Integrating Genetic Algorithm and Leverage the Slap Swarm Algorithm to Optimize the LSTM Model to Predict Cardiovascular Disease

Abstract

To efficiently avoid cardiovascular ailments, that are ordinary and a major community health question, early discovery is essential. Problems accompanying network arrangement and acting decay stretch to affect the veracity of demonstrative models, even though skilled are many of the ruling class. This research suggests the OCI-LSTM model, which signifies well-organised and enhanced long-term working memory, as a forceful answer. The LSTM's network design is optimised using the Genetic Algorithm, and superfluous traits are accurately erased utilizing the Salp Swarm Algorithm. The model's efficiency is habitual by confirmation measures, which involve the F1 score, particularity, sense, and veracity. The OCI-LSTM outperforms both the in research comparing Deep Neural System and the Deep Belief System, the outcomes showed that the former achieved 98.12% better accuracy. These advancements have transformed the OCI-LSTM into a paradigm for the efficient, accurate, and early detection of cardiovascular diseases. To ensure a smooth transition into clinical practice, future studies may investigate real-world applications and methods for further improvement.