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

Objective:Metabolic alkalosis has raised concerns in patients receiving continuous renal replacement therapy (CRRT) via regional citrate anticoagulation (RCA). This study searched for alkalosis-related factors and mechanisms.Methods:It's a retrospective study of alkalosis in patients who received CRRT for at least 12 hours with RCA in a tertiary hospital between April 2017 and April 2020. Demographic features, baseline laboratory results, CRRT metrics and laboratory results at 12h after CRRT was recorded. Patients was grouped based on whether alkalosis exist at 12h after CRRT, and multivariable logistic regression analysis was used to identify risk factors for alkalosis during CRRT with citrate anticoagulation.Results:The 59 patients meeting the inclusion criteria were 49% male, with a mean age of (55±18) years old, and 42% had alkalosis by 12 hours after CRRT. No significant differences in demographic features or laboratory results were observed patients with or without alkalosis. CRRT metrics, including blood flow rate, citrate rate, replacement fluid rate and total effluent rate, were significantly different among groups ( P<0.01). Multivariable Logistic regression analysis indicated that the citrate rate was a risk factor for alkalosis ( OR=1.088, 95% CI 1.020-1.161, P =0.010). In patients receiving no NaHCO 3 and without alkalosis, the linear regression analysis described the relationships of citrate with replacement fluid rate (citrate rate = 0.090 × replacement fluid rate + 56.581; R2 = 0.6918) and total effluent rate (citrate rate = 0.099 × total effluent rate + 2.449). Conclusions:This retrospective observational study demonstrated that CRRT metrics are highly associated with alkalosis after 12 hours of CRRT. Without NaHCO3 infusion, a 10-fold linear correlation was observed between citrate and total effluent rate in patients without metabolic alkalosis.

Objective:To evaluate the utility of pulse oximetry-derived parameters—specifically, the pulse oximetry plethysmographic waveform area under the curve (POP AUC) and the peripheral perfusion index (PPI)—in assessing disease severity and predicting prognosis in patients with sepsis. Methods:In this prospective descriptive study, 68 patients with sepsis were categorized based on illness severity into septic shock and non-shock groups, and by 28-day outcome into survival and non-survival groups. POP AUC, PPI, and lactate (Lac) levels were recorded at 0, 24, 48, 72, and 96 hours after admission. APACHEⅡ and SOFA scores were calculated within the first 24 hours. The prognostic value of these parameters was evaluated. Results:Significant differences were observed between the septic shock and non-shock groups in POP AUC, PPI, Lac (all P < 0.05 except at 96 h), APACHEⅡ, and SOFA scores (all P < 0.05). These differences were most pronounced at admission: POP AUC0 (2475.1 ± 899.0) vs. (4260.3 ± 1028.5), PPI 0 (0.78 ± 0.74) vs. (3.13 ± 2.18), Lac 0 (4.95 ± 4.32) vs. (2.07 ± 1.55), APACHE Ⅱ (16.78 ± 5.59) vs. 11.82 ± 4.89), and SOFA (8.89 ± 3.25) vs. (5.06 ± 2.60). Optimal prognostic cut-off values were 2741.43 for POP AUC, 0.97 for PPI, 2.05 for Lac, 12.5 for APACHEⅡ, and 5.5 for SOFA. ROC curve analysis showed that at 24 hours, POP AUC and PPI had significantly larger AUC values than Lac ( P < 0.05), while no significant differences were found among other parameters. Significant differences between non-survivors and survivors were also found in POP AUC, PPI (at 0, 24, and 48 h), APACHE II, and SOFA (all P < 0.05). No significant differences were observed in PPI (72 h and 96 h) or Lac between the two outcome groups. Conclusions:POP AUC and PPI, as derived from pulse oximetry, are non-inferior to Lac, SOFA, and APACHEⅡ scores in evaluating disease severity and predicting 28-day mortality in sepsis patients. These parameters show promise as practical and non-invasive tools for clinical assessment in sepsis.

Objective:To explore the potential advantages and application prospects of cardiopulmonary resuscitation ventilation mode (CPRV) for ventilation during CPR, through comparing of the resuscitation effect of CPRV, intermittent positive pressure ventilation (IPPV) and impedance threshold device (ITD) during advanced cardiovascular life support (ACLS).Methods:30 miniature landrace pigs [weighing (31.7±4.5) kg] were randomly divided into three groups: CPRV group, IPPV group and ITD group (10 pigs in each group). Each animal received 5 min of chest compressions only CPR after 3 min of untreated ventricular fibrillation. Then in the ACLS stage, chest compressions and mechanical ventilation (tidal volume of 7 mL/kg, respiratory rate 10 times/min) were performed according to the divided groups. Defibrillation was delivered after 16 min of ACLS, and intravenous epinephrine was administered for the pigs without return of spontaneous circulation (ROSC). A second defibrillation was delivered after 2 more minutes of CPR. Blood gases, respiratory parameters, and hemodynamic parameters were collected at baseline, ACLS 8 min and ACLS 16 min. ROSC after defibrillation was also recorded.Results:At ACLS 8 min and 16 min, intrathoracic high pressure and intrathoracic pressure variability of CPRV group were significantly higher than those of IPPV and ITD group, while the absolute value of intrathoracic negative pressure in CPRV group was higher than that in IPPV group (all P <0.01), but no difference was found between CPRV group and ITD group. The levels of arterial pH, PaO 2 and venous oxygen saturation in CPRV group were significantly higher than those in IPPV group and ITD group during ACLS, while PaCO 2 was significantly lower in CPRV group than in IPPV group and ITD group (all P <0.05). Aortic blood pressure, coronary perfusion pressure and carotid blood flow during ACLS in CPRV group were significantly higher than those in IPPV group, and right atrial pressure of CPRV group was significantly lower than that of IPPV group (all P <0.05). Coronary perfusion pressure of CPRV group was significantly higher than that of ITD group at ACLS 16 min but not ACLS 8 min, and there were no differences of aortic blood pressure and carotid blood flow between CPRV group and ITD group. The total ROSC rate in the CPRV group (90%) was significantly higher than that in the IPPV group (30%) and the ITD group (40%) (P <0.05). Conclusion:Ventilation with CPRV during ACLS showed better ventilation, oxygenation, hemodynamic effects and higher ROSC than IPPV and ITD, and the use of CPRV during CPR shows a certain application prospect.

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:Cardiac arrest (CA) represents a significant public health challenge, posing a substantial threat to individual health and survival. To enhance the survival rates of patients experiencing out-of-hospital cardiac arrest (OHCA), Baoan District in Shenzhen City has undertaken exploratory initiatives and practical interventions, yielding promising preliminary outcomes.Methods:1.Innovate emergency medical services by developing a "four-circle integration" system that connects to the hospital. This system encompasses the social emergency medical system, the out-of-hospital emergency medical system, the in-hospital emergency medical service system, and the intensive care treatment system. 2.Develop a comprehensive model for the construction of a social emergency medical training system, characterized by party leadership, government oversight, departmental coordination, professional guidance, technological support, and community involvement, termed the "Baonan Model." Additionally, establish evaluation criteria to assess the effectiveness of the social emergency medical training system in Baonan District; 3. Develop a cardiac arrest registration system and a social emergency medical training management system for Baonan District; 4. Enhance the proficiency in treatment techniques and the quality of cardiopulmonary resuscitation among emergency medical professionals; 5. Strengthen and advance the development of a "five-minute social rescue network" to address the critical "emergency window period." .Result:In Baonan District, 9.18% of the public is trained in emergency medical skills. The bystander CPR rate for OHCA is 26.11%, AED use is at 4.78%, the 30-day survival rate is 6.31%, and the discharge survival rate is 4.44%.Conclusion:The implementation of the aforementioned measures can substantially enhance the survival rate of patients experiencing OHCA at the time of discharge.

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.

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 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).