• Asad Choudhary
• Vishnu Potdar
• Abhishek Bhatt
• Shubhangi Tidake

Cardiac illness is a major cause of death worldwide, and lifestyle factors such as diet, physical activity and drug use play a crucial role in the progression of the disease. Initial diagnosis and management are important to improve patient outcomes and reduce treatment burden. Medical records of 299 patients with heart problems were examined. These data, which include demographic information, medical history, and medical assessments, are intended to develop a predictive model to classify patients with a medical history of left ventricular dysfunction and heart failure. Using the minority variance method (SMOTE). Evaluate model effectiveness using metrics like accuracy, precision, recall, F1 score and ROC AUC score. The results prove that the 1D-CNN model outperforms deep learning models when used with autoencoders, demonstrating the effectiveness of this approach in predicting cardiac survival. The ability of learning models, especially when augmented with autoencoders, can improve the prediction and management of heart failure. This can lead to significant improvements in patient outcomes and healthcare decisions.

"Harnessing Advanced Deep Learning Techniques for Cardiac Illness Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.f174-f180, May-2025, Available :http://www.jetir.org/papers/JETIR2505616.pdf

"Harnessing Advanced Deep Learning Techniques for Cardiac Illness Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppf174-f180, May-2025, Available at : http://www.jetir.org/papers/JETIR2505616.pdf