NFFGRAM: Nonlinear Multi-feature Fusion and Gated Recurrent Self-Attention Mechanism for Traditional Chinese Medicine Formula Recommendation

Traditional Chinese Medicine (TCM) prescriptions are derived from the distinctive thought process and clinical experiences of Chinese medical theory. With the advent of artificial intelligence (AI), there is an enhanced ability to formulate these prescriptions by analyzing symptom data. However, the inherent sparseness of herb-symptom association data still limits the efficacy of such predictive methods. This study introduces an enhanced bipartite graph diffusion algorithm coupled with a gated recurrent self-attention mechanism for predicting herb and symptom associations. The initial phase involves the reconstruction of the herb-symptom association matrix, leveraging the fractal-weighted K-nearest neighbor algorithm. Subsequently, a method is conceived to extract analogous features between herbs and symptoms, which integrates linear neighborhood similarity with Gaussian kernel similarity, both based on fractal dimensions. The next stage employs a modified bipartite graph diffusion to deduce underlying herb-symptom relationships. This process culminates with the integration of the gated recurrent self-attention mechanism and a confidence scoring system to refine the herb-symptom association predictive matrix at a granular level. We benchmark our results against leading-edge algorithms to ascertain the precision and reliability of our model. Such as improvements of precision@20 by 21.77%, recall@20 by 12.46%, and F1-score@20 by 19.28% compared with the best baseline for the TCM2 dataset. Additionally, comprehensive case studies are undertaken, evaluating recommended prescriptions using insights from contemporary medicine and network pharmacology. The proposed model provides a novel paradigm for enhancing herbal prescription methodologies and TCM herb-based treatments.