Enhancing Heart Health Prediction with Natural Remedies Through Integration of Hybrid Deep Learning Models

Abstract

Background: Cardiovascular disease remains a leading cause of mortality worldwide, necessitating advanced predictive models to improve early detection and prevention. The integration of natural remedies with machine learning techniques offers a promising approach for enhancing heart disease prediction. Aim: This study aims to develop a hybrid learning model for predicting cardiac disease by combining machine learning algorithms with natural remedies to improve the model’s accuracy and clinical applicability. Methods: A dataset titled “Indicators of Heart Disease (2022 UPDATE)” containing 246,023 patient records was sourced from Kaggle. The hybrid model combines Random Forest (RF) for interpretability and Long Short-Term Memory (LSTM) networks for time-series analysis. Features related to herbal medicines and their impact on heart health were incorporated to enhance predictive accuracy. Results: The hybrid model achieved an accuracy of 100%, demonstrating the potential of integrating traditional medical data with natural remedies to enhance cardiovascular disease forecasting. The inclusion of natural remedies provided a comprehensive tool for clinicians, enabling more precise decision-making. Conclusion: Integrating natural remedies into machine learning models is a promising direction for improving the prediction and early prevention of heart disease. This approach offers a sustainable and accessible solution to cardiovascular healthcare, with the potential to significantly improve patient outcomes.