Traditional Chinese medicine （TCM） diagnostics is a discipline that studies the basic theories and fundamental skills of diagnostic methods， disease diagnosis， and differentiation in accordance with the theories of TCM. The artificial intelligence （AI） technology has gained remarkable achievements in the intelligentization of the four diagnostic methods in TCM and the standardization of differentiation and diagnosis. However， it still faces many challenges. The standardization of clinical data collection is difficult， and the data quality is uneven， which affects the usability of the data. The integration of the four diagnostic information is insufficient. Most instruments can only collect data from a single diagnostic method， lacking overall integrity. The scientific nature of the diagnostic model needs to be improved. The existing models lack dynamics and the reasoning logic of TCM differentiation. The accuracy of intelligent methods needs to be improved， and the existing evaluation indicators cannot fully reflect the practical application effect of the model. Furthermore， the relevant laws and regulations are still not perfect， and data security and patient privacy lack guarantees. The cultivation of compound talents is insufficient， and there is a lack of interdisciplinary talents who are proficient in both TCM and AI. On this basis， this paper expounded on the current development status， difficulties， and bottlenecks of AI in TCM diagnosis and then explored the development trend of AI in the field of TCM diagnosis. It proposed solutions such as optimizing the data collection process， constructing multimodal diagnostic models， facilitating multi-disciplinary exchanges and cooperation， improving laws and regulations， and cultivating compound talents. It is hoped that modern， standardized， normalized， and intelligent TCM diagnosis can be further promoted， thereby providing new impetus and methods for the inheritance and innovation of TCM.

ObjectiveTo investigate the potential mechanism of Danggui Buxuetang （DBT） in the treatment of vascular dementia （VAD）. MethodsSixty male SD rats were randomly assigned to the sham-operated group， model group， DBT low-， medium-， and high-dose groups， and the donepezil group. Except for the sham-operated group， rats in all other groups underwent bilateral common carotid artery ligation. After successful modeling， DBT was administered at doses of 9.2， 18.4， 36.8 g·kg^-1 for the low-， medium-， and high-dose groups， respectively， while the donepezil group received 3 mg·kg^-1 donepezil solution by gavage once daily. After 4 consecutive weeks of drug treatment， rats underwent the Morris water maze test， novel object recognition test， Nissl staining to observe hippocampal neurons， and immunofluorescence staining to detect the expression of neuronal nuclear protein （NeuN） in the hippocampus. Western blot was used to assess the expression of PTEN-induced kinase 1 （PINK1）， Parkin， microtubule-associated protein 1 light chain 3Ⅱ （LC3Ⅱ）， B-cell lymphoma-2 （Bcl-2）， and Bcl-2-associated X protein （Bax）. Transmission electron microscopy was used to observe hippocampal neuronal ultrastructure. Real-time PCR was used to detect the expression of NADPH oxidase subunits p22^phox and p47^phox in hippocampal tissues. The levels of malondialdehyde （MDA）， glutathione （GSH）， superoxide dismutase （SOD）， and total antioxidant capacity were measured to evaluate oxidative stress levels. ResultsIn the Morris water maze test， escape latency changed significantly over time in all groups except the model group. Compared with the sham-operated group， the model group showed significantly prolonged escape latency （P<0.01）. Compared with the model group， rats in the DBT groups and the donepezil group exhibited significantly shorter escape latency （P<0.05， P<0.01）. The number of crossings over the original platform was significantly reduced in the model group compared with the sham-operated group （P<0.01）， whereas rats in the DBT and donepezil groups showed significantly increased platform crossings compared with the model group （P<0.05， P<0.01）. Compared with the sham-operated group， exploration time of new objects was significantly reduced in the model group （P<0.01）. Compared with the model group， exploration time of new objects increased significantly in the medium- and high-dose DBT groups and the donepezil group （P<0.05， P<0.01）， while no significant change was observed in the low-dose DBT group. Compared with the high-dose DBT group， rats in the donepezil group had significantly prolonged escape latency and reduced platform crossings and new-object exploration time （P<0.05）. Nissl staining showed decreased density of healthy neurons in the CA1 and CA3 regions of the hippocampus in the model group， with loss of Nissl bodies and nuclear atrophy or disappearance. In the high-dose DBT group， neuronal density in CA1 and CA3 increased， with neurons arranged closely and displaying normal morphology. Immunofluorescence showed that compared with the sham-operated group， the hippocampal NeuN⁺ cell count in the VAD model group was significantly decreased（P<0.01）， compared with the VAD model group， the hippocampal NeuN⁺ cell count in the high-dose DBT group was significantly increased（P<0.01）. Compared with the sham-operated group， the expression of PINK1， Parkin， LC3Ⅱ， and Bax proteins was significantly increased（P<0.01）， while the expression of Bcl-2 was significantly decreased in the VAD model group（P<0.01）. Compared with the VAD model group， the high-dose DBT group showed significantly decreased expression of PINK1， Parkin， LC3Ⅱ， and Bax proteins（P<0.01）and significantly upregulated Bcl-2 expression（P<0.01）. The medium-dose DBT group exhibited significantly reduced expression of Parkin， LC3Ⅱ， and Bax proteins（P<0.05，P<0.01） and significantly increased Bcl-2 expression（P<0.01）， while no statistically significant differences were observed in the low-dose DBT group. Transmission electron microscopy showed mitochondrial pyknosis， thickened cristae， increased electron density， and the presence of mitochondrial autophagy in the model group. In contrast， hippocampal neurons in the high-dose DBT group contained abundant mitochondria with intact morphology， clear cristae， and uniform matrix. Compared with the sham-operated group， total antioxidant capacity， SOD activity， and GSH levels were significantly decreased， while MDA levels were significantly increased in the model group （P<0.01）. Compared with the model group， total antioxidant capacity and antioxidant levels （SOD， GSH） increased significantly， and MDA decreased significantly in the medium- and high-dose DBT groups （P<0.01）， while no significant changes were observed in the low-dose DBT group. Compared with the sham-operated group， mRNA expression of p22^phox and p47^phox was significantly increased in the model group （P<0.01）. Compared with the model group， expression of p22^phox and p47^phox was significantly decreased in the DBT groups （P<0.05， P<0.01）. ConclusionDBT may exert neuroprotective effects by regulating PINK1/Parkin-mediated mitochondrial autophagy， thereby improving learning and memory abilities and treating VAD.

ObjectiveTo explore the effect and mechanism of Jianpi Xiaoai prescription （JPXA） in ameliorating the 5-fluorouracil （5-FU） resistance of colon cancer. MethodsA HCT116/5-FU resistant cell line was established. Different concentrations （10%， 15%， 20%） of JPXA-containing serum and drug-free serum were used for intervention， and 10% fetal bovine serum （10% FBS）， fibroblast growth factor receptor （FGFR） inhibitor （AZD4547）， and recombinant fibroblast growth factor 2 （FGF2） were set as the control groups. Sensitive HCT116 cells were used in the FGF2 group， while HCT116/5-FU cells were used in other groups. Drug resistance， the level of FGF2 in the cell culture medium， the mRNA level of FGF2 in cells， and the protein levels of FGF2/FGFR and phosphatidylinositol 3-kinase/protein kinase B （PI3K/Akt） were determined. The drug-resistant cells were transplanted into the axilla of nude mice to establish a tumor model. The modeled mice were allocated into model， JPXA （15 g·kg^-1）， 5-FU （0.02 g·kg^-1）， JPXA+5-FU （15 g·kg^-1+0.02 g·kg^-1）， AZD4547 （0.012 5 g·kg^-1）， and AZD4547+5-FU （0.012 5 g·kg^-1+0.02 g·kg^-1） groups. The tumor growth and the protein levels of FGF/FGFR and PI3K/Akt in each group were observed. ResultsThe survival rate of HCT116/5-FU cells decreased in all the JPXA groups with different concentrations. The cell survival rate was decreased most obviously in the 20% JPXA group. The level of FGF2 in the cell culture medium and the mRNA level of FGF2 in cells of each JXPA group decreased， and the decrease was the most significant in the 20% group （P<0.01）. HCT116/5-FU cells showed up-regulated protein levels of FGF2 and phosphorylated fibroblast growth factor receptor 1 （p-FGFR1）， but down-regulated protein level of FGFR1 （P<0.01）. JPXA down-regulated the expression of FGF2 and p-FGFR1 and up-regulated the expression of FGFR1 （P<0.05）. In addition， JPXA down-regulated the expression levels of phosphorylated protein kinase B （p-Akt） and phosphorylated mammalian target of rapamycin （p-mTOR）， while up-regulating the expression levels of Akt and Bcl-2-asociated death promoter （Bad） （P<0.05）. Animal experiments showed that the JPXA combined with 5-FU significantly inhibited the growth of drug-resistant tumors， reduced the protein levels of FGF2， p-FGFR1， phosphorylated phosphatidylinositol-3-kinase （p-PI3K）， p-Akt， and p-mTOR， and increased the expression of Bad. It indicated that JPXA can inhibit the FGF2/FGFR1 signaling in colon cancer and regulate PI3K/Akt and downstream signaling pathways. ConclusionJPXA can ameliorate the chemotherapy resistance of colon cancer through down-regulating FGF2 expression and inhibiting the activation of the PI3K/Akt signaling pathway.

Objective: To characterize perioperative dynamic changes in immune-cell phenotypes and inflammatory cytokines in patients undergoing CPB (cardiopulmonary bypass) cardiac surgery, and to explore their associations with postoperative outcomes. Methods: In this prospective cohort study, 120 adult patients who underwent elective cardiac surgery under CPB at West China Hospital from May 2022 to March 2023 were enrolled. Perioperative immune-cell phenotypes and concentrations of 40 inflammation-related cytokines were measured. The primary outcomes were the sequential organ failure assessment (SOFA) score at 24 h after surgery and ΔSOFA (the peak SOFA score within 48 h after surgery minus the preoperative SOFA score). Secondary outcomes included major adverse cardiovascular events (MACE), acute kidney injury (AKI), respiratory failure, severe liver injury, and infection. Results: The mean age of enrolled patients was 57±10 years. Of these, 52% (62/120) were male and 90% (108/120) underwent valve surgery. During the rewarming to the end of CPB, neutrophil counts rapidly increased (7.39×10 /L vs preoperative 3.07×10 /L, P<0.001), with significant upregulation of CD11b (7.30×10 /L vs preoperative 3.05×10 /L, P<0.001) and CD54 (7.15×10 /L vs preoperative 2.99×10 /L, P<0.001). Lymphocyte counts increased at the end of CPB (1.75×10 /L vs preoperative 1.12×10 /L, P<0.001) but decreased significantly at 24 h after surgery (0.59×10 /L vs preoperative 1.12×10 /L, P<0.001). Plasma analysis showed that multiple pro-inflammatory cytokines increased during CPB and remained elevated up to 24 h after surgery; five chemokines and the anti-inflammatory cytokine IL-10 peaked at the end of CPB. The SOFA score increased from 1 (1, 2) preoperatively to 7 (5, 10) at 24 h after surgery, with a ΔSOFA of 6 (4, 8). Within 30 days after surgery, 48 patients (40.0%) developed AKI, 17 (14.2%) developed infection, 4 (3.3%) developed severe liver injury, 3 (2.5%) developed respiratory failure, and 3 (2.5%) experienced MACE. During the 2-year follow-up, 8 patients (6.7%) experienced MACE and 5 (4.2%) died. Conclusion: Multi-organ dysfunction is common after cardiac surgery under CPB (median ΔSOFA, 6), accompanied by perioperative activation of multiple immune-cell subsets and upregulation of pro-inflammatory, anti-inflammatory, and chemotactic mediators. This study provides data-driven evidence and research clues for further investigation of the associations between CPB-related immune perturbations and postoperative organ dysfunction and clinical outcomes.

ObjectiveTo integrate network pharmacology prediction with multi-level experimental verification methods， and to explore in depth the therapeutic efficacy and potential mechanism of luteolin in treating gout. MethodsDatabases were used to obtain potential pharmacodynamic targets of luteolin. Protein-protein interaction （PPI） network construction and network pharmacology analysis techniques were used to screen key core targets of luteolin in gout treatment. Further biological function enrichment analysis and signaling pathway analysis were performed on these targets. Molecular docking simulation was used to calculate the binding energy between luteolin and potential core targets， clarifying the strength of their interactions. In the in vivo experiment for hyperuricemia， 48 mice were randomly divided into a blank group， a model group， an allopurinol group （5 mg·kg^-1）， and low-dose （10 mg·kg^-1）， medium-dose （30 mg·kg^-1）， and high-dose （90 mg·kg^-1） luteolin groups. For the first three days， the blank and model groups were gavaged with an equal volume of normal saline， while the allopurinol group and luteolin groups were gavaged with corresponding drugs. From day 4 onwards， modeling was performed by intraperitoneal injection at 12：00 daily （normal saline for the blank group， and oxonic acid potassium-hypoxanthine mixture for other groups， with 300 mg·kg^-1 for each group）. Gavage intervention was administered at 18：00 daily （normal saline for the blank/model groups， and corresponding drugs for the treatment groups） until day 7. After sampling， levels of serum uric acid （UA）， alanine aminotransferase （ALT）， and aspartate aminotransferase （AST） were measured. Levels of xanthine oxidase （XO） in the liver and kidney， ATP-binding cassette transporter G2 （ABCG2） and malondialdehyde （MDA） in the kidney， and superoxide dismutase （SOD） in the liver were determined. Renal HE staining was also performed. In the pharmacodynamic study of gouty arthritis， 36 rats were randomly divided into a blank group， a model group， a colchicine group （0.315 mg·kg^-1）， and low-dose （7 mg·kg^-1）， medium-dose （21 mg·kg^-1）， and high-dose （63 mg·kg^-1） luteolin groups. The model was established by vertically injecting 100 µL of 25 g·L^-1 monosodium urate suspension into the posterior lateral aspect of the right ankle joint （the blank group was injected with an equal volume of normal saline）， with repeated injections every two days for reinforcement. From day 2 after modeling， daily gavage administration was performed （normal saline for the blank/model groups， and corresponding drugs for the treatment groups） for a total of 16 days. During the experiment， ankle swelling and pain threshold were measured regularly. After sampling， levels of serum tumor necrosis factor-α （TNF-α）， interleukin-6 （IL-6）， and interleukin-1β （IL-1β） were determined. Ankle joints were subjected to HE， Masson， and safranin O-fast green staining， and HE staining was also performed on ankle synovial tissue and various organs. Western blot was used to determine the expression levels of key proteins in gout-related signaling pathways. ResultsNetwork pharmacology analysis predicted that luteolin may regulate over 20 core targets， such as XO， ABCG2， nuclear factor erythroid 2-related factor 2 （Nrf2）， and SOD， through acting on signaling pathways including NF-κB， phosphoinositide 3-kinase/protein kinase B （PI3K/Akt）， and ABC transporters， thereby affecting uric acid metabolism and inflammatory responses. In the hyperuricemia model， compared with the blank group， the model group showed significantly increased serum UA level， liver and kidney XO activity， renal ABCG2 expression， and liver SOD activity （P<0.01）. Compared with the model group， the high-dose luteolin group significantly reduced serum UA level （P<0.01）， inhibited liver and kidney XO activity （P<0.01）， and significantly increased renal ABCG2 expression and liver SOD activity （P<0.01）， effectively alleviating renal oxidative stress damage and improving renal histopathological status. In the gouty arthritis model， compared with the blank group， the model group showed significant ankle swelling， decreased pain threshold， and significantly increased levels of IL-6， IL-1β， and TNF-α in serum and synovial tissue （P<0.01）. The high-dose luteolin group significantly reduced ankle swelling， prolonged hot plate pain threshold， effectively decreased the levels of the above inflammatory factors in serum and synovial tissue （P<0.01）， and significantly improved ankle pathological damage， showing good analgesic and anti-inflammatory effects. Western blot results further confirmed that luteolin significantly upregulated Nrf2 protein expression and downregulated XO and nucleotide-binding oligomerization domain （NOD）-like receptor protein 3 （NLRP3） expression in animals. ConclusionLuteolin can improve symptoms of hyperuricemia and gouty arthritis， and its potential mechanism may be related to inhibiting XO activity， increasing ABCG2 and SOD levels， and regulating Nrf2-mediated oxidative stress-related pathways.

OBJECTIVE To systematically evaluate the influential factors for all-cause mortality in patients with carbapenem-resistant Gram-negative bacteria （CR-GNB） treated with polymyxin B. METHODS PubMed， Embase， the Cochrane Library， Web of Science， Wanfang Data， VIP， CBM and CNKI were searched to collect clinical studies on all-cause death within 30 days or 28 days after treatment with polymyxin B in patients with CR-GNB infection from database establishment to July 2025. After literature screening， data extraction and evaluation of literature quality， meta-analysis was performed using RevMan 5.4 software. RESULTS A total of 12 studies were included， involving 1 326 patients， among whom 529 patients died， with a mortality rate of 39.89%. Meta-analysis results showed that combined with cardiovascular disease [OR＝2.06， 95%CI （1.37， 3.09）， P ＝0.005 ] ， increased Sequential Organ Failure Assessment （SOFA） score [OR＝1.20， 95%CI （1.07， 1.35）， P ＝0.003 ] ， mechanical ventilation [OR＝2.35， 95%CI （1.65， 3.34）， P ＜0.001 ] ， continuous renal replacement therapy （CRRT） [OR＝2.58， 95%CI （1.67， 3.97）， P ＜0.001 ] ， bloodstream infection [OR＝3.24， 95%CI （2.19， 4.78）， P ＜0.001 ] ， multiple-site infection [OR＝1.51， 95%CI （1.03， 2.20）， P ＝0.03 ] ， septic shock [OR＝3.19， 95%CI （1.94， 5.24）， P ＜0.001 ] ， use of vasoactive drugs [OR＝2.90， 95%CI （1.97， 4.27）， P ＜0.001 ] ， and the occurrence of acute kidney injury （AKI） [OR＝2.17， 95%CI （1.41， 3.36）， P ＜0.001 ] were risk factors for all-cause mortality in patients with CR-GNB infection treated with polymyxin B. Conversely， an extended duration of polymy xin B treatment [OR＝0.92， 95%CI （0.86， 0.99）， P ＝0.03 ] and early administration after CR-GNB infection [OR＝0.47， 95%CI （0.25， 0.85）， P ＝0.01 ] were protective factors. CONCLUSIONS Patients with cardiovascular disease， receiving mechanical ventilation or CRRT， having bloodstream infection， multiple-site infection or septic shock， combining with vasoactive drugs， with AKI and increased SOFA scores have a higher risk of all-cause mortality. Conversely， extending the duration of polymyxin B treatment （beyond 7 days） and early administration within 48 hours after confirmed CR-GNB infection can significantly reduce the risk of all-cause mortality.

BACKGROUND:Arthroscopic anchor repair has become the main treatment method for rotator cuff tears at present.Among them,the insertion status of the anchor is a key factor in the success or failure of the operation.However,currently,the impact of the insertion depth of the anchor on the stress of the bone tunnel and the anchor under different bone density conditions remains unclear.OBJECTIVE:To explore the stress distribution of the bone tunnel and the anchor when the insertion depth of the anchor varies under different bone density conditions by using three-dimensional finite element analysis technology.METHODS:The CT image data of the humerus of volunteers were collected,and the models of the humerus and the anchor were constructed by using Mimics,3-Matic,and Solidworks software.In 3-Matic,holes with distances of 0,2,4,6,and 8 mm from the surface of the humerus were respectively created at the same position of the humerus and assembled with the anchor.In Mimics,values were assigned based on the CT gray value to obtain a model with normal bone mass(T value ≥-1.0).The parameters were changed to construct models with reduced bone mass(-2.5＜T value＜-1.0)and osteoporosis(T value＜-2.5).In each model,a 70 N pulling force was applied to the anchor along the direction tangent to the inner edge of the bone tunnel.The stress distribution and magnitude of the bone tunnel and the anchor when inserted at different depths under different bone density conditions were observed.RESULTS AND CONCLUSION:(1)When the insertion depth was the same,as the bone density decreased,the maximum equivalent stress of the anchor increased,while the maximum equivalent stress of the bone tunnel decreased.(2)When the bone density was the same,as the insertion depth of the anchor increased,the maximum equivalent stress of the anchor decreased.When the insertion depth was 4 mm,the stress of the bone tunnel was the smallest and the distribution was relatively uniform.The stress of the anchor was mainly distributed around the lower anchor hole and the proximal thread,and the stress of the bone tunnel was mainly at the part in contact with the proximal thread.The increase in the insertion depth would change the uniformity and pattern of the stress distribution,while the bone density had a relatively small impact on the stress distribution pattern.(3)It is concluded that the bone density of the humerus is crucial for the anchor repair of rotator cuff tears.It is recommended that clinicians measure the bone density of the greater tuberosity of the humerus before the operation.Excessive insertion depth of the anchor does not significantly increase its stability.Clinicians can conduct personalized preoperative assessments by using the finite element analysis method in combination with the actual situation of patients to achieve the best surgical results.

BACKGROUND:Arthroscopic anchor repair has become the main treatment method for rotator cuff tears at present.Among them,the insertion status of the anchor is a key factor in the success or failure of the operation.However,currently,the impact of the insertion depth of the anchor on the stress of the bone tunnel and the anchor under different bone density conditions remains unclear.OBJECTIVE:To explore the stress distribution of the bone tunnel and the anchor when the insertion depth of the anchor varies under different bone density conditions by using three-dimensional finite element analysis technology.METHODS:The CT image data of the humerus of volunteers were collected,and the models of the humerus and the anchor were constructed by using Mimics,3-Matic,and Solidworks software.In 3-Matic,holes with distances of 0,2,4,6,and 8 mm from the surface of the humerus were respectively created at the same position of the humerus and assembled with the anchor.In Mimics,values were assigned based on the CT gray value to obtain a model with normal bone mass(T value ≥-1.0).The parameters were changed to construct models with reduced bone mass(-2.5＜T value＜-1.0)and osteoporosis(T value＜-2.5).In each model,a 70 N pulling force was applied to the anchor along the direction tangent to the inner edge of the bone tunnel.The stress distribution and magnitude of the bone tunnel and the anchor when inserted at different depths under different bone density conditions were observed.RESULTS AND CONCLUSION:(1)When the insertion depth was the same,as the bone density decreased,the maximum equivalent stress of the anchor increased,while the maximum equivalent stress of the bone tunnel decreased.(2)When the bone density was the same,as the insertion depth of the anchor increased,the maximum equivalent stress of the anchor decreased.When the insertion depth was 4 mm,the stress of the bone tunnel was the smallest and the distribution was relatively uniform.The stress of the anchor was mainly distributed around the lower anchor hole and the proximal thread,and the stress of the bone tunnel was mainly at the part in contact with the proximal thread.The increase in the insertion depth would change the uniformity and pattern of the stress distribution,while the bone density had a relatively small impact on the stress distribution pattern.(3)It is concluded that the bone density of the humerus is crucial for the anchor repair of rotator cuff tears.It is recommended that clinicians measure the bone density of the greater tuberosity of the humerus before the operation.Excessive insertion depth of the anchor does not significantly increase its stability.Clinicians can conduct personalized preoperative assessments by using the finite element analysis method in combination with the actual situation of patients to achieve the best surgical results.

Objective To construct a lung cancer surgery-oriented disease-specific database covering the entire perioperative care pathway, thereby improving the quality and usability of key surgical data elements. Methods Real-world clinical data were extracted from a single-center thoracic surgery department. A standardized data model was established based on the open electronic health record (openEHR) standard. Large language model (LLM), optical character recognition (OCR), and artificial intelligence (AI)-driven techniques were employed to extract, structure, and perform quality control on unstructured clinical narratives, imaging reports, and radiological data, with a focus on capturing surgically relevant perioperative indicator. Results A multimodal database comprising 19 917 patients was established, including 7 930 males and 11 987 females, with ages ranging from 15 to 97 (61.7±9.7) years. The database includes 582 structured data variables, textual report data corresponding to 69 clinical indicators, 13 000 pulmonary function test PDF reports, and chest CT imaging data from 16 884 patients. This database comprehensively covers major information relevant to surgical diagnosis and treatment of lung cancer, significantly improving the completeness and granularity of surgical detail data. Large language models (LLMs) and optical character recognition (OCR) technologies enhanced the efficiency of converting unstructured data into structured formats, while a multi-level manual verification process ensured data accuracy and traceability. The database supports real-world research including comparisons of surgical procedures, prediction of postoperative complications, prognosis assessment, and multimodal data association analyses.

Objective To analyze the epidemiological characteristics of hand, foot, and mouth disease (HFMD) in Shanxi Province from 2012 to 2024, and predict the incidence trend for 2025, and to provide a scientific basis for the formulation of prevention and control strategies. Methods Based on the surveillance data of HFMD in Shanxi Province from 2012 to 2024, the spatial and temporal distribution characteristics and time trends of the disease were analyzed. The ARIMA model was constructed and used to predict the incidence trend in 2025. Results From 2012 to 2024, a total of 254 028 HFMD cases were reported in Shanxi Province, with an average annual incidence rate of 54.17 per 100 000 population, a severe case rate of 0.56%, and a case fatality rate (CFR) of 12.60 per 100 000 population. Joinpoint regression analysis showed that the incidence rate, severe case rate, mortality rate, and case fatality rate all presented a downward trend. The epidemic exhibited obvious seasonal distribution characteristics, with the peak period from April to November, and two incidence peaks in June-July and October-November. The male-to-female incidence ratio was 1.41:1. Children aged 1-5 years accounted for 89.24% of the total cases, among which scattered children (58.48%) and nursery children (33.54%) were the high-risk groups. Linfen City (96.06 /100 000) and Taiyuan City (88.54 /100 000) had relatively high incidence rates. After 2017, the proportion of enterovirus A71 (EV-A71) decreased, while coxsackievirus A16 (Cox-A16) and other enteroviruses became the main epidemic strains. The ARIMA(1,0,1)(0,1,1)₁₂ model predicted that the incidence of HFMD in 2025 would remain at the level of 2023-2024, and the dual-peak characteristic would continue. Conclusion From 2012 to 2024, the overall HFMD epidemic in Shanxi Province generally shows a significant downward trend. The high-risk population includes scattered children and nursery children under 5 years old, with high-incidence areas concentrated in the central and southern regions, requiring focused attention. The seasonal ARIMA model can effectively fit the evolutionary trend of HFMD incidence in Shanxi Province and possesses short-term predictive capability.