Univrsity Of Tehran Press Journal of Information Technology Management 2980-7972 16 1 2024 02 01 An Accurate Prediction Framework for Cardiovascular Disease Using Convolutional Neural Networks 27 43 96373 10.22059/jitm.2024.96373 EN Krishna Lava Kumar Gopu Computer Science and Engineering, Geethanjali College of Engineering and Technology, Hyderabad, Telangana, India. Suthendran Kannan Information Technology, Kalasalingam Academy of Research and Education, Krishnankoil, Srivilliputhur, Tamil Nadu, India. Journal Article 2024 03 14 Cardiovascular-Diseases (CVD) are a principal cause of death worldwide. According to the World-Health-Organization (WHO), cardiovascular illnesses kill 20 million people annually. Predictions of heart-disease can save lives or take them, depending on how precise they are. The virus has rendered conventional methods of disease anticipation ineffective. Therefore, a unified system for accurate illness prediction is required. The study of disease diagnosis and identification has reached new heights thanks to artificial intelligence. With the right kind of training and testing, deep learning has quickly become one of the most cutting-edge, reliable, and sustaining technologies in the field of medicine. Using the University of California Irvine (UCI) machine-learning (ML) heart disease dataset, we propose a Convolutional-Neural-Network (CNN) for early disease prediction. There are 14 primary characteristics of the dataset that are being analyzed here. Accuracy and confusion matrix are utilized to verify several encouraging outcomes. Irrelevant features in the dataset are eliminated utilizing Isolation Forest, and the data is also standardized to enhance accuracy. Accuracy of 98% was achieved by employing a deep learning technique. https://jitm.ut.ac.ir/article_96373_f662129e97c396205659ed39cfa06a94.pdf