<p>This paper proposes a novel deep learning-based approach for analyzing the relationship between eating habits and heart health. The method leverages wearable technology, smartphone applications, and food diaries to gather comprehensive dietary data. This data is then processed by recurrent neural networks (RNNs) and convolutional neural networks (CNNs) to extract significant dietary patterns and features relevant to cardiovascular health. By integrating dietary information with other health-related data, a comprehensive model is constructed to analyze the intricate interactions between lifestyle, nutrition, and cardiovascular outcomes. This approach facilitates the generation of personalized dietary recommendations and enables a more precise and objective evaluation of eating habits. To validate the effectiveness of the proposed methodology, an LSTM model is implemented and achieves a precision of 0.982, indicating a high percentage of true positive predictions. Additionally, the model demonstrates an accuracy of 98.9%, highlighting its ability to classify nearly all instances accurately. These exceptional results suggest the suitability of the modified LSTM model for further investigation and potential real-world implementation.</p>