With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Objective To investigate the effect of silencing alpha tubulin acetyltransferase 1(α-TAT1)on migration behavior of endothelial cells induced by hepatopulmonary syndrome(HPS).Methods Online database Tabula Muris was used to analyze the expression of α-TAT1 in various cell subsets in the lungs.Twenty-four male SD rats were randomly divided into control group(Sham group,n=6)and common bile duct ligation group(HPS group,n=18).The rats in HPS group were euthanasized at 2 and 4 weeks after modelling,and then the expression of α-TAT1 in pulmonary vascular endothelial cells was detected by immunofluorescence colocalization.The sera from the Sham and HPS rats were used to stimulate human umbilical vein endothelial cells(HUVECs)for 12 and 24 h,respectively.Then the obtained HUVECs were divided into 4 groups:Sham serum+siRNA NC group,Sham serum+siRNA α-TAT1 group,HPS serum+siRNA NC group,HPS serum+siRNA α-TAT1 group.The expression levels of α-TAT1 and Ace-α-tubulin in HUVECs were detected by Western blotting.Immunofluorescence assay was applied to observe the levels of polymerized microtubules of α-Tubulin in HUVECs after nocodazole(10 μmol/L)pretreatment to evaluate the stability of microtubule structure.Cell scratch assay combined with cell immunofluorescence assay was employed to observe the nuclear localization of Golgi apparatus and cell migration ability of HUVECs.The angiogenesis ability of HUVECs was tested by in vitro angiogenesis test.Results In vivo and in vitro experiments showed that the expression of α-TAT1 in endothelial cells was significantly increased after HPS inducement.The expression levels of α-TAT1 and Ace-α-tubulin were significantly down-regulated,and the stability of microtubules was weakened in the siRNA α-TAT1 interference group(P＜0.01).In addition,the distribution of GM 130 labeled Golgi apparatus in the protrusion of HUVECs was down-regulated in the siRNAα-TAT1 interference group,as well as the migration ability(P＜0.01).And the length of angiogenesis and network level were also significantly declined(P＜0.01).Conclusion Silencing α-TAT1 reduces the migrαtion and angiogenesis of endothelial cells in HPS,which was associated with weakened stabilization of microtubule.

To summarize the clinical experience of Professor YAN Huimin in pattern identification and treatment for chest tightness variant asthma in children with the method of regulating qi movement. It is believed that children's chest tightness variant asthma is mainly located in lungs and involves liver and spleen， and the core mechanism of the disease is disturbance of qi movement. On the basis of regulating qi， syndrome differentiation and treatment is conducted： for pattern of lung qi deficiency and cold， phlegm-fluid retention， the treatment is appropriate to tonify the lung and benefit qi， and warm phlegm-fluid， which commonly used in modified Yupingfeng Powder （玉屏风散） and Xiaoqinglong Decoction （小青龙汤）； for pattern of phlegm and qi binding constraint， the treatment is appropriate to soothe the liver and resolve constraint， and dissolve phlegm and dissipate masses， which commonly used in modified Banxia Houpo Decoction （半夏厚朴汤） and Jinlingzi Powder （金铃子散）； for pattern of qi deficiency and blood stasis， the treatment is appropriate to tonify the deficiency to reinforce healthy qi， and move qi to invigorate blood， which commonly used in modified Xuefu Zhuyu Decoction （血府逐瘀汤）. It is emphasised that during the treatment process， the developmental dynamics of the disease should be grasped， patterns and treat should be identified， and special attention to the changes of qi movement should be paid.

OBJECTIVE To provide a reference for the safe use of drugs in elderly patients with diabetes mellitus. METHODS Clinical data of elderly diabetic patients aged ≥65 years old and with ≥5 types of long-term medication who were admitted to two tertiary general hospitals in Hebei Province one day a month in 2022 were randomly selected. 2023 Beers criteria and 2023 STOPP criteria were used to analyze the potentially inappropriate medication （PIM） of the patients； multivariate Logistic regression was used to analyze the influencing factors of PIM. RESULTS A total of 227 patients were included. According to the Beers criteria， 157 patients （69.16%） had PIM， and the drugs with the most frequent cases of PIM were proton pump inhibitors （PPIs）， sodium-glucose linked transporter-2 inhibitors and rivaroxaban. According to the STOPP criteria， 142 patients （62.56%） had PIM， and the main drugs involved were non-steroidal anti-inflammatory drugs and PPIs. The results of multivariate Logistic regression analysis showed that patients with age ≥80 years old， with ≥4 other types of chronic diseases， ≥10 types of long-term medication， ≥8 days of hospitalization， medication regimen complexity index scoring ≥20 points of medication regimen， and complication with hypertension， coronary heart disease， and cerebrovascular diseases were influential factors for PIM. CONCLUSIONS The detection rate of PIM is high in elderly patients with diabetes mellitus， and the Beers criteria are more sensitive to PIM than the STOPP criteria. Clinically， we should focus on patients who are elderly， have multiple chronic diseases at the same time， have a large number of long-term medications， have a long hospital stay， have complex medication regimens， and strengthen their rational drug management.

ObjectiveTo explore the mechanism of Naoxintong capsules' intervention in cerebral ischemia-reperfusion by building a mouse cerebral ischemia-reperfusion model based on short-chain fatty acids. MethodC57BL/6J male mice were randomly divided into the sham group， model group， Naoxintong group （158.9 mg∙kg^-1）， and Ginaton group （12.1 mg∙kg^-1） according to the random number table method. The model of cerebral ischemia-reperfusion （MCAO/R） was prepared via the filament occlusion method. The effect of Naoxintong capsules on brain injury in MCAO/R mice was evaluated by the neuroethological score， cerebral infarction area determination， Nissl staining， and immunofluorescence staining. Hematoxylin-eosin （HE） staining and Western blot were employed to evaluate the effect of Naoxintong capsules on the intestinal barrier in MCAO/R mice. The content of short-chain fatty acids in mouse feces was detected by LC-MS/MS. ResultCompared to the sham group， the model group exhibited significant increases in the cerebral infarction area， neuroethological score， and cell apoptosis rate （P<0.01）， with a notable decrease in the number of Nissl bodies （P<0.01）. The protein expression levels of Claudin-1 and Occludin were significantly reduced （P<0.05）. Compared with the model group， the intervention of Naoxintong capsules significantly decreased the cerebral infarction area （P<0.05） and improved the neuroethological score （P<0.01） and cell apoptosis rate （P<0.01）， with the number of Nissl bodies （P<0.01） and expression levels of Claudin-1 and Occludin proteins （P<0.01） increased. LC-MS/MS results showed that compared to the sham group， the model group featured a significantly reduced content of acetic acid， propionic acid， and butyric acid in feces （P<0.01）， while valeric acid， isovaleric acid， and isobutyric acid levels were increased （P<0.01）. The intervention of Naoxintong capsules notably lowered the content of valeric acid， isovaleric acid， and isobutyric acid （P<0.01）. ConclusionNaoxintong capsules can improve brain and intestinal barrier damage and play a protective role in cerebral ischemia-reperfusion by regulating the content of short-chain fatty acids.

Objective To construct the performance evaluation index system of public hospitals,and provide reference for promoting the high-quality development of public hospitals.Methods Delphi method and analytic hierarchy process were used to determine the performance evaluation index system of public hospitals based on performance prism model.Results It established a public hospital performance evaluation system including 5 first-level indicators,16 second-level indicators and 40 third-level indicators of government,staff,patients,suppliers and regulatory agencies.The weights of the five first-level indicators are 0.254 8,0.476 8,0.154 4,0.073 4 and 0.040 6,respectively.Among the 16 second-level indicators,salary,quality and safety,practice environment,medical quality and operation efficiency rank the top 5.The combined weights were 0.268 5,0.174 3,0.165 4,0.080 9 and 0.060 6,respectively.Among the 40 tertiary indicators,the satisfaction of medical staff,the quality control index of single disease,organizational support,the intensity of antibacterial drug use and the case mortality of the low-risk group were investigated.The combined weights were 0.212 0,0.110 0,0.107 0,0.064 3 and 0.0624,respectively.Conclusion The performance evaluation index system of public hospitals based on the performance prism model established is helpful to guide hospitals to think about hospital strategic reform,process optimization and capacity improvement from the multi-dimensional perspective of internal and external stakeholders,so as to improve development performance and promote social harmonious development,and to improve performance,promote high-quality development.

Objective To construct the performance evaluation index system of public hospitals,and provide reference for promoting the high-quality development of public hospitals.Methods Delphi method and analytic hierarchy process were used to determine the performance evaluation index system of public hospitals based on performance prism model.Results It established a public hospital performance evaluation system including 5 first-level indicators,16 second-level indicators and 40 third-level indicators of government,staff,patients,suppliers and regulatory agencies.The weights of the five first-level indicators are 0.254 8,0.476 8,0.154 4,0.073 4 and 0.040 6,respectively.Among the 16 second-level indicators,salary,quality and safety,practice environment,medical quality and operation efficiency rank the top 5.The combined weights were 0.268 5,0.174 3,0.165 4,0.080 9 and 0.060 6,respectively.Among the 40 tertiary indicators,the satisfaction of medical staff,the quality control index of single disease,organizational support,the intensity of antibacterial drug use and the case mortality of the low-risk group were investigated.The combined weights were 0.212 0,0.110 0,0.107 0,0.064 3 and 0.0624,respectively.Conclusion The performance evaluation index system of public hospitals based on the performance prism model established is helpful to guide hospitals to think about hospital strategic reform,process optimization and capacity improvement from the multi-dimensional perspective of internal and external stakeholders,so as to improve development performance and promote social harmonious development,and to improve performance,promote high-quality development.

AIM:To investigate of the effect of Shenqifuzheng injection(SFI)combined with PD-L1 antibody on tumor immune microenvironment and its efficacy.METHODS:A subcutaneous transplanta-tion tumor model for B16F10-LUC melanoma was created.The expression of Ki67,CD31,CD8,CD16,CD163,FOXP3,LY6C,LY6G with labeling antibodies was used to detect CD8+T cells,Treg cells,NK cells,MDSCs cells,centrocytes,and granulocytes in the tumor tissues via immunohistochemistry.Flow cy-tometry was used to measure the ratios of CD11c+,IA/IE+,and CD80+cells in splenic tissue,as well as the ratios of CD8+T,CD4+T,and Treg cells in tumor tissue.Additionally,granulocyte count and NK cell expression were analyzed.RESULTS:The immuno-histochemistry results indicate that the drug admin-istration group effectively suppressed tumor angio-genesis and cell proliferation,while decreasing the expression level of immunosuppressive cytokines CD4+T cells,Treg cells,MDSCs and centroblasts.Ad-ditionally,CD8 and NK cell infiltration was promot-ed compared to the control group.The results of the flow analysis demonstrated a significant in-crease in the expression level of CD8+T cells within tumor tissues,as well as inhibition of CD4+T,Treg,and DC cell infiltration within the spleen in the drug administration group.Additionally,the tumor volume analysis indicated that the drug administra-tion group effectively inhibited tumor growth.The flow results illustrate that the group administering treatment exhibited significant increases in CD8+T cell expression levels in tumor tissue and DC cells in the spleen.Furthermore,the treatment effec-tively inhibited the infiltration of CD4+T and Treg cells.The results also indicate that the treatment significantly reduced tumor growth,with the tumor inhibition rate being better with PD-L1 antibody alone than with the SFI group.Additionally,combin-ing drugs resulted in superior results compared to the PD-L1 antibody group alone.CONCLUSION:SFI combined with a PD-L1 antibody can have synergis-tic anti-tumor effects,potentially enhancing DC cell infiltration and promoting T cell activation.Immu-nohistochemistry results indicate a positive impact on the tumor immune microenvironment.

Objective:To investigate the prognostic value of albumin (ALB), aspartate aminotransferase/alanine aminotransferase ratio (AST/ALT) in patients with acute liver failure (ALF) in hyperacute phase of sepsis which provided the basis for clinical evaluation and prognostic judgment and corresponding treatment options.Methods:A multicenter retrospective cohort study was conducted. Patients with ALF in hyperacute phase of sepsis admitted to Zhoupu Hospital Affiliated to Shanghai Health College, Shanghai Pudong New Area People's Hospital, and Shanghai Oriental Hospital from January 2019 to February 2024 were enrolled. General data such as gender and age of the patients were collected. Lactate dehydrogenase (LDH), liver function indexes [total bilirubin (TBIL), direct bilirubin (DBIL), AST, ALT, AST/ALT, ALB, total protein (TP), globulin (GLB), ALB/GLB ratio (A/G), blood amine, γ-glutamyl transpeptidase (γ-GT)], platelet count (PLT), creatinine, activated partial thromboplastin time (APTT), severity of illness scores [acute physiology and chronic health evaluation Ⅱ (APACHEⅡ), sequential organ failure assessment (SOFA)], serum procalcitonin (PCT), N-terminal pro-brain natriuretic peptide (NT-proBNP), arterial blood lactic acid (Lac) within 24 hours after admission, and whether to use mechanical ventilation, whether to use vasoactive drugs, whether to use artificial liver treatment and prognosis during hospitalization also were collected. The differences of clinical data between patients with different prognosis were compared. The variables with statistically significant differences in univariate analysis were included in multivariate Logistic regression analysis to determine the independent risk factors for death of patients with ALF in hyperacute phase of sepsis during hospitalization. The receiver operator characteristic curve (ROC curve) was drawn to evaluate the predictive value of ALB and AST/ALT for death of patients with ALF in hyperacute phase of sepsis during hospitalization.Results:A total of 73 patients with ALF in hyperacute phase of sepsis were included, with 22 survived and 51 died during hospitalization and the mortality of 69.86%. Compared with the survival group, the patients in the death group had lower ALB, γ-GT within 24 hours after admission and proportion of artificial liver treatment, and higher AST/ALT, SOFA score, LDH and proportion of use of vasoactive drugs. The differences were statistically significant. Multivariate Logistic regression analysis showed that ALB and AST/ALT were the independent risk factors for death in patients with ALF in hyperacute phase of sepsis during hospitalization [ALB: odds ratio ( OR) = 0.856, 95% confidence interval (95% CI) was 0.736-0.996, P = 0.044; AST/ALT: OR = 2.018, 95% CI was 1.137-3.580, P = 0.016]. ROC curve analysis showed that the area under the curve (AUC) of ALB for predicting in-hospital death in patients with ALF in hyperacute phase of sepsis was 0.760 (95% CI was 0.637-0.884, P < 0.001). When ALB ≤ 29.05 g/L, the sensitivity was 68.2%, and the specificity was 76.5%. The AUC of AST/ALT for predicting in-hospital death in patients with ALF in hyperacute phase of sepsis was 0.764 (95% CI was 0.639-0.888, P < 0.001). When AST/ALT ≥ 1.26, the sensitivity was 59.1%, and the specificity was 90.2%. Conclusions:The lower the ALB level, and the higher the AST/ALT within 24 hours after admission, the worse the prognosis of patients with ALF in hyperacute phase of sepsis. ALB and AST/ALT can be used as clinical indicators to evaluate the severity and prognosis of patients with ALF in hyperacute phase of sepsis.

Objective To construct the performance evaluation index system of public hospitals,and provide reference for promoting the high-quality development of public hospitals.Methods Delphi method and analytic hierarchy process were used to determine the performance evaluation index system of public hospitals based on performance prism model.Results It established a public hospital performance evaluation system including 5 first-level indicators,16 second-level indicators and 40 third-level indicators of government,staff,patients,suppliers and regulatory agencies.The weights of the five first-level indicators are 0.254 8,0.476 8,0.154 4,0.073 4 and 0.040 6,respectively.Among the 16 second-level indicators,salary,quality and safety,practice environment,medical quality and operation efficiency rank the top 5.The combined weights were 0.268 5,0.174 3,0.165 4,0.080 9 and 0.060 6,respectively.Among the 40 tertiary indicators,the satisfaction of medical staff,the quality control index of single disease,organizational support,the intensity of antibacterial drug use and the case mortality of the low-risk group were investigated.The combined weights were 0.212 0,0.110 0,0.107 0,0.064 3 and 0.0624,respectively.Conclusion The performance evaluation index system of public hospitals based on the performance prism model established is helpful to guide hospitals to think about hospital strategic reform,process optimization and capacity improvement from the multi-dimensional perspective of internal and external stakeholders,so as to improve development performance and promote social harmonious development,and to improve performance,promote high-quality development.