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 analyze the preventive effect of stratified combination nursing guided by Connelly pediatric thrombosis risk model on venous thromboembolism (VTE) in children with traumatic fractures, and provide a theoretical basis for reducing the risk of VTE occurrence.Methods:A randomized controlled trial was conducted, and 94 children with traumatic fractures admitted to Beijing Jishuitan Hospital, Capital Medical University from January to June 2023 were selected as research subjects by convenience sampling method. According to the time of admission, the 47 children admitted from January to March 2023 were included in the control group, and the 47 children admitted from April to June 2023 were included in the observation group. The control group was treated with routine nursing, and the observation group was treated with stratified combination nursing guided by Connelly pediatric thrombosis risk model. The deep vein thrombosis (DVT), VTE, hospitalization related indicators (time to first get out of bed, length of hospital stay and other complications) were compared between the two groups. The platelet count (PLT) and D-dimer levels were compared between the two groups after 1 week of intervention. The scores of the Newcastle Nursing Satisfaction Scale (NSNS) were compared between the family members of two groups sick children.Results:There were 29 males and 18 females in the control group, aged (9.09 ± 1.59) years, and 32 males and 15 females in the observation group, aged (9.34 ± 1.46) years. The total incidence of VTE in the observation group was 2.13% (1/47), which was lower than 12.77% (6/47) in the control group, and the difference was statistically significant ( χ2=3.86, P<0.05). After intervention, the levels of PLT and D-dimer in the control group and observation group were (173.26 ± 20.16)×10 9/L, (168.56 ± 19.66)×10 9/L, (0.40 ± 0.12) mg/L and (0.36 ± 0.10) mg/L, which were lower than (202.71 ± 24.51)×10 9/L, (203.15 ± 25.26) × 10 9/L, (1.19 ± 0.14) mg/L, (1.15 ± 0.11) mg/L before intervention, and the differences were statistically significant ( t values were 6.36 to 36.43, all P<0.05). The time to first get out of bed and the length of hospital stay were (2.21 ± 0.55) and (6.21 ± 1.54) in the control group, and (1.76 ± 0.45) and (5.13 ± 1.21) in the observation group, respectively, and the differences between the two groups were statistically significant ( t=4.34, 3.78, both P<0.05). The total incidence of other complications was 17.02% (8/47) in the control group and 4.26% (2/47) in the observation group, and the difference between the two groups was statistically significant ( χ2=4.03, P<0.05). The satisfaction of family members in the control group was 78.72% (37/47) and 93.62% (44/47) in the observation group, and the difference of sick children between the two groups was statistically significant ( χ2=4.37, P<0.05). Conclusions:Stratified combination nursing guided by Connelly's thrombosis risk model in children can improve the level of D-dimer and PLT, reduce the occurrence of VTE, and shorten the first time of children getting out of bed and staying in hospital, which is conducive to postoperative rehabilitation of children with traumatic fractures.

Objective:To analyze the preventive effect of stratified combination nursing guided by Connelly pediatric thrombosis risk model on venous thromboembolism (VTE) in children with traumatic fractures, and provide a theoretical basis for reducing the risk of VTE occurrence.Methods:A randomized controlled trial was conducted, and 94 children with traumatic fractures admitted to Beijing Jishuitan Hospital, Capital Medical University from January to June 2023 were selected as research subjects by convenience sampling method. According to the time of admission, the 47 children admitted from January to March 2023 were included in the control group, and the 47 children admitted from April to June 2023 were included in the observation group. The control group was treated with routine nursing, and the observation group was treated with stratified combination nursing guided by Connelly pediatric thrombosis risk model. The deep vein thrombosis (DVT), VTE, hospitalization related indicators (time to first get out of bed, length of hospital stay and other complications) were compared between the two groups. The platelet count (PLT) and D-dimer levels were compared between the two groups after 1 week of intervention. The scores of the Newcastle Nursing Satisfaction Scale (NSNS) were compared between the family members of two groups sick children.Results:There were 29 males and 18 females in the control group, aged (9.09 ± 1.59) years, and 32 males and 15 females in the observation group, aged (9.34 ± 1.46) years. The total incidence of VTE in the observation group was 2.13% (1/47), which was lower than 12.77% (6/47) in the control group, and the difference was statistically significant ( χ2=3.86, P<0.05). After intervention, the levels of PLT and D-dimer in the control group and observation group were (173.26 ± 20.16)×10 9/L, (168.56 ± 19.66)×10 9/L, (0.40 ± 0.12) mg/L and (0.36 ± 0.10) mg/L, which were lower than (202.71 ± 24.51)×10 9/L, (203.15 ± 25.26) × 10 9/L, (1.19 ± 0.14) mg/L, (1.15 ± 0.11) mg/L before intervention, and the differences were statistically significant ( t values were 6.36 to 36.43, all P<0.05). The time to first get out of bed and the length of hospital stay were (2.21 ± 0.55) and (6.21 ± 1.54) in the control group, and (1.76 ± 0.45) and (5.13 ± 1.21) in the observation group, respectively, and the differences between the two groups were statistically significant ( t=4.34, 3.78, both P<0.05). The total incidence of other complications was 17.02% (8/47) in the control group and 4.26% (2/47) in the observation group, and the difference between the two groups was statistically significant ( χ2=4.03, P<0.05). The satisfaction of family members in the control group was 78.72% (37/47) and 93.62% (44/47) in the observation group, and the difference of sick children between the two groups was statistically significant ( χ2=4.37, P<0.05). Conclusions:Stratified combination nursing guided by Connelly's thrombosis risk model in children can improve the level of D-dimer and PLT, reduce the occurrence of VTE, and shorten the first time of children getting out of bed and staying in hospital, which is conducive to postoperative rehabilitation of children with traumatic fractures.

The annexins(ANX)family is widely present in the cell membrane,cytoplasm or extracellular matrix.As key tumor regulatory molecules,annexins A(ANX A)family can promote or inhibit invasion and metastasis of breast cancer cells by influencing cell membrane and cytoskeleton formation and participating in signaling pathways.ANX A family also plays a role in the apoptosis of breast cancer cells by regulation of pro-apoptotic proteins and cell cycle independent kinases(CDKs)and related pathways.In addition,ANX A family can also promote therapeutic resistance to a large number of drugs.For instance,ANX A1 enhances triple-negative breast cancer resistance by in-ducing epithelial-mesenchymal transformation.ANX A4 induces resistance by forming ANX A4-Fhit complexes and secretion of exosomes containing ANX A6 promotes paclitaxel resistance in breast cancer cells in a YAP1-dependent manner.So ANX A family may be a new target for breast cancer treatment.

Objective:To construct a representative index system for evaluating pediatric orthopedic nursing quality, providing a basis for hospital pediatric orthopedic nursing quality assessment and monitoring.Methods:From April to July 2023, using the "structure-process-outcome" three-dimensional quality structure model as the theoretical framework, a literature review was conducted, and an item pool was formulated. Through two rounds of Delphi method expert consultations, the hierarchical analysis method was finally employed to determine the indicators and their weights at each level.Results:The effective recovery rates of the questionnaire of the two rounds of expert consultations were 100% (20/20), the authority coefficients of experts were 0.87 and 0.88, the coefficients of variation were 0.00 to 0.27 and 0.00 to 0.24. The Kendell harmony coefficients of the second and third indicators in the two rounds of inquiry were 0.140, 0.166 and 0.192, 0.161(all P<0.05). The final pediatric orthopedic nursing quality evaluation index system included 3 primary indicators, 21 secondary indicators and 83 tertiary indicators. Among the primary indicators, the weight of process quality was the highest at 0.493 4, followed by outcome quality at 0.310 8, and the lowest was structural quality at 0.195 8. In the secondary indicators, "assessment criteria of limb blood circulation" had the highest weight at 0.099 8. Conclusions:The constructed pediatric orthopedic nursing quality evaluation index system covers key aspects and is more operationally feasible. It provides better guidance for nursing interventions and quality control.

Objective: To investigate the levels of cytidine/uridine monophosphate kinase 2(CMPK2) expression in CD4+T cells of systemic lupus erythematosus(SLE) patients and its correlation with clinical indicators. Additionally, to explore whether CMPK2 can induce pyroptosis in CD4+T cells of SLE patients through NLRP3, potentially providing a new target for the diagnosis and treatment of SLE. Methods: RT-qPCR and Western blot analyses were used to assess the gene and protein expression levels of CMPK2 in SLE CD4+T cells and healthy controls(HC). Pearson or Spearman correlation analysis was performed to evaluate the relationship between CMPK2 mRNA expression levels and clinical indicators. Subsequently, the expression levels of pyroptosis-related proteins, including NLRP3, apoptosis-associated speck-like protein containing a CARD(ASC), caspase-1, gasdermin D(GSDMD), and the N-terminal domain of GSDMD(GSDMD-N), were examined in SLE CD4+T cells and HC. Furthermore, the protein expression levels of NLRP3, ASC, caspase-1, GSDMD, and GSDMD-N were detected after silencingCMPK2in SLE CD4+T cells. Results: CMPK2 expression was significantly elevated in SLE CD4+T cells, exhibiting a positive correlation with SLE disease activity index(SLEDAI), anti-dsDNA antibody, anti-nucleosome antibody, anti-C1q antibody, and a negative correlation with complement C3 and C4 levels. Additionally, the expression levels of pyroptosis-related proteins, including NLRP3, ASC, caspase-1, GSDMD, and GSDMD-N significantly increased in SLE CD4+T cells(P<0.05), Moreover, the levels of cytokines IL-1β and IL-18 in the cell culture supernatants were elevated, and there was a notable increase in the rate of cellular pyroptosis(P<0.05). Silencing CMPK2 led to a reduction in the levels of these markers(P<0.05). Conclusion CMPK2 is highly expressed in SLE CD4+T cells and may serve as a diagnostic marker for SLE. Moreover, it is likely involved in the pathogenesis of SLE by promoting CD4+T cell pyroptosis through NLRP3.

Objective:To explore the effect of variable priority cognitive-motor dual-task training in aged cognitive frailty patients with type 2 diabetes mellitus.Methods:From September 2022 to September 2023, a total of 108 aged cognitive frailty patients with type 2 diabetes mellitus were selected in the Department of Endocrinology of North China University of Science and Technology Affiliated Hospital as research subjects.The subjects were divided into three groups in the order of admission, with 36 people in each group.Three groups of patients were intervened for 8 weeks using variable priority cognitive-motor dual-task training (VP group), exercise combined cognitive intervention with sequential task (ST group), and endocrinology routine treatment and nursing (control group), respectively.The scores of mini-mental state examination(MMSE), frailty phenotype(FP) and Berg balance scale(BBS) were compared among the three groups before and after the intervention.Repeated measurement variance analysis was used to compare scale results by SPSS 22.0.Results:(1)The MMSE score of patients before and after intervention had significant interaction effect between time and groups ( F=69.929, P<0.05).The MMSE scores of the VP group and ST group after 8 weeks of intervention were higher than those before intervention and after 4 weeks of intervention, and the MMSE scores of the two groups after 4 weeks of intervention were also higher than those before intervention (all P<0.05).After 4 weeks and 8 weeks of intervention, the MMSE score of the VP group was higher than that of the ST group and the control group, and the MMSE score of the ST group was higher than that of the control group after 8 weeks of intervention(all P<0.05).(2)The FP score of patients before and after intervention had a significant interaction effect between time and groups ( F=46.425, P<0.05).The FP score of the VP group at 8 weeks of intervention (2.64±0.59) was lower than that after 4 weeks of intervention (3.28±0.51) and before intervention (3.56±0.61), and the FP score after 4 weeks of intervention was lower than before intervention (all P<0.05).The FP score of the ST group after 8 weeks of intervention (3.44±0.56) was lower than before the intervention (3.59±0.56) ( P<0.05); After 4 weeks of intervention, the FP score of the VP group was lower than that of the control group (3.36±0.54) ( P<0.05).After 8 weeks of intervention, the FP score of the VP group was lower than that of the ST group and the control group (3.39±0.55) (both P<0.05).(3)The FP score of patients before and after intervention had a significant interaction effect between time and groups ( F=135.791, P<0.05).The BBS scores of the VP group and ST group after 8 weeks of intervention were higher than those before and after 4 weeks of intervention, and the BBS scores after 4 weeks of intervention were also higher than those before intervention (all P<0.05).After 4 weeks of intervention, the BBS score of the VP group was higher than that of the control group ( P<0.05).After 8 weeks of intervention, the BBS score of the VP group was higher than that of the ST group and the control group, and the BBS score of the ST group was also higher than that of the control group (all P<0.05). Conclusion:The variable priority cognitive-motor dual-task training can improve the cognitive function, physical frailty and balance function in aged cognitive frailty patients with type 2 diabetes mellitus, and the intervention effect is better than that of exercise combined cognitive intervention with sequential task and endocrinology routine treatment and nursing.

OBJECTIVE To analyze the hotspots， progress and frontiers of the therapy of recurrent high-grade gliomas， and to provide a reference for the research in this field. METHODS The relevant literature were retrieved from the Web of Science and CNKI during Jan. 1st， 2005-Mar. 14th， 2022. CiteSpace 6.1.R3 software was used to quantitatively analyze the countries， authors， institutions and keywords of the included literature to form visual network maps and generate data. RESULTS A total of 1 019 English papers and 308 Chinese papers were included. The number of international publications kept growing and the number of domestic publications remained stable. Institutions and authors cooperated extensively. The United States featured a large centrality （0.38） and the largest number of publications （442）， with major research institutions such as the University of California San Francisco， University Texas MD Anderson Cancer Center， Dana-Farber Cancer Institute， and important researchers such as Wen， Cloughesy， Reardon， and so on. Domestic research groups were relatively fixed and closed. Internationally， the mechanism of tumorigenesis and drug resistance were the focus of basic research， while there was less basic research in China. Radiotherapy， chemotherapy， targeted therapy and combination therapy were studied the most internationally. Immunotherapy and photodynamic therapy were emerging therapies in recent years. In China， temozolomide and radiotherapy were the main research directions. CONCLUSIONS International attention and investment in the treatment of recurrent high-grade glioma are increasing. The United States has a high influence in this field. Currently， radiotherapy， traditional chemotherapeutic agents and bevacizumab are still the main treatment for recurrent high-grade glioma. Novel therapeutic approaches， including immunotherapy and photodynamic therapy， warrant more attempts and research.

Via an insufficient coat protein complex I (COPI) retrieval signal, the majority of SARS-CoV-2 spike (S) is resident in host early secretory organelles and a tiny amount is leaked out in cell surface. Only surface-exposed S can be recognized by B cell receptor (BCR) or anti-S therapeutic monoclonal antibodies (mAbs) that is the trigger step for B cell activation after S mRNA vaccination or infected cell clearance by S mAbs. Now, a drug strategy to promote S host surface exposure is absent. Here, we first combined structural and biochemical analysis to characterize S COPI sorting signals. A potent S COPI sorting inhibitor was then invented, evidently capable of promoting S surface exposure and facilitating infected cell clearance by S antibody-dependent cellular cytotoxicity (ADCC). Importantly, with the inhibitor as a probe, we revealed Omicron BA.1 S is less cell surface exposed than prototypes because of a constellation of S folding mutations, possibly corresponding to its ER chaperone association. Our findings not only suggest COPI is a druggable target against COVID-19, but also highlight SARS-CoV-2 evolution mechanism driven by S folding and trafficking mutations.

Objective:To investigate the characteristics of nasal flora and the pathogenic role of differential microbiome in patients with allergic rhinitis (AR) and non-allergic rhinitis (nAR).Methods:Thirty-five patients with AR who attended the rhinology outpatient clinic of the Second Hospital of Harbin Medical University from February to July 2022 were selected. A total of 35 nAR patients were selected as the test group, and 20 cases of healthy people with physical examination at the same period were selected as the control group, including 39 males and 51 females, aged 8 to 55 years. 16SrDNA High-throughput sequencing was used to analyze the relative abundance from nasal flora in the three groups of subjects. Alpha diversity index analysis was conducted with R software, and differences between groups were analyzed with LEfSe, Metastats, and t tests. At the same time, the role of microbiome and its relationship with environmental factors were analyzed with R software. Results:There was a significant difference in the bacterial composition of the samples from the three groups, with the relative abundance of Staphylococcus aureus ( P=0.032) and Corynebacterium proinquum ( P=0.032) within the AR group being significantly higher than that of the nAR group, and that of Lactobacillus murinus, Lactobacillus kunkeei, and Alcaligenes faecalis ( P value was 0.016, 0.005, and 0.001, respectively) being significantly lower than that of the nAR group. The relative abundance of Ackermannia muciniphila within the nAR group was higher than that of the control group ( P=0.009). Correlation analysis of environmental factors showed a negative correlation between Lactobacillus kunkeei and IgE ( P=0.044), and a positive correlation between Lactobacillus murinus and age ( P=0.019). AR and nAR random forest prediction models were constructed for the five genera, respectively, and the area under the curve (AUC) of the models of Streptococcus-SP-FF10, Pseudoalteromonas luteoviolacea, Pseudomonas parafulva, Acinetobacter ursingii, and Azotobacter chroococcum in the AR group was 100% (95%CI: 100% to 100%). The AUC for the Pseudomonas parafulva, Azotobacter chroococcum, Closoridium baratii, Turicibacter-SP-H121, and Streptococcus lutetiensis models in the nAR group was 98.4% (95%CI: 94.9% to 100%). Conclusions:The distribution of nasal flora in AR patients, nAR patients and healthy subjects is significantly different, and the changes of bacterial flora abundance are significantly related to the occurrence of AR and nAR. Combined detection of microbiota has the potential to diagnose AR and nAR patients.