Heart Disease Prediction using Deep Learning Techniques

Considering that heart attacks are one of the main causes of unexpected mortality, heart attack prediction is essential. With the help of treatment histories and current health
conditions, the healthcare industry generates substantial volumes of data each day that can be exploited to forecast future heart attacks that could affect a patient. Eventually,
when making decisions this suppressed information from the health care data can be employed. Researchers are concentrating on creating software that can aid doctors in
making decisions about a patient's health, including the diagnosis and outlook of heart disease. The major goal of this paper is to foresee the likelihood of having a heart attack
before it happens. By treating patients early, this can lower the risk to their lives, increase their chances of survival, and lower treatment costs. Through graphical representation of
the outcomes, comparative analysis of the accuracy of deep learning algorithms like Feedforward Neural Network, Long Short-Term Memory (LSTM) and Bidirectional LSTM will
be carried out.