In this study, we present a multi-agent chatbot system designed to enhance patient engagement and support for heart attack risk prediction and management. The system comprises three key modules: a Query Agent, which addresses patients’ heart health-related inquiries; a Heart Attack Risk Prediction Module, leveraging advanced machine learning techniques to predict heart attack risk; and a Nutrition Meal Recommendation System, which provides personalized meal plans based on individual health data. We utilized a comprehensive dataset of 7,000 patient records to develop the risk prediction model, achieving an accuracy of 96% and a robust balance between precision and recall. The performance of the LSTM model in the nutrition recommendation module further demonstrated high effectiveness, achieving an accuracy of 97%. The results highlight the potential of integrating these modules into a cohesive system that can improve patient outcomes through informed decision-making and personalized support.<\/p>\n","protected":false},"featured_media":5184,"template":"","meta":{"_acf_changed":false},"schedule":[7],"speaker-category":[6],"class_list":["post-5182","speaker","type-speaker","status-publish","has-post-thumbnail","hentry","schedule-day-2","speaker-category-speakers"],"acf":[],"yoast_head":"\n