Cardiac Arrest Prediction Model Using Ensemble Technique

The physician employs a diverse range of laboratory diagnostics, physical examinations, and on occasion, even invasive procedures to ascertain the presence of diseases. It is necessary to have a physician that possesses exceptional training, expertise and skill in the specific field, for detection of the disease in its initial phases. Despite the widespread use of ensemble techniques in disease prediction, here is a notable absence of comprehensive evaluation of regularly utilized ensemble algorithms for highly studied diseases. Consumers typically resort to seeking medical assistance from a doctor or other medical expert only after exhausting all other home remedies without finding relief for their ailments. This is probably a result of insufficient comprehension, as well as other factors related to behavior. This paper introduces a conventional ensemble LSTM model that incorporates data preparation and feature engineering. The model proposed in this research represents major gains in numerous statistical parameters like precision, f score, accuracy and ROC curve in comparison to the other models.