Early Detection of Coronary Heart Disease Using Deep Learning

Diabetes is frequently referred to as the "mother of all diseases" because of its extensive impact on the body's organs. Heart disease is one of the main dangers connected with diabetes, so prompt detection and treatment are essential because neglect can result in major problems. The Optimal Scrutiny Boosted Graph Convolutional LSTM (O-SBGC-LSTM) is a revolutionary technique introduced in this paper. With the goal of early diabetes identification and prevention, this approach improves the SBGC-LSTM by hyperparameter tuning utilizing the Eurygaster Optimization Algorithm (EOA). illustrations. The O-SBGC-LSTM explores the connections between these two domains and efficiently captures key elements in both spatial and temporal configurations. It greatly lowers computing costs while enhancing the model's capacity to learn high-level semantic representations by extending the temporal receptive fields of the top SBGC-LSTM layer through the use of a temporal hierarchical design. Overall, the LSTM model's performance is deemed adequate, and numerous tests show that the suggested hybrid deep learning strategy outperforms conventional machine learning techniques in terms of accuracy. Additionally, emphasis is placed on prevention over treatment. Suggestion tables and fuzzy-based inference approaches are used to improve the prevention process.