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*

In the current process of talent cultivation in biology majors,some challenges like teaching content that lags behind the forefront of scientific research,instructional models that deviate from the principles of effective knowledge transmission,and evaluation systems that lack dimensions reflecting scientific innovation.As a strategy of tackling challenges,the Genetic Engineering teaching team,drawing on theoretical analysis and extensive teaching practice,has explored a reform of the instructional model from the perspective of integrating theory with practice.This effort led to the development of a research-oriented teaching model characterized by four iterative stages:knowledge instruction,thinking exercises,practical operation,and feedback evaluation.This model is ground-ed in five core elements of scientific thinking:criticality,coherence,simplicity,logic,and integrity.Imple-mentation follows the four-step framework,emphasizing structured knowledge delivery,cultivation of analytical thinking,hands-on experimentation,and comprehensive feedback.After one semester of application,it was found that through reconstructed knowledge systems,immersive simulations of research contexts,realistic problem-solving of technical bottlenecks and all-round feedback,this teaching model effectively fosters scientific thinking among both instructors and students,significantly enhances students'scientific research ca-pabilities and improves overall teaching effectiveness.

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 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 a prediction model for ventilator-associated pneumonia (VAP) in mechanically ventilated preterm infants in the neonatal intensive care unit (NICU) and to test its clinical effect.Methods:This was a cross-sectional study. A total of 740 preterm infants admitted to the NICU for mechanical ventilation from July 2018 to June 2023 were retrospectively selected as the study subjects, and were divided into the modeling set (518 cases) and the validation set (222 cases) according to the ratio of 7∶3 using the computer-generated random number method. The modeling set was divided into the VAP group (181 cases) and the non-VAP group (337 cases) according to whether VAP occured, and 21 clinical characteristics were analyzed, using single factor difference analysis to screen predictive factors, the independent risk factors of VAP in mechanically ventilated preterm infants were determined by multivariate Logistic regression analysis, and the nomogram model was made by R software. Then, the nomogram model was tested by validating the data of the validation set. The receiver operating characteristic (ROC) curve, Hosmer-Lemeshow goodness-of-fit test, calibration curve and clinical decision curve were used to evaluate the efficacy and practical value of the model.Results:There were 88 males and 93 females in the VAP group, with 156 cases of gestational age<34 weeks and 25 cases of gestational age≥34 weeks. There were 155 males and 182 females in the non-VAP group, with 196 cases of gestational age<34 weeks and 141 cases of gestational age≥34 weeks. Birth weight ( OR=0.114, 95% CI 0.044-0.268, P<0.05) and oral care of breast milk ( OR=0.124, 95% CI 0.0.057-0.249, P<0.05) were protective factors for VAP in mechanically ventilated preterm infants, and Apgar score at 5 min after birth ( OR=2.895, 95% CI 1.318-6.419, P<0.05), serum prealbumin at 72 h of mechanical ventilation ( OR=4.837, 95% CI 2.643-9.063, P<0.05), gastric contents reflux ( OR=6.754, 95% CI 3.156-15.240, P<0.05), and time of mechanical ventilation ( OR=7.784, 95% CI 3.491-18.160, P<0.05) were independent risk factors for VAP in mechanically ventilated preterm infants. The area under the curve (AUC) of the ROC curve of the modeling set was 0.929 (95% CI 0.907-0.950, P<0.01), and the validation set (AUC) was 0.917 (95% CI 0.882-0.952, P<0.01), the model has good discrimination. The C indices of the modeling set and the validation set were 0.93 and 0.92 respectively by sampling 500 times by the Bootstrap method, indicating that the model had good consistency, and the decision curve suggested that the prediction model was far from the extreme curve and the net return value was high, indicating that the nomogram prediction model constructed this time had high prediction value. Conclusions:Birth weight, Apgar score at 5 min after birth, time of mechanical ventilation, oral care of breast milk, serum prealbumin at 72 h of mechanical ventilation, and gastric contents reflux are independent influencing factors for VAP in mechanically ventilated preterm infants. The nomogram prediction model constructed can provide a visual and simple evaluation tool for early identification of high-risk children and reducing the occurrence of VAP.

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.

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.

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 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.