks, this research extends CAD detection accuracy through the application of Machine Learning (ML) algorithms. The method being proposed makes use of the Deep Discern dataset containing 20,612 angiograms of 10,073 patients and uses state-of-the-art ML models, such as Particle Swarm Optimization (PSO) and Genetic Algorithms (GA) for selecting features. The Gradient Boosting Decision Tree (GBDT) model is trained and tested using accuracy, precision, recall, F-measure, and specificity. Experimental findings ascertain that the projected Predictive Convolutional Neural Network (PCNN) improves upon current models, with an accuracy of 98.95%, precision 98.2%, recall 98.51%, F-measure 98.35%, and specificity of 98.7%. Findings confirm the potential of diagnostic tools based on ML to advance CAD detection rates, reducing reliance on traditional mechanisms while improving in early diagnosis as well as in treatment planning. The study takes the development of non-invasive, low-cost, and computer-based CAD detection systems closer to the vision of AI-integrated clinical solutions for improved cardiovascular healthcare outcomes.

Machine Learning, CAD, Angiography, PSO

"Enhancing the accuracy of Angiography for the Detection of Coronary Artery Disease using Machine Learning Task", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 2, page no.g741-g757, February-2025, Available :http://www.jetir.org/papers/JETIR2502693.pdf

"Enhancing the accuracy of Angiography for the Detection of Coronary Artery Disease using Machine Learning Task", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 2, page no. ppg741-g757, February-2025, Available at : http://www.jetir.org/papers/JETIR2502693.pdf