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:To investigate the effect of zirconia personalized gingival structure on peri-implant soft and hard tissue stability after single-tooth implant restorations in patients with thin gingival biotypes in the anterior region, with a view to provide a clinical guideline.Methods:This retrospective study included 20 patients with thin gingival biotype and implant restorations in the anterior region. These patients included 9 males and 11 females, and the age was (35.2± 10.3) years. The patients were from the Department of Periodontal Implantology, Stomatology Hospital, Southern Medical University from January 2018 to December 2022. Computer-aided design/computer-aided manufacturing (CAD/CAM) techniques were used to fabricate a titanium base zirconia personalized gingival structure to maintain the soft-tissue perforated gingival contour of the anterior esthetic zone. This structure consists of two modalities: titanium base + zirconia outer crown or titanium base personalized zirconia abutment + zirconia outer crown. Clinical outcomes were recorded immediately and after delivery of the final restorations. Implant retention was recorded, esthetic scoring was performed using the pink esthetic index, the amount of bone resorption at the implant margins was measured based on digitized apical radiographs, and periodontal health was evaluated using the modified plaque index and the modified bleeding index.Results:The survival rate of the 20 implants was 100% after 3 years of wearing the final restorations, with a pink aesthetic score of 9.3±0.9. Bone resorption at the proximal and distal mesial margins of the implants was 0.09 (-0.21, 0.20) mm, 0.17 (-0.12, 0.27) mm after 3 years, respectively, and the difference was not statistically significant when compared to bone resorption immediately after placement of the final restoration [0(0, 0) mm] ( Z=-1.03, P=0.394; Z=-2.05, P=0.065). Conclusions:Zirconia personalized gingival structure maintains the stability of peri-implant hard and soft tissues of thin gingival biotypes in the anterior region.

Objective To summarize the medication law of TCM in the treatment of chronic bronchitis;To provide reference for clinical medication.Methods Medical records of patients with chronic bronchitis who were hospitalized in the Respiratory Department of the First Affiliated Hospital of Henan University of Chinese Medicine from January 1,2016 to December 31,2021 were extracted based on HIS electronic medical record data.After screening,the TCM prescriptions used by patients with chronic bronchitis were input into Excel 2019 to establish a database.Based on the software Lantern 5.0,the latent structure model was learned,hidden variables and explicit variables were obtained,and the model was interpreted.SPSS Modeler 18.0 was used to establish model points with Apriori algorithm for Chinese materia medica with a frequency greater than 6%,to obtain the association rules between drugs,and to analyze the medication law of TCM in treating chronic bronchitis.Results A total of 3 410 cases were included,involving 423 kinds of Chinese materia medica,with a cumulative frequency of 82 766 times.Among them,109 kinds of Chinese materia medica with a frequency of>6 % had a cumulative frequency of 69 845 times.The top five commonly used medicines were Fritillariae Cirrhosae Bulbus,Poria,Atractyodis Macrocephalae Rhizoma,Asteris Radix et Rhizoma,Citri Reticulatae Pericarpium,mainly with medicines of reducing cough and phlegm,antiasthmatic medicine,tonifying deficiency,clearing heat,relieving superficies,promoting blood circulation and removing blood stasis.The medicinal properties were warming,cold and mild,and the main tastes were bitter,sweet and pungent,and the meridians were mainly lung,spleen,liver and stomach meridians.Through analysis of latent structure,49 hidden variables and 149 hidden classes were obtained.Combined with professional knowledge,10 comprehensive clustering models and 21 core formulas were deduced,such as Sangbaipi Decoction,Xuefu Zhuyu Decoction,Xiaoqinglong Decoction,Erchen Decoction,Shashen Maidong Decoction,Liuwei Dihuang Pills,Yinqiao Powder,Zhisou Powder,Yupingfeng Powder,Xuefu Zhuyu Decoction combined with Daotan Decoction,etc.It was concluded that the chronic bronchitis syndrome included phlegm-heat stagnation lung syndrome,qi stagnation blood stasis syndrome,cold fluid attacking lung syndrome,phlegm-dampness accumulation lung syndrome,lung qi and yin deficiency syndrome,kidney yin deficiency syndrome,wind heat attacking lung syndrome,wind cold attacking lung syndrome,lung qi and spleen deficiency syndrome,phlegm stasis interjunction syndrome.A total of 41 strong association rules were screened in the analysis of association rules,including 5 strong association rules for two and 36 strong association rules for three.The high confidence rules were Saposheikovize Radix + Angelicae Sinensis Radix →Atractyodis Macrocephalae Rhizoma,Saposheikovize Radix + Codonopsis Radix → Atractyodis Macrocephalae Rhizoma,Codonopsis Radix + Citri Reticulatae Pericarpium → Atractyodis Macrocephalae Rhizoma;the higher degree of improvement were Bupleuri Radix + Mori Cortex → Scutellariae Radix,Perillae Fructus + Belamcandae Rhizoma → Fritillariae Cirrhosae Bulbus,Armeniacae Semen Amarum + Pinelliae Rhizoma → Citri Reticulatae Pericarpium,etc.Conclusion In the treatment of chronic bronchitis,TCM is mainly used to reduce phlegm,relieve cough and asthma,and the method of promoting blood circulation and removing blood stasis is commonly used to help eliminate phlegm.In addition,TCM pays attention to the application of methods such as tonifying lung and securing the exterior,invigorating spleen and benefiting qi.

ObjectiveThis study aims to explore risk factors for the development of major adverse cardiovascular and cerebrovascular events （MACCEs） in middle-aged and elderly patients with type 2 diabetes mellitus complicated with stable angina pectoris （T2DM-SAP） based on real-world clinical data in traditional Chinese medicine （TCM）， so as to develop a COX proportional risk prediction model and visualize the predicted results using a nomogram. MethodBased on the clinical scientific research information sharing system， the medical records of 586 T2DM-SAP patients （45-94 years old） were collected from January 2012 to December 2019， including age， gender， course of disease， major medical history， laboratory examination， tongue image， pulse image， TCM syndrome， and major treatment drugs. MACCE outcome indicators of patients were obtained by telephone follow-up and re-hospitalization records. The data was divided into a training set and a validation set according to 7∶3. In the training set， COX univariate analysis was used to determine the risk factors for MACCE in T2DM-SAP patients， and then variables were screened by forward-backward stepwise regression method， so as to establish a MACCE risk prediction model and construct a nomogram. The predictive efficacy of the model was reflected by the C-index， receiver operating characteristic （ROC） curve， calibration map， and clinical decision curve. ResultThe history of cerebrovascular disease ［Hazard ratio （HR）=1.983， 95% confidence interval （CI，1.314-2.993）］， low-density lipoprotein （LDL-C/mmol·L^-1）≥4.1［HR=2.683， 95%CI（1.461-4.925）］， dull red tongue ［HR=1.955， 95%CI（1.273-3.002）］， dull purple tongue ［HR=4.214， 95%CI（2.017-8.803）］， white thick coating ［HR=3.030， 95%CI（1.634-9.293）］， thin and weak pulse ［HR=2.233， 95%CI（1.283-3.888）］， and syndrome of wind-phlegm blocking collaterals ［HR=2.007， 95%CI（1.179-3.418）］ were found to be risk factors in middle-aged and elderly T2DM-SAP patients. Insulin ［HR=0.604， 95%CI（0.399-0.914）］， glycosidase inhibitor ［HR=0.627， 95%CI（0.409-0.962）］， and TCM treatment ［HR=0.328， 95%CI（0.214-0.503）］ were protective factors in middle-aged and elderly T2DM-SAP patients. The prediction model was constructed based on the above risk factors. The C-index of the model was 0.818 （95% CI 0.777 -0.859） in the training set and 0.814 （95% CI 0.773-0.855） in the validation set， and the change of C-index over time was plotted. The AUC of patients for 5， 10， 15 years in the training set was 0.71， 0.67， and 0.61. The AUC of patients for 5， 10， and 15 years in the validation set was 0.60， 0.68， and 0.63， respectively. The calibration map and clinical decision curves of 5， 10， 15 years were drawn in the training set and the validation set， respectively. The model was well calibrated and clinically effective. ConclusionThe history of cerebrovascular disease， LDL， dull red tongue， dull purple tongue， white thick coating， thin and weak pulse， and syndrome of wind-phlegm blocking collaterals are risk factors for MACCE in middle-aged and elderly T2DM-SAP patients， and insulin， glycosidase inhibitors， TCM treatment are protective factors for MACCE in middle-aged and elderly T2DM-SAP patients. A clinical prediction model is established accordingly. This model has good discrimination， calibration degree， and clinical effectiveness and provides a scientific basis for the prevention and treatment of MACCE in middle-aged and elderly T2DM-SAP patients.

Objective:To analyze the prevention and treatment of Kaschin-Beck disease in Fu County, Shaanxi Province, so as to provide basis for consolidating the results of Kaschin-Beck disease prevention and control and the treatment of patients with Kaschin-Beck disease.Methods:The epidemiological investigation of data and clinical data Kaschin-Beck disease from 1954 to 2022 were collected from the Fu County Institute for Endemic Disease Prevention and Control and People's Hospital of Fu County in Shaanxi Province, respectively. The retrospective study was used to investigate the prevention and control of Kaschin-Beck disease in Fu County through the adoption of comprehensive measures such as relocation, grain exchange, water improvement, conversion of farmland to forest and so on.Results:In 1954, there were 6 endemic townships and 127 endemic villages of Kaschin-Beck disease in Fu County, with a total population of 78 781. A total of 16 327 patients with Kaschin-Beck disease were detected by X-ray examination, with a detection rate of 20.72%, including 5 434 patients without clinical symptoms. There were 5 850 patients with clinical grade Ⅰ, 3 725 patients with clinical grade Ⅱ and 1 318 patients with clinical grade Ⅲ. In 1975, the first general survey of Kaschin-Beck disease was conducted in the whole county, with a total population of 101 341. A total of 9 575 patients with Kaschin-Beck disease were detected by X-ray examination, with a detection rate of 9.45%, including 3 247 cases without clinical symptoms. Among the patients with symptoms, there were 3 704 cases of clinical grade Ⅰ, 2 006 cases of clinical grade Ⅱ and 618 cases of clinical grade Ⅲ. The patients with Kaschin-Beck disease were mainly local residents, accounting for 93.92% (8 993/9 575). In 1997, 27 320 students aged 7 to 16 years in 342 schools of 15 townships were examined and found that there were 169 cases without clinical symptoms with X-ray changes, only 2 cases with clinical grade Ⅰ, and the detection rate decreased to 0.63%. In 1997, Fu County began to encourage relocation and grain exchange to prevent Kaschin-Beck disease. The relocation targets were mainly the seriously ill villages with new cases among children and poor living conditions. By 1999, a total of 100 households and 469 people were relocated, and by 2020, 1 569 households and 5 334 people were relocated. In 1997 and 1998, measures were taken to improve water quality in 43 natural villages in 6 townships, with 1 591 households and 7 375 people benefiting. In 2010, a general survey of Kaschin-Beck disease was conducted in 15 townships of Fu County, with a total population of 135 858, and 3 424 patients with Kaschin-Beck disease were detected by X-ray examination, with a detection rate of 2.52%. There were 2 885 cases with clinical symptoms, including 1 584 cases with clinical grade Ⅰ, 1 024 cases with clinical grade Ⅱ and 277 cases with clinical grade Ⅲ. Among them, 32 561 minors under 16 years old were examined, and 49 patients with Kaschin-Beck disease were detected by X-ray examination, with a detection rate of 0.15%, and all of them were clinical gradeⅠ patients. In 2014, a total of 73 600 people were surveyed in 170 endemic villages of Fu county, and 2 885 patients with Kaschin-Beck disease were detected by X-ray examination, with a detection rate of 3.92%. Compared with 2010, the number of patients with Kaschin-Beck disease increased zero, and there were no underage patients under the age of 16 for 4 consecutive years. By the end of 2016, 666.67 hm 2 of farmland had been converted to forest in Fu County, involving 9 townships (including communities), 33 administrative villages and 1 993 households. In 2018, another general survey of Kaschin-Beck disease was conducted in Fu County, with a total population of 157 362. A total of 2 308 patients were detected by X-ray examination, with a detection rate of 1.47%. Among them, there were 1 270 cases of clinical grade Ⅰ, 870 cases of clinical grade Ⅱ and 168 cases of clinical grade Ⅲ, and there were no patients with Kaschin-Beck disease under 16 years old in the county for 8 consecutive years (2011-2018). In the same year, 22 cases of Kaschin-Beck disease joint replacement were completed in Fu County, and by January 2022, about 60 cases had completed joint replacement. Conclusion:The prevention and control of Kaschin-Beck disease in Fu County has achieved remarkable results through comprehensive measures such as relocation, grain exchange, water improvement and conversion of farmland to forest.

Objective:To evaluate the role of aryl hydrocarbon receptor (AhR) in the down-regulation of Clara cell secretory protein (CCSP) expression during endotoxin-induced lung injury in rats.Methods:Twenty-four clean-grade healthy male Sprague-Dawley rats, aged 8 weeks, weighing 200-250 g, were divided into 4 groups ( n=6 each) using a random number table method: normal control group (group C), acute lung injury (ALI) group, ALI+ AhR antagonist group, and ALI+ vehicle group. Lipopolysaccharide(LPS) 1 mg/kg was intratracheally instilled to develop the model of lung injury, while the equal volume of normal saline was given instead in group C. At 2 h before LPS injection, AhR antagonist 6, 2′, 4′-trimethoxyflavone solution 5 mg/kg (diluted to 1 ml in dimethyl sulfoxide solution) was intraperitoneally injected in ALI+ AhR antagonist group, while dimethyl sulfoxide solution 1 ml was given in ALI+ vehicle group. The rats were sacrificed under anesthesia at 48 h after LPS administration. The left lung was lavaged and the broncho-alveolar lavage fluid (BALF) was collected for determination of the concentrations of CCSP by enzyme-linked immunosorbent assay, and the expression of CCSP in the bronchial epithelium in right lung tissues was determined by immunohistochemistry. Results:Compared with group C, the expression of CCSP in the bronchial epithelium was significantly down-regulated, and the concentrations of CCSP in BALF were decreased in the other three groups ( P<0.05 or 0.01). Compared with ALI group and ALI+ vehicle group, the histopathological injury was significantly reduced, the expression of CCSP in the bronchial epithelium was up-regulated, and the concentrations of CCSP in BALF were increased in ALI+ AhR antagonist group ( P<0.01). Conclusions:AhR partially mediates the down-regulation of CCSP expression during endotoxin-induced lung injury in rats.

Objective:To explore the predictive value of lactic acid for the adverse prognostic outcomes in patients with acute-on-chronic liver failure combined with infection.Methods:A retrospective analysis was conducted on the clinical data of 208 cases of ACLF combined with infection who were hospitalized from January 2014 to March 2016. Patients were divided into a survival group ( n = 83) and a mortality group ( n = 125) according to the results of a 90-day follow-up. The clinical data were statistically analyzed between the two groups. Multivariate logistic regression with two categorical variables was used to analyze the independent risk factors for 90-day disease mortality and establish a new prediction model. The receiver operating characteristic curve (ROC curve) was used to evaluate the predictive value of lactic acid, the MELD score, the MELD-Na score, lactic acid combined with the MELD score, lactic acid combined with the MELD-Na score, and the new model. Results:The 90-day mortality rate of 208 cases of ACLF combined with infection was 60.1%. There were statistically significant differences in white blood cell count, neutrophil count, total bilirubin (TBil), serum creatinine (Cr), blood urea nitrogen (BUN), blood ammonia, the international normalized ratio (INR), lactic acid (LAC), procalcitonin, the MELD score, the MELD-Na score, hepatic encephalopathy (HE), acute kidney injury (AKI), and bleeding between the two groups. Multivariate logistic regression analysis showed that TBil, INR, LAC, HE, and bleeding were independent risk factors for 90-day mortality in patients with ACLF combined with infection. After the establishment of MELD-LAC, MELD-Na-LAC, and a new prediction model, the ROC curve revealed that the AUC (95% confidence interval) of MELD-LAC and MELD-Na LAC were 0.819 (0.759 ~ 0.870) and 0.838 (0.780 ~ 0.886), respectively, and was superior than the MELD score [0.766 (0.702 ~ 0.823)] and MELD-Na score [0.788 (0.726 ~ 0.843)], with P < 0.05, while the new model had an AUC of 0.924, the sensitivity of 83.9%, specificity of 89.9%, and accuracy of 87.8%, which was higher than LAC, MELD score, MELD-Na score, MELD-LAC, and MELD-Na-LAC ( P < 0.01). Conclusion:Lactic acid is an independent risk factor for mortality in patients with ACLF combined with infection, and it improves the clinical predictive value of MELD and MELD-Na for the prognosis of mortality.

ObjectiveTo establish the quality standard of Liangditang benchmark samples. MethodUltra performance liquid chromatography-quadrupole time-of-flight mass spectrometry （UPLC-QTOF-MS） was used to qualitatively analyze the chemical composition of Liangditang on the basis of molecular and fragment ion peak information with cracking law. The mobile phase was methanol （A）-0.05% phosphate aqueous solution （B） for gradient elution （0-10 min， 5%-23.5%A； 10-20 min， 23.5%A； 20-58 min， 23.5%-63%A； 58-60 min， 63%-90%A）， the flow rate was 0.8 mL·min^-1， and the detection wavelength was 254 nm. Electrospray ionization was employed under positive ion mode， the detection range was m/z 100-1 700. Key quality attributes and sources were determined by comparing with single medicine and reference substances. Through mass transfer analysis of multiple batches from decoction pieces to benchmark samples， high performance liquid chromatography （HPLC） for determining the contents of index components and HPLC detection of characteristic maps were established. Through the determination of 15 batches of benchmark samples， the content range of the index components and the common peaks of the characteristic map were determined. Thin layer chromatography （TLC） was applied to the identification of 5 medicines in the formula. Moisture and dry extract yield of the benchmark samples were determined by drying method. ResultA total of 27 compounds were inferred from the benchmark samples of Liangditang， among which 9 compounds were confirmed by comparison with the control， including catalpol， harpagide， gallic acid， albiflorin， paeoniflorin， verbascoside， angoroside C， cinnamic acid and harpagoside. A method for determining the characteristic maps of the benchmark samples were established and 13 peaks were assigned， and the characteristic peaks were mainly derived from wine-processed products of Rehmanniae Radix， Scrophulariae Radix and wine-processed products of Paeoniae Radix Alba. The similarity between the characteristic map of 15 batches of benchmark samples and the control characteristic map was >0.9. Methods for the determination of paeoniflorin， harpagoside， L-hydroxyproline and glycine were established， and the contents of these four components in 15 batches of benchmark samples were within ±30% of the corresponding mean value， and the transfer rate of decoction pieces to the benchmark samples was stable and controllable. TLC was established to identify 5 prescription drugs （except Ejiao） with two kinds of test solutions， and the results showed that the method had good specificity. The average dry extract yield was 48.06%， and the average moisture was 5.58%， which were within the range of ±10% and ±30% of their mean values， respectively. ConclusionThe quality standard of Liangditang benchmark samples was as follows：the similarity between the benchmark samples and the control characteristic map is >0.9， the contents of paeoniflorin， harpagoside， L-hydroxyproline and glycine are 217-403， 24-46， 634-1 178， 1 253-2 328 mg per dose， the dry extract yield is 43.0%-53.0%， the moisture is 4.0%-7.0%， under the set detection conditions， the benchmark samples have corresponding characteristic spots by comparing with the control herbs of 5 medicines. This quality standard is stable and reliable， which fills the gap in the quality control of Liangditang， and can provide a reference for the establishment of the quality standard of Liangditang granules.

Objective:To evaluate the efficacy of Chaichuan Tongren Mixture supplemented with hysteroscopic recanalization in the treatment of tubal obstructive infertility of liver depression and qi stagnation type.Methods:A total of 60 patients with tubal obstructive infertility of liver depression and qi stagnation type who met the inclusion criteria were selected, between August 2018 and June 2020, and they were divided into the observation group with 31 cases and the control group with 29 cases, according to the random number table method. The control group was treated with hysteroscopic recanalization, while the observation group was given Chaichuan Tongren Mixture on the basis of the control group. Both groups were treated for 4 months and followed up for 12 months. TCM syndromes were scored before and after treatment, and prostaglandin E 2 (PGE 2) was detected by fully automatic biochemical analyzer and levels of TNF-α, CRP and IL-6 were measured by ELISA. The tubal patency of patients after treatment was observed, the pregnancy status was recorded after the end of follow-up and the clinical efficacy was evaluated. Results:The total effective rate was 96.77% in the observation group and that in the control group was 75.86% ( χ2=4.01, P<0.01). The scores of breast distending pain, irregular menstruation, dark purple menstrual flow and lumbosacral pain in the observation group after treatment were significantly lower than those in the control group ( t values were 17.69, 21.67, 20.89, 14.67, 18.20, respectively, all Ps<0.001). After treatment, the levels of serum PGE 2, TNF-α, CRP, and IL-6 were significantly lower in the observation group than those in the control group [(65.31±6.73) ng/L vs. (87.10±8.85) ng/L, t=10.78; (6.90±0.71) ng/L vs. (11.35±1.23) ng/L, t=17.30; (2.47±0.25) mg/L vs. (5.10±0.52) mg/L, t=25.23; (12.38±1.26) ng/L vs. (30.16±3.15) ng/L, t=29.05] ( P<0.01). After treatment, there was statistical significance in the total effective rate of tubal patency of 96.8% (30/31) in the observation group compared to 79.3% (23/29) in the control group ( χ2=4.43, P<0.01). At the end of follow-up, the pregnancy rate was 71.0% (22/31) in the observation group and 44.8% (13/29) in the control group, and the difference was statistically significant ( χ2=4.21, P<0.01). Conclusion:The Chaichuan Tongren Mixture supplemented with hysteroscopic recanalization can reduce the levels of inflammatory mediators and increase the pregnancy rate of patients with tubal obstructive infertility of liver depression and qi stagnation type.

Objective:To investigate the clinical characteristics and therapeutic effect of adult primary hemophagocytic syndrome (HPS).Methods:The clinical data of a patient with primary HPS in the Third Affiliated Hospital of Southern Medical University in July 2017 were retrospectively analyzed, and the related literature was reviewed.Results:The patient was a 53-year-old female without history of basic disease, presenting as repeated high fever, with mutation of STXBP2 (FHL5), and was diagnosed as HPS according to hemophagocytic lymphohistiocytosis (HLH)-2004 criteria. The patient was treated with HLH-2004 regimen, and the efficacy was good. The patient was followed up until May 2021, and the overall survival time was 45 months.Conclusions:The atypical primary HPS and delayed primary HPS are rare, with mild clinical symptoms and only manifested by repeated high fever. Therefore, the gene mutations associated with HPS should be detected as soon as possible to confirm the diagnosis and to treat the disease early.