• Siddhesh S. Ghadi
• Sharmila Rathod
• Simra Bhombal
• Vallirani Ravulapati
• Sakshi Jangir

This literature survey examines the integration of machine learning (ML) techniques in electrocardiogram (ECG)-based biometric authentication and cardiovascular disease (CVD) prediction. Key studies highlight various ML frameworks addressing challenges such as dataset quality, interpretability, and model accuracy across different application scenarios, including security checks, hospitals, and wearable devices. Notable contributions include advanced data processing techniques, innovative classification models like Decision Trees, Support Vector Machines (SVM), and deep learning architectures, which have demonstrated high predictive accuracy and reliability. The findings emphasize the importance of preprocessing methods and feature selection in enhancing model performance. Furthermore, the survey underscores the potential of combining multimodal bio-signals for improved stroke prognostic predictions, paving the way for real-time health monitoring solutions. Overall, this review serves as a comprehensive resource for researchers and practitioners seeking to leverage ML in biometric systems and cardiovascular healthcare.

Machine Learning, ECG, Biometric Authentication, Cardiovascular Disease Prediction, Deep Learning, Feature Selection, Stroke Prognostic Prediction

"Machine Learning Approaches for Cardiovascular Disease Prediction and Prognostics: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.d400-d405, December-2024, Available :http://www.jetir.org/papers/JETIR2412346.pdf

"Machine Learning Approaches for Cardiovascular Disease Prediction and Prognostics: A Comprehensive Survey", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppd400-d405, December-2024, Available at : http://www.jetir.org/papers/JETIR2412346.pdf