This article uses the real medical records and web pages of Chinese medicine diagnosis and treatment of hepatitis B to extract structured medical knowledge, and obtains a total of 8,563 entities, 96,896 relationships, 32 entity types, and 40 relationship types. The structured data was stored in the Neo4j graph structure database, and a knowledge graph of Chinese medical diagnosis and treatment of hepatitis B was constructed. The knowledge map is used as a structured data source to provide high‐quality knowledge information for the medical question and answer system based on hepatitis B disease. Applying the deep learning method to the question identification and knowledge response of the question answering system makes the hepatitis B medical intelligent question answering system has important research and application significance. The question‐and‐answer system takes aim at hepatitis B, a public health problem in the world and leverages the advantages of traditional Chinese medicine for diagnosis and treatment. It provides a reference for doctors’ disease diagnosis, treatment, and patient self‐care. Its value is important for the treatment of hepatitis B disease.

Cerebral palsy is one of the most prevalent neurological disorders and the most frequent cause of disability. Identifying the syndrome by patients’ symptoms is the key to traditional Chinese medicine (TCM) cerebral palsy treatment. Artificial intelligence (AI) is advancing quickly in several sectors, including TCM. AI will considerably enhance the dependability and precision of diagnoses, expanding effective treatment methods’ usage. Thus, for cerebral palsy, it is necessary to build a decision-making model to aid in the syndrome diagnosis process. While the recurrent neural network (RNN) model has the potential to capture the correlation between symptoms and syndromes from electronic medical records (EMRs), it lacks TCM knowledge. To make the model benefit from both TCM knowledge and EMRs, unlike the ordinary training routine, we begin by constructing a knowledge-based RNN (KBRNN) based on the cerebral palsy knowledge graph for domain knowledge. More specifically, we design an evolution algorithm for extracting knowledge in the cerebral palsy knowledge graph. Then, we embed the knowledge into tensors and inject them into the RNN. In addition, the KBRNN can benefit from the labeled EMRs. We use EMRs to fine-tune the KBRNN, which improves prediction accuracy. Our study shows that knowledge injection can effectively improve the model effect. The KBRNN can achieve 79.31% diagnostic accuracy with only knowledge injection. Moreover, the KBRNN can be further trained by the EMRs. The results show that the accuracy of fully trained KBRNN is 83.12%.

Objective: Herbal prescriptions hold significant importance in Traditional Chinese Medicine (TCM) diagnosis and treatment, embodying millennia of clinical case summaries and wisdom. Despite numerous proposed methods for herbal prescription recommendation (HPR), significant challenges persist due to the lack of comprehensive clinical data, particularly regarding the relationships between symptoms and herbs. This scarcity poses considerable hurdles for effective HPR modeling. Methods: In this study, we introduced a novel herbal prescription recommendation framework with cross-domain neural collaborative filtering (termed PresRecCDL). The cross-domain learning mechanism is introduced to learn the noise-reduced cross-domain features of herbs and symptoms in the unified space, which alleviated the sparsity of data, and the neural collaborative filtering is utilized to carry out prescription recommendations. Results: Comprehensive experiments demonstrate the superiority of the proposed PresRecCDL model over the SOTA model. The effectiveness of each module in PresRecCDL and model robustness are validated by the ablation and hyper-parameter tuning experiments, respectively. The case study based on network pharmacology further validates the effectiveness of the proposed approach, particularly its scientific rigor and feasibility at the molecular mechanism level. Conclusion: This study contributes to enhancing the performance of the HPR model, ultimately benefiting the efficiency and precision of clinical treatment.

Introduction: Rheumatoid arthritis (RA) is a complex immune-mediated inflammatory disease involving multiple dysregulated signaling pathways and marked inter-individual heterogeneity in treatment response. In real-world clinical practice in China, traditional Chinese medicine (TCM) is widely used for RA management in the form of multi-herbal prescriptions; however, systematic approaches that link heterogeneous TCM prescription patterns to objective clinical signals and underlying molecular mechanisms remain limited. Methods: In this study, large-scale inpatient electronic medical records from two tertiary hospitals were analyzed to identify representative TCM prescriptions used for RA treatment. Frequent closed itemset mining combined with compression strategies was applied to extract stable and non-redundant core prescription patterns across different physicians. Retrospective clinical validation was conducted using longitudinal changes in C-reactive protein (CRP) as an objective biomarker of inflammatory activity. Systems pharmacology approaches—including network pharmacology, network topology-based proximity analysis, and molecular docking—were integrated to characterize shared and prescription-specific molecular targets, signaling pathways, and compound-target interaction feasibility. Results: Five representative core TCM prescriptions were identified. Among 614 eligible patients receiving these prescriptions, all groups exhibited significant post-treatment reductions in CRP levels (p < 0.05), indicating consistent anti-inflammatory signals in real-world settings. Network pharmacology analysis revealed substantial overlap between prescription targets and RA-associated genes (65–115 targets per prescription), with convergent enrichment in key inflammatory pathways, including Toll-like receptor, IL-17, and TNF signaling pathway. Network proximity metrics demonstrated close associations between prescription targets and the RA disease module. Molecular docking further supported the structural plausibility of direct interactions between representative active compounds—such as quercetin and berberine—and core RA-related targets, including TNF-α and PTGS2. Discussion: This integrative analysis demonstrates that heterogeneous TCM prescriptions used in RA converge on shared inflammatory regulatory networks while retaining prescription-specific mechanistic features. By linking real-world clinical evidence with systems-level and structural analyses, this study provides a reproducible framework for mechanistic interpretation of TCM-based therapeutic heterogeneity and generates testable hypotheses for future prospective and stratified RA studies incorporating standardized clinical outcomes.