Intelligent prescription recommendation has become an important research direction in traditional Chinese medicine (TCM), offering new opportunities to support clinical decision-making and promote the modernization of TCM practice. With the rapid development of artificial intelligence (AI), a variety of computational approaches have been proposed to learn prescription patterns from clinical data and generate personalized treatment recommendations. However, despite increasing research activity, systematic and comprehensive reviews of AI-driven methods for TCM prescription recommendation remain limited. In this study, we present a comprehensive review of computational approaches for herbal prescription recommendation (HPR) in TCM. Existing methods are systematically categorized into several major paradigms, including traditional machine learning methods, topic model methods, sequential generative methods, deep learning and graph-based methods, and large language model–based frameworks. In addition to summarizing methodological developments, we also review commonly used public datasets and evaluation metrics in this field. Furthermore, representative models with publicly available implementations are experimentally evaluated on multiple benchmark datasets to provide a comparative analysis of their performance on the HPR task. Finally, we discuss the key challenges that hinder the practical deployment of intelligent prescription recommendation systems, including data heterogeneity, limited interpretability, and insufficient integration of TCM domain knowledge. Future research directions are outlined to facilitate the development of more reliable, interpretable, and clinically applicable AI-assisted HPR systems for TCM.

Background: Diabetic peripheral neuropathy (DPN) is a common chronic complication of diabetes mellitus that significantly impairs patients’ quality of life. Traditional Chinese medicine (TCM), as a major component of complementary and alternative medicine, has accumulated numerous effective formulas for the clinical management of DPN. However, systematic approaches for optimizing TCM formulas remain limited. Objective: To establish a pathway-oriented approach for TCM formula optimization and to evaluate the efficacy and mechanisms of the optimized formula in DPN. Methods: We developed 2 formula optimization algorithms that defined pathway-oriented herbal correlation (HC) and herbal contribution (HO) to screen and construct a new herbal formula, Qihongtongbi (QHTB), for treating Qi deficiency and blood stasis syndrome complicated with DPN. An animal experiment was subsequently conducted to evaluate the therapeutic effectiveness of QHTB. A total of 32 specific-pathogen-free male ob/ob mice (18–20 g) were randomly divided into 4 groups: model, Mudan Granules (MDG), QHTB low- and high-dose groups (n = 8). Ten male C57BL/6J mice (18–20 g) served as the control group. Metabolomics analysis was further employed to elucidate the biological mechanisms underlying the effects of QHTB. Results: Based on our previous study on TCM medication patterns for treating DPN, 22 candidate herbs were selected for formula optimization. The top 5 candidate herbs (total HC = 25.24 × 10 ) exhibited HC values comparable to those of MDG (total HC = 26.1 × 10 ). These herbs were Carthamus tinctorius L. (HC = 5.40 × 10 ), Astragalus mongholicus Bunge (HC = 5.23 × 10 ), Salvia miltiorrhiza Bunge (HC = 5.15 × 10 ), Commiphora myrrha (T. Nees) Engl. (HC = 5.02 × 10 ), and Glycyrrhiza glabra L. (HC = 4.44 × 10 ). HO analysis showed that the cumulative HO of these 5 herbs exceeded 50%. In vivo experiments demonstrated that, compared with the model group, QHTB significantly lowered blood glucose (P < 0.05), enhanced nerve conduction velocity (P < 0.01), improved nociceptive hypersensitivity (P < 0.01), and ameliorated sciatic nerve morphology, with efficacy comparable to MDG. Serum and fecal metabolomics further revealed that QHTB exerted multipathway regulatory effects, among which nicotinate and nicotinamide metabolism represented a key mechanism. Conclusion: In summary, this study provides a methodological reference for the systematic optimization of TCM formulas.

Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI's potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities-particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.
Medicine, Chinese Traditional/methods* ; Artificial Intelligence ; Humans ; Precision Medicine ; Decision Support Systems, Clinical

In 2009,the World Health Organization included snakebite on the list of neglected tropical diseases,acknowledging it as a common occupational hazard for farmers,plantation workers,and others,causing tens of thousands of deaths and chronic physical disabilities every year.This guideline aims to provide practical information to help clinical professionals evaluate and treat snakebite victims.These recommendations are based on clinical experience and clinical research evidence.This guideline focuses on the following topics:snake venom,clinical manifestations,auxiliary examination,diagnosis,treatments,and prevention.

To investigate the therapeutic effect of open reduction and internal fixation (ORIF) on supination external rotation (SER) ankle fractures (AF) and its impact on ankle joint function and range of motion in patients.Methods:The observation group patients were treated with ORIF, while the control group patients were treated with manual reduction combined with plaster external fixation. Both groups of patients were followed up after 3 and 6 months of treatment. Compare the ankle joint function levels of two groups of patients before treatment and after 3 and 6 months of treatment (Kofood score, AOFAS score, Olerud Molander subjective ankle score (OMAS)). Compare the joint range of motion (relative peak force, torque acceleration energy, endurance) between two groups of patients after 3 and 6 months of treatment. Compare the clinical indicators and incidence of adverse events between two groups of patients after 6 months of treatment. T-test was used for comparison between two groups. Multiple group comparisons were conducted using analysis of variance, while pairwise comparisons were conducted using Dunnett-t test. Comparison of count data between groups using χ2 inspections or Fisher exact test. Results:Before treatment, there was no statistically significant difference in the Kofoed score, AOFAS score, and OMAS score between the two groups of patients (all P>0.05). The Kofoed scores of patients in the observation group before treatment and at 3 and 6 months of treatment were (53.78±6.40), (76.73±4.12), and (89.07±5.78) points, respectively. The control group was (52.22±7.08), (71.68±4.82), and (84.05±5.45) points, respectively. The Kofoed scores of patients in both groups were higher than before treatment at 3 and 6 months of treatment (all P<0.05), and the observation group was higher than the control group (all P<0.01).The AOFAS scores of patients in the observation group before treatment and at 3 and 6 months of treatment were (70.13±5.39), (81.62±4.25), and (92.05±4.15) points, respectively. The control group was (69.85±5.41), (79.08±4.60), and (88.92±4.43) points, respectively. The AOFAS scores of patients in both groups were higher than before treatment at 3 and 6 months of treatment (all P<0.05), and the observation group was significantly higher than the control group (all P<0.01).The OMAS scores of the observation group patients before treatment and at 3 and 6 months of treatment were (53.43±5.07), (76.14±4.52), and (85.68±4.14) points, respectively. The control group was (54.42±4.86), (71.39±3.94), and (81.78±4.15) points, respectively. The OMAS scores of the two groups of patients at 3 and 6 months of treatment were higher than before treatment (all P<0.05), and the observation group was higher than the control group (all P<0.01). The fracture healing time (38.85±4.50) days and complete weight-bearing time (66.62±7.14) days of the observation group patients were shorter than those of the control group patients (49.42±5.43) days and (74.39±6.75) days, and the differences between the two groups were statistically significant (t-values were 12.89 and 6.80, respectively, all P<0.01); There was no statistically significant difference in the incidence of adverse events between the two groups of patients (5.41% (4/74) and 9.46% (7/74)), χ2=0.88, P=0.347). Conclusion:ORIF has a good therapeutic effect on SER-AF patients, promotes ankle joint function recovery, and has a low incidence of adverse events, indicating good safety.

Objective To analyze the medication law of core prescriptions and categorized prescriptions of TCM for the treatment of heart failure with preserved ejection fraction(HFpEF);To provide references for clinical prescriptions of HFpEF.Methods The clinical research literature on TCM for HFpEF was retrieved from CNKI,Wanfang Data,VIP,CBM,PubMed,Web of Science,Embase and Cochrane Library from establishment of the databases to November 1,2023.Data mining methods,such as complex network,prescription similarity network and community detection method were used to explore the prescription medication law of HFpEF.Results Totally 142 articles related to TCM treatment of HFpEF were included,containing 146 prescriptions and involving 162 kinds of Chinese materia medica.The most frequently used drugs were represented by Astragali Radix,Salviae Miltiorrhizae Radix et Rhizoma and Poria.The core prescription and the commonly used modified law of HFpEF treatment were obtained by complex network analysis.The core prescription consisted of Astragali Radix,Poria,Salviae Miltiorrhizae Radix et Rhizoma,Glycyrrhizae Radix et Rhizoma,Chuanxiong Rhizoma,Cinnamomi Ramulus,Descurainiae Semen Lepidii Semen,Atractylodis Macrocephalae Rhizoma,Paeoniae Radix Rubra,Ophiopogonis Radix and Angelicae Sinensis Radix.Further based on the prescription similarity network and community detection method,the basic prescriptions of the 3 major community of categorized prescription corresponding to the HFpEF staging and syndrome types were obtained,and the staged diagnosis and treatment medication law with the development of the HFpEF disease course were found.Conclusion Invigorating qi and activating blood circulation,warming yang and promoting diuresis are the main therapeutic principles of HFpEF.Data mining technology provides a feasible method for the analysis of core prescriptions and categorized prescriptions for HFpEF,which can provide a basis for the diagnosis and treatment law and medication experience of HFpEF in TCM.

OBJECTIVE To reveal the pharmacological mechanism of Sofren Injection in the treatment of Qi deficiency and blood stasis syndrome of angina pectoris in coronary heart disease,and to preliminarily verify the reliability of the prediction results by cell experiments.METHODS Firstly,we screened the main chemical components of Sofren injection and their targets from biomedical databases and literature.Then,using the DIAMOnD algorithm,we constructed the angina disease module by screening Qi deficiency and blood stasis syndrome-related genes from the GeneCards and MalaCards databases.Next,we conducted gene functional enrichment analysis of the core targets in the"angina pectoris-Qi deficiency and blood stasis-Sofren Injection"network to identify key pathways.Finally,we performed cell experiments to verify the effect of Sofren Injection on the expression of key pathway proteins in hypoxic H9C2 cardiomyocytes.RESULTS We identified 7 main chemical components of Sofren Injection,targeting a total of 362 genes.We screened 232 known angina pectoris-related genes and added 100 predicted genes by constructing the angina pectoris dis-ease module.A total of 2 960 genes related to Qi deficiency and blood stasis syndrome were obtained.Network topological analysis re-vealed 30 core targets for Sofren Injection in treating coronary heart disease angina pectoris with Qi deficiency and blood stasis syn-drome,including STAT3,EGFR,TNF,and IL-6.Gene functional enrichment analysis identified 82 pathways.Literature analysis combined with the results indicated that STAT3 and the JAK2/STAT3 pathway might be key pathways for Sofren Injection in treating coronary heart disease angina pectoris with Qi deficiency and blood stasis syndrome.Cell experimental results showed significant de-creases in mRNA and protein expression of JAK2 and STAT3 in the SI group and the nicorandil group compared to the model group(P<0.05).CONCLUSION Disease module analysis and cell experiments confirm that STAT3 is a key gene in the pathological mecha-nism of coronary heart disease angina pectoris with Qi deficiency and blood stasis syndrome,and the JAK2/STAT3 pathway is a core pathway for Sofren Injection in treating this condition.This study demonstrates the effectiveness and novelty of combining disease mod-ule for mining the treatment of TCM formulas with specific disease and syndrome.

Objective To develop and evaluate a fine-tuned large language model(LLM)for traditional Chinese medicine(TCM)prescription recommendation named TCMLLM-PR.Methods First,we constructed an instruction-tuning dataset containing 68 654 samples(ap-proximately 10 million tokens)by integrating data from eight sources,including four TCM textbooks,Pharmacopoeia of the People's Republic of China 2020(CHP),Chinese Medicine Clinical Cases(CMCC),and hospital clinical records covering lung disease,liver disease,stroke,diabetes,and splenic-stomach disease.Then,we trained TCMLLM-PR using Chat-GLM-6B with P-Tuning v2 technology.The evaluation consisted of three aspects:(i)compari-son with traditional prescription recommendation models(PTM,TCMPR,and PresRecST);(ii)comparison with TCM-specific LLMs(ShenNong,Huatuo,and HuatuoGPT)and general-domain ChatGPT;(iii)assessment of model migration capability across different disease datasets.We employed precision,recall,and F1 score as evaluation metrics.Results The experiments showed that TCMLLM-PR significantly outperformed baseline models on TCM textbooks and CHP datasets,with F1@10 improvements of 31.80%and 59.48%,respectively.In cross-dataset validation,the model performed best when migrating from TCM textbooks to liver disease dataset,achieving an F1@10 of 0.155 1.Analysis of real-world cases demonstrated that TCMLLM-PR's prescription recommendations most closely matched actual doctors'prescriptions.Conclusion This study integrated LLMs into TCM prescription recommendations,leverag-ing a tailored instruction-tuning dataset and developing TCMLLM-PR.This study will pub-licly release the best model parameters of TCMLLM-PR to promote the development of the decision-making process in TCM practices(https://github.com/2020MEAI/TCMLLM).

OBJECTIVE To reveal the pharmacological mechanism of Sofren Injection in the treatment of Qi deficiency and blood stasis syndrome of angina pectoris in coronary heart disease,and to preliminarily verify the reliability of the prediction results by cell experiments.METHODS Firstly,we screened the main chemical components of Sofren injection and their targets from biomedical databases and literature.Then,using the DIAMOnD algorithm,we constructed the angina disease module by screening Qi deficiency and blood stasis syndrome-related genes from the GeneCards and MalaCards databases.Next,we conducted gene functional enrichment analysis of the core targets in the"angina pectoris-Qi deficiency and blood stasis-Sofren Injection"network to identify key pathways.Finally,we performed cell experiments to verify the effect of Sofren Injection on the expression of key pathway proteins in hypoxic H9C2 cardiomyocytes.RESULTS We identified 7 main chemical components of Sofren Injection,targeting a total of 362 genes.We screened 232 known angina pectoris-related genes and added 100 predicted genes by constructing the angina pectoris dis-ease module.A total of 2 960 genes related to Qi deficiency and blood stasis syndrome were obtained.Network topological analysis re-vealed 30 core targets for Sofren Injection in treating coronary heart disease angina pectoris with Qi deficiency and blood stasis syn-drome,including STAT3,EGFR,TNF,and IL-6.Gene functional enrichment analysis identified 82 pathways.Literature analysis combined with the results indicated that STAT3 and the JAK2/STAT3 pathway might be key pathways for Sofren Injection in treating coronary heart disease angina pectoris with Qi deficiency and blood stasis syndrome.Cell experimental results showed significant de-creases in mRNA and protein expression of JAK2 and STAT3 in the SI group and the nicorandil group compared to the model group(P<0.05).CONCLUSION Disease module analysis and cell experiments confirm that STAT3 is a key gene in the pathological mecha-nism of coronary heart disease angina pectoris with Qi deficiency and blood stasis syndrome,and the JAK2/STAT3 pathway is a core pathway for Sofren Injection in treating this condition.This study demonstrates the effectiveness and novelty of combining disease mod-ule for mining the treatment of TCM formulas with specific disease and syndrome.

Objective To develop and evaluate a fine-tuned large language model(LLM)for traditional Chinese medicine(TCM)prescription recommendation named TCMLLM-PR.Methods First,we constructed an instruction-tuning dataset containing 68 654 samples(ap-proximately 10 million tokens)by integrating data from eight sources,including four TCM textbooks,Pharmacopoeia of the People's Republic of China 2020(CHP),Chinese Medicine Clinical Cases(CMCC),and hospital clinical records covering lung disease,liver disease,stroke,diabetes,and splenic-stomach disease.Then,we trained TCMLLM-PR using Chat-GLM-6B with P-Tuning v2 technology.The evaluation consisted of three aspects:(i)compari-son with traditional prescription recommendation models(PTM,TCMPR,and PresRecST);(ii)comparison with TCM-specific LLMs(ShenNong,Huatuo,and HuatuoGPT)and general-domain ChatGPT;(iii)assessment of model migration capability across different disease datasets.We employed precision,recall,and F1 score as evaluation metrics.Results The experiments showed that TCMLLM-PR significantly outperformed baseline models on TCM textbooks and CHP datasets,with F1@10 improvements of 31.80%and 59.48%,respectively.In cross-dataset validation,the model performed best when migrating from TCM textbooks to liver disease dataset,achieving an F1@10 of 0.155 1.Analysis of real-world cases demonstrated that TCMLLM-PR's prescription recommendations most closely matched actual doctors'prescriptions.Conclusion This study integrated LLMs into TCM prescription recommendations,leverag-ing a tailored instruction-tuning dataset and developing TCMLLM-PR.This study will pub-licly release the best model parameters of TCMLLM-PR to promote the development of the decision-making process in TCM practices(https://github.com/2020MEAI/TCMLLM).