With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

ObjectiveThe malaria parasites remodel the host erythrocyte structure by exporting parasite proteins that interact with the membrane skeleton proteins of red blood cells (RBCs), facilitating their intracellular survival and pathogenicity. Skeleton-binding protein 1 (SBP1) is a conserved exported protein across Plasmodium species. In Plasmodium falciparum, SBP1 has been reported to interact with erythrocyte membrane skeleton proteins 4.1R and spectrin, while its contribution to erythrocyte remodeling and parasite virulence in Plasmodium berghei (Pb) remains unclear. This study aims to determine whether PbSBP1 associates with the host cytoskeletal protein 4.1R and to investigate its role in the remodeling of host RBCs and the pathogenicity of Plasmodium berghei. MethodsIn Plasmodium berghei, the relationship between PbSBP1 and the erythrocyte cytoskeletal protein 4.1R was examined using co-immunoprecipitation. A Pbsbp1 gene knockout mutant of Plasmodium berghei (Pbsbp1∆) was generated based on the principle of double crossover homologous recombination. The deformability of erythrocytes infected with Pbsbp1∆ parasites was assessed using microfluidic methods. Microchannels with an array of cylindrical pillars were used to detect modifications in infected RBC deformability. The infected RBCs were squashed between the rows and recovered between the columns and the transit velocity (μm/s) of infected RBCs travelling through the microchannel was recorded. The component of the erythrocyte membrane skeleton junctional complex, tropomodulin (TMOD), was fluorescently labeled, and the cytoskeletal network of infected erythrocytes was imaged using super-resolution stochastic optical reconstruction microscopy (STORM) to analyze ultrastructural changes in the cytoskeleton of wild-type (WT) and Pbsbp1∆-infected erythrocytes. Actin-based junctional complexes were displayed as individual clusters by the labeled TMOD in the STORM images, and the cluster densities and distances between adjacent clusters of infected RBCs were calculated. Additionally, rodent malaria models (BALB/c mice) and experimental cerebral malaria models (C57BL/6 mice) were employed to monitor the growth of Pbsbp1∆ and WT parasites during the intraerythrocytic stage and their capacity to induce cerebral malaria in mice. ResultsPbSBP1 may participate in the remodeling of infected erythrocytes through direct or indirect interaction with the erythrocyte cytoskeletal protein 4.1R. Microfluidic assays revealed that the deformability of erythrocytes infected with Pbsbp1∆ parasites was significantly enhanced compared to those infected with WT parasites. STORM imaging further demonstrated that the ultrastructure of the erythrocyte cytoskeleton in Pbsbp1∆-infected cells was altered relative to that in WT-infected erythrocytes. The distances between nearest neighbors of clusters had a tendency to increase while the cluster densities were decreased in Pbsbp1∆-infected RBCs compared to WT-infected RBCs. Subsequent phenotypic analysis indicated that the growth rate of Pbsbp1∆ parasites during the intraerythrocytic stage was significantly slower than that of WT parasites, and their ability to induce cerebral malaria in mice was also attenuated. These findings suggest that PbSBP1 is involved in the remodeling of the erythrocyte membrane skeleton, likely through its direct or indirect interaction with protein 4.1R, thereby regulating the deformability of infected erythrocytes and influencing the pathogenicity of the blood-stage parasites. ConclusionThis study establishes a role for PbSBP1 in host erythrocyte remodeling and parasite virulence, providing new research strategies for the prevention and treatment of malaria.

Objective To introduce the causes of accidents and the diagnosis and treatment of two patients with radiation-induced skin injury admitted to our hospital in 2023, and to provide a reference for the clinical treatment of subsequent radiation-induced skin injury. Methods The clinical treatment process of two patients with acute skin injury caused by external radiation exposure were summarized and analyzed. Results The exposure history of the two patients was reconstructed, the flaw detection scenario was simulated, the biological dose and hand skin exposure dose were estimated, and the infrared thermal imaging device was used for dynamic monitoring. A comprehensive analysis was conducted based on clinical manifestations and other data. The diagnosis of “Xie” was excessive exposure combined with acute radiation-induced skin injury on both hands (Grade IV for the right hand palm, index finger, and middle finger and Grade II for the left hand little finger). The diagnosis of “Hao” was acute radiation-induced skin injury on both hands (Grade I). The two patients received different clinical treatment measures: “Xie” was treated with both local and systemic therapies, while “Hao” was mainly treated with systemic therapy. Conclusion After systematic and effective treatment, the radiation-induced skin injuries healed in both patients.

Objective To investigate the role of activating transcription factor 4 (ATF4) in benign prostatic hyperplasia (BPH) in order to elucidate the molecular mechanism underlying BPH progression. Methods Firstly, we analyzed the correlation between the expression of ATF4 and the volume of prostate transition zone in BPH tissues using publicly available datasets. Subsequently, we explored the potential association among ATF4, epithelial-mesenchymal transition (EMT) and BPH through single-cell RNA sequencing (scRNA-seq). Finally, we validated the findings by silencing ATF4 and treating BPH cells with ATF4 protein inhibitors, followed by reverse transcription quantitative polymerase chain reaction (RT-qPCR), CCK-8 assay, and Western blot. Results The expression of ATF4 in BPH tissues exhibited a significant positive correlation with the volume of prostate transition zone (r=0.64, P＜0.05). scRNA-seq analysis revealed that ATF4 was significantly upregulated in the prostate epithelial cells of BPH patients (P＜0.05), and its expression demonstrated a significant positive correlation with the Hallmark EMT singscore (r=0.14, P＜0.05). In vitro experiments further indicated that knockdown of ATF4 led to a significant reduction in the proliferative activity of BPH-1 cells (P＜0.05). Similarly, inhibition of ATF4 activity resulted in a marked decrease in the proliferative capacity and EMT of BPH-1 cells (P＜0.05). Conclusion ATF4 may exert a promoting effect on BPH by modulating the EMT signaling pathway;therefore, ATF4 may serve as a novel therapeutic target of BPH.

Background: Malignant pleural effusion (MPE), a common complication of advanced cancers, is associated with poor prognosis and reduced quality of life. Although host–tumor interactions are known to drive MPE development, the associated immune dynamics during disease progression remain unclear. Using a Lewis lung carcinoma-induced MPE model in C57BL/6JNidfc mice, we systematically evaluated general parameters and immune cell changes at two-day intervals throughout disease progression. Results: The day of Lewis lung carcinoma cell injection into the pleural space was designated as day 0. By day 10 post-injection (p.i.), MPE-bearing mice exhibited ~ 10% body weight loss, marking the experimental endpoint. Pleural tumor mass and pleural effusion volume were minimal up to day 4 p.i. but increased sharply from day 6 onward.CD45⁺ immune cell counts rose over time, and days 6, 8, and 10 p.i. marked key stages of MPE progression. On day 6, B cells, T cells, and natural killer cells, but not macrophages and neutrophils, increased significantly compared to earlier timepoints. By day 8, all immune cell subsets except T cells exceeded day 6 levels, and at day 10, natural killer cell numbers declined while others continued to increase. Besides, the numbers of CD8⁺ T cells, Th1 cells, regulatory T cells, and M2 macrophages progressively increased from day 6 to 10. Based on these data, days 6 and 10 were defined as early and advanced MPE stages, respectively, with distinct immune phenotypes. In advanced MPE, CD8⁺ T cells displayed reduced IFN-γ, TNF-α, Granzyme B, Perforin, FasL, and Ki-67, but upregulated PD-1 and CTLA-4 relative to early stage. Similarly, Th1 cells showed decreased IFN-γ, TNF-α, and IL-2 production along with reduced Ki-67 expression. Advanced-stage M2 macrophages exhibited lower MHC-II levels and impaired phagocytosis, but higher PD-L1 and IL-10 production, while neutrophils showed reduced TNF-α release and phagocytic activity. Conclusions Our findings characterize the temporal immune dynamics associated with MPE progression in a mouse model, revealing a transition from an early immunostimulatory state to a late immunosuppressive state. This study enhances our understanding of MPE immunopathogenesis and provides a foundation for developing precise, stagespecific therapeutic strategies.

Objective To screen for key genes and important pathways common for different etiologies of acute kidney injury(AKI)by pathway-associated deep neural network and multiple machine learning algorithms.Methods AKI microarray datasets GSE30718,GSE37838,GSE53769,GSE108113,GSE125779,GSE99325,and GSE174020 downloaded from the Gene Expression Omnibus(GEO)database were merged,including 60 kidney samples from AKI patients and 79 kidney samples from healthy controls.They were divided(8∶2)into training sets and test sets,and were used to train and evaluate pathway-associated deep neural network and 4 machine learning algorithms,including least absolute shrinkage and selection operator(LASSO),random forest(RF),support vector machine-recursive feature elimination(SVM-RFE),and extreme gradient boosting(XgBoost),to screen for common key genes and pathways of different etiologies of AKI.The downloaded datasets GSE99340 and GSE1563 were merged,including 43 kidney samples from AKI patients and 36 kidney samples from healthy controls,which were used as external validation sets for LASSO model and nomogram performance test based on the final screened genes.The pathway-associated deep neural network and machine learning algorithms were evaluated using receiver operating characteristic curves,precision,recall,accuracy,and F1-score.The immune cell infiltration characteristics were explored in AKI via cell-type identification by estimating relative subsets of RNA transcripts(CIBERSORT),and Pearson correlation coefficients were used to evaluate the correlation between the final screened common key genes and immune cell infiltration levels.Results The pathway-associated deep neural network trained by 5-fold cross validation produced an area under curve(AUC)of 0.914 5±0.007 0,a precision of 0.750 0±0.044 0,a recall of 0.923 1±0.048 0,an accuracy of 0.838 7±0.016 0,and an F1-score of 0.827 6±0.020 0 in the test set,yielding a robust and highly accurate classification performance for AKI,and identified key pathways and a subset of candidate genes.The 4 machine learning algorithms all achieved high discriminative performance for AKI in the test set with AUC≥0.860,precision≥0.750,recall≥0.800,and F1-score≥0.774,and screened 7 common key genes for AKI with different etiologies,including CD86,C-X-C motif chemokine ligand 10(CXCL10),dynamin 2(DNM2),proto-oncogene FOS,transcription factor 12(TCF12),VGF nerve growth factor inducible(VGF),and A kinase anchoring protein 5(AKAP5).Based on the final screened common key genes,the LASSO model had an AUC of 0.940 4 for the test set and an AUC of 0.944 4 for the external validation,and the model showed a very high discriminatory ability for the AKI,which demonstrated the overall regulatory performance of the genes.The nomogram constructed based on the screened 7 genes demonstrated the highest classification performance with an AUC of 0.928 9,validating the outstanding contribution and overall action performance of the screened individual genes.Immune cell infiltration analysis showed that there were significant differences in B cells na?ve,mast cells activated,monocytes,macrophages M1,B cells memory,and dendritic cells activated between AKI samples and healthy control samples(all P＜0.05).Macrophages M1 and monocytes were positively correlated with CD86 and CXCL10,mast cells activated were positively correlated with FOS,and B cells na?ve were negatively correlated with CD86 and CXCL10(all P＜0.01).Mast cells activated were positively correlated with VGF and negatively correlated with CD86 and TCF12,while memory B cells were positively correlated with CD86(all P＜0.05).Conclusion Strategy combining pathway-associated deep neural network and multiple machine learning classifiers can mine high-value key genes from high-dimensional,complex and heterogeneous transcriptomic data as potential targets for therapeutic interventions in AKI.

Objective To construct a medical consumables selection indicator system based on analytic hierarchy process(AHP)and fuzzy cluster method.Methods Firstly,a medical consumables selection indicator system was established preliminarily with the literature research results and actual situation of hospital consumables management;secondly,13 experts in related fields were selected to execute two rounds of online questionnaires,the expert weights were determined with AHP,the importance of each selection indicator was scored by the expert evaluation method and fuzzy cluster method,and consistency analysis was carried out on the two rounds of expert evaluation results;finally,the final medical consumables selection indicator system was built with the 100-point scale.Results The constructed medical consumables selection indicator system was composed of 5 primary indicators,12 secondary indicators and 38 tertiary indicators.The primary indicators included consumables quality,clinical demand,cost-effectiveness,supply capacity and after-sales service,with the percentage-based scores being 27,25,14,26 and 8,respectively.Conclusion The medical consumables selection indicator system based on AHP and fuzzy cluster method with high reliability provides effective and reliable references for medical institutions to select medical consumables.

With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.

Objective:To evaluate the sample preparation proficiency and storage proficiency of 11 clinical biobanks in Beijing through simulated experiments, and to establish an assessment method for the quality comparability of biological samples.Methods:An exploratory research design was adopted. In November 2023, artificial composite serum quality control materials containing six recombinant human protein markers—recombinant human alanine aminotransferase (rhALT), recombinant human aspartate aminotransferase (rhAST), recombinant human creatine kinase (rhCK), recombinant human creatine kinase-MB (rhCK-MB), recombinant human B-type natriuretic peptide (rhBNP), and recombinant human troponin I (rhTNI)—were distributed to 11 clinical biobanks in Beijing City. Sample preparation and storage followed the standardized operating procedures. Proficiency differences were assessed through statistical analysis.Results:Three-way repeated measures ANOVA revealed all six protein markers showed a declining trend over storage time in ultra-low-temperature environments ( F values 11.68-4 179.66, all P<0.01). However, neither long-term/temporary refrigerator types ( F values 0.01-1.23, all P>0.05)nor placement locations within refrigerators significantly affected the stability of these six proteins ( F valus 0.03-1.47, all P>0.05). The biases in detection results for rhALT, rhAST, rhTNI, and rhBNP at different storage time points were within the allowable bias limits for each item, supporting their use as markers for protein stability in biobank samples. All 11 institutions passed the storage proficiency assessment. In the preparation proficiency assessment, deviations were observed in post-preparation sample results, with a notably high out-of-control rate for rhCK (36.36%). Conclusion:Sample preparation proficiency can serve as a quality control metric for clinical biobanks. Future external quality assessment systems for biobanks should focus on sample preparation rather than storage processes.

Objective To design a training device of the flight crew for plateau normobaric low-oxygen acclimatization so as to enhance the flight crew's ability to adapt to the low oxygen environment after rushing into the plateau and reduce the incidence of acute plateau reaction.Methods The training device comprised a plateau environment simulation controller,a multimodal physiological acquisition system and hypoxia exercise training evaluation software.The plateau environment simulation controller was composed of an environment monitor for plateau acclimatization,two composite sensor sets,a control valve and an alarm device;the multimodal physiological acquisition system was made up of 20 groups of vital signs acquisi-tion devices,with a wearable dynamic ECG and respiration recorder,a wrist oximeter and an arm sphygmomano-meter included in each group.The hypoxia exercise training evaluation software was developed with a B/S architecture,Java language and JetBrains 2020.3.Results The training device proved to have the simulation altitude ranging from 0 to 6 000 m and facilitated simultaneous training of 20 persons for normobaric low-oxygen acclimatization,screening for hypoxia endurance,real-time monitoring of physiological parameters and assessment of training effect,with none of the trainees having acute plateau reaction.Conclusion The training device assists the flight crew for plateau normobaric low-oxygen acclimatization,and can be used for acclimatization training before plateau missions.[Chinese Medical Equipment Journal,2025,46(8):18-24]