A Graphical Neural Network-Based Chatbot Model for Assisting Cancer Patients with Dietary Assessment in their Survivorship

This research work proposes a novel approach for assisting cancer patients in their dietary assessment before, during, and after the cancer treatment by developing a Graphical Neural Network-based Chatbot (GNNC). In the survivorship phase of the cancer treatment, patients go through several challenges in their regular dietary habits. In order to alleviate these challenges an Artificial Intelligence(AI)-enabled chatbot can recommend a personalized diet to improve health and quality of life (QOL). In this study, GNNC integrates existing Natural Language Understanding (NLU) algorithms to process the textual description of meal preferences and relevant dietary recommendations by enabling an adaptive dialog system. This enables the dynamic conversations between API and chatbot users to gather knowledge about their dietary preferences, restrictions, and nutrition goals. The system places a high priority on user-centricity intending to enhance dietary compliance and patient involvement. The graphical neural network-based chatbot shows promising results in aiding cancer patients on their road toward survivorship after rigorous examination and validation. The model offers a user-friendly and compassionate support system that encourages the best post-cancer eating practices, making it an invaluable tool for patients and healthcare professionals. This study emphasizes the potential of neural network-based chatbots in healthcare support systems and represents a big step toward personalized dietary advice for cancer survivors. Moreover, the integration of GNN and holomorphic fusion enriches the security of the model. The accuracy of our suggested model is 94.11%, which is pretty encouraging.