Blood transfusion is an important life-support measure in modern medicine. As clinical demand for transfusion continues to rise, blood supply remains under persistent strain, making the efficient utilization of this precious medical resource a critical component of blood management. Accurate prediction of transfusion needs is of great significance for optimizing blood resource allocation and conserving blood products. Traditional transfusion decision-making relies on clinical experience and simplified scoring systems, which are insufficient to meet the demands of precision medicine. Machine learning (ML) technology can integrate multidimensional data—including demographic characteristics, laboratory indicators, surgical information, and dynamic physiological waveforms—to construct high-performance predictive models, offering a new approach to transfusion prediction. This article systematically reviews the application progress of ML in transfusion prediction across clinical scenarios such as trauma, the perioperative period, and obstetrics. In trauma, ML has been applied to early massive transfusion prediction, prehospital transfusion decision-making, and precise prediction in pediatric trauma. In the perioperative field, applications span specialties including traumatic brain injury, orthopedic surgery, cardiovascular and major vascular surgery, and hepatic surgery. In obstetrics, models can effectively predict postpartum hemorrhage and transfusion requirements associated with cesarean section. Studies have shown that algorithms such as random forest, gradient boosting machines, and deep neural networks achieve area under the receiver operating characteristic curve (AUC) values of 0.83-0.98 in massive transfusion prediction, 0.75-0.97 in perioperative scenarios, and 0.80-0.89 in obstetric transfusion prediction—significantly outperforming traditional scoring tools. However, current studies are generally limited by single-center retrospective designs, insufficient external validation, and inadequate reporting standards; limited model interpretability and challenges in clinical integration further constrain practical translation. Future research should focus on constructing multicenter data cohorts, integrating multimodal data, conducting prospective implementation studies, and deeply embedding models within electronic health record systems, thereby advancing the application of ML to optimize clinical transfusion decision-making.

Objective : To explore the role of lysophosphatidylcholine acyltransferase 3(LPCAT3) in Erastin-induced ferroptosis of acute myeloid leukemia(AML) cells and its related molecular regulatory mechanisms. Methods : Tetrazolium salt(MTS) method was used to detect the sensitivity of different AML cells to the classic ferroptosis inducer Erastin, real time quantitative polymerase chain reaction(qPCR) was used to detect the basal expression level ofLPCAT3mRNA, and the correlation between them was analyzed. Lentivirus-mediatedLPCAT3overexpression AML cell lines(OE group) and negative control lines(NC group) were constructed. After Erastin intervention, MTS, flow cytometry, and micromethods were used to detect cell viability, lipid reactive oxygen species(ROS), and Malondialdehyde(MDA), respectively. qPCR and Western blot were used to detect unfolded protein response(UPR) classic pathway signaling molecules(PERK, ATF4, GRP78, etc.) expression levels. The above ferroptosis-related indicators were detected after combined intervention with the UPR inhibitor 4-phenylbutyric acid(4-PBA), and the regulatory relationship was analyzed. Results : Four different types of AML cells had different sensitivities to ferroptosis, among which K562 cells were relatively insensitive. The IC50of the four types of AML cells to Erastin was negatively correlated with the expression level ofLPCAT3(r=-0.919,P<0.001). After Erastin intervention, the cell viability of K562 cells in the OE group was significantly inhibited by Erastin compared with the NC group(P<0.001), and the levels of lipid ROS and MDA increased(P<0.001). The results of qPCR and Western blot showed that, compared with the NC group, the mRNA and protein expression of UPR classic pathway moleculesPERK,ATF4, andGRP78mRNA and protein increased in the OE group(P<0.01). After inhibiting the UPR pathway by 4-PBA, the viability of K562 cells decreased(P<0.01), and lipid ROS and MDA levels increased(P<0.01) compared with the uninhibited state. Conclusion Overexpression ofLPCAT3can promote ferroptosis in K562 cells, and this process is negatively regulated by the classical UPR pathway PERK/ATF.

ObjectiveTo investigate the mechanism of modified Si Junzitang and Shashen Maidong Tang ［Yiqi Yangyin Jiedu prescription （YQYYJD）］ in enhancing the sensitivity of cisplatin in epidermal growth factor receptor tyrosine kinase inhibitor （EGFR-TKI）-resistant lung adenocarcinoma cells based on aerobic glycolysis. MethodsThe effects of different concentrations of YQYYJD （0， 2， 3， 4， 5， 6， 7， 8 g·L^-1） and cisplatin （0， 3， 6， 9， 12， 15， 18， 21， 24， 27 mg·L^-1） on the proliferation and activity of PC9/GR cells were detected by the cell counting kit-8 （CCK-8） assay after 24 hours of intervention. The half-maximal inhibitory concentration （IC₅₀） for PC9/GR cells was calculated to determine the concentrations used in subsequent experiments. PC9/GR cells were divided into blank group （complete medium）， YQYYJD group （5 g·L^-1）， cisplatin group （12 mg·L^-1）， and combined group （YQYYJD 5 g·L^-1 + cisplatin 12 mg·L^-1）. After 24 hours of intervention， cell viability was measured using CCK-8 assay. Cell proliferation was assessed by colony formation assay， and cell migration was evaluated by scratch and Transwell assays. Glucose consumption， lactate production， and adenosine triphosphate （ATP） levels were measured by colorimetric assays. The expression levels of glycolysis-related proteins， including hexokinase 2 （HK2）， phosphofructokinase P （PFKP）， pyruvate kinase M2 （PKM2）， lactate dehydrogenase A （LDHA）， glucose transporter 1 （GLUT1）， and monocarboxylate transporter 4 （MCT4）， were determined by Western blot. ResultsBoth YQYYJD and cisplatin inhibited the viability of PC9/GR cells in a concentration-dependent manner. The IC₅₀ of PC9/GR cells for YQYYJD and cisplatin were 5.15 g·L^-1 and 12.91 mg·L^-1， respectively. In terms of cell proliferation， compared with the blank group， the cell survival rate and the number of colonies formed in the YQYYJD group， cisplatin group， and combined group were significantly decreased （P<0.01）. Compared with the YQYYJD and cisplatin groups， the combined group showed a further significant reduction in cell survival rate and colony formation （P<0.01）. In terms of cell migration， compared with the blank group， the cell migration rate and the number of cells passing through the Transwell membrane in the YQYYJD group， cisplatin group， and combined group were significantly decreased （P<0.01）. Compared with the YQYYJD and cisplatin groups， the combined group exhibited a further significant reduction in cell migration rate and the number of cells passing through the Transwell membrane （P<0.01）. In terms of glycolysis， compared with the blank group， glucose consumption， lactate production， and ATP levels in the YQYYJD group， cisplatin group， and combined group were significantly decreased （P<0.01）. Compared with the YQYYJD and cisplatin groups， the combined group showed a further significant reduction in glucose consumption， lactate production， and ATP levels （P<0.05）. Compared with the blank group， the protein expression levels of HK2， PFKP， PKM2， and LDHA in the YQYYJD， cisplatin， and combined groups were significantly decreased （P<0.01）. The combined group showed a further significant reduction in the expression levels of these proteins compared with the YQYYJD and cisplatin groups （P<0.01）. No significant differences were observed in the protein expression levels of GLUT1 and MCT4 among the groups. ConclusionYQYYJD can synergistically inhibit the proliferation and migration of PC9/GR cells and enhance their sensitivity to cisplatin. The mechanism may be related to the downregulation of the expression of glycolysis-related rate-limiting enzymes， including HK2， PFKP， PKM2， and LDHA， thereby inhibiting glycolysis.

ObjectiveTo observe the prognosis effect of soluble programmed death ligand-1（sPD-L1） in treating patients with advanced lung adenocarcinoma treated with epidermal growth factor receptor-tyrosine kinase inhibitors（EGFR-TKIs） and the influence of Yiqi Yangyin Jiedu prescription. MethodA prospective cohort-controlled study was conducted to enroll patients treated with EGFR-TKIs in the first line of treatment，who were admitted to the Oncology Department of Longhua Hospital and Shanghai Chest Hospital from May 1^st， 2021 to June 30^th， 2023， and they were evaluated as non-progressive and identified with deficiency of Qi and Yin after one month of treatment. The patients were divided into an exposed group （EGFR-TKIs combined with Yiqi Yangyin Jiedu prescription） and a non-exposed group （EGFR-TKIs alone）according to whether or not they were treated with Yiqi Yangyin Jiedu prescription and were treated until disease progression， or death and intolerable adverse reactions occurred. The enzyme-linked immunosorbent assay （ELISA） was applied to detect the level of sPD-L1 in patients at the time of enrollment and disease progression，and Cox risk proportionality model was used to analyze the independent prognostic factors affecting disease progression of patients treated with EGFR-TKIs. ResultA total of 90 patients （39 in the exposed group and 51 in the non-exposed group） undergoing disease progression after EGFR-TKI treatment were enrolled. At the time of enrolment and after disease progression，the levels of serum sPD-L1 in the 90 patients were 12.06 （27.54） ng·L^-1 and 41.99 （62.93） ng·L^-1，respectively. Compared with that at the time of enrollment， the serum sPD-L1 level in the 90 patients was significantly increased after disease progression （P<0.01）. The serum sPD-L1 level in patients in the exposed group was 12.27 （24.78） ng·L^-1 and 29.57 （61.12）ng·L^-1 respectively at the time of enrolment and after disease progression. In the non-exposed group， patients had serum sPD-L1 levels of 11.81 （28.46） ng·L^-1 and 49.54 （74.12） ng·L^-1 respectively at the time of enrolment and after disease progression. Compared with that at the time of enrollment， the serum sPD-L1 level in the two groups of patients was significantly increased after disease progression （P<0.01）. In addition， compared with that in the non-exposed group， the sPD-L1 level in the exposed group was greatly reduced after disease progression（P<0.01）. Cox multifactorial analysis showed that sPD-L1 level and age at the time of enrolment were associated with patients' progression-free survival（PFS），and that low levels of sPD-L1 （<12.06 ng·L^-1） prolonged the PFS and reduced the risk of disease progression in patients treated with EGFR-TKIs compared with high levels of sPD-L1. ConclusionElevated sPD-L1 level is a poor prognostic factor for the long-term efficacy of EGFR-TKIs，and treatment with Yiqi Yangiin Jiedu prescription can down-regulate sPD-L1 level of patients treated with EGFR-TKIs.

IgA nephropathy（IgAN）is the most common primary glomerular disease，characterized by the deposition of IgA in the glomerular mesangial area. IgAN is a progressive disease with a protracted and relapsing course. Approximately 50%~75% of adult IgAN patients experience renal function deterioration and eventually progress to end-stage kidney disease（ESKD）within 20 years after diagnosis. Among patients with onset in childhood，about 30% ultimately progress to ESKD after 20 years of long-term follow-up. In recent years，numerous studies have continuously explored important signaling pathways and key molecules in its pathogenesis. This review introduces the therapeutic advances in IgAN，aiming to provide better treatment options for clinicians.

This article discusses the important role and practical experience of Guangxi Zhuang Autonomous Region as a bridgehead between China and the Association of Southeast Asian Nations (ASEAN) in the joint prevention and control of cross-border infectious diseases between China and Vietnam. The cross-border transmission of infectious diseases has been effectively managed in Guangxi Zhuang Autonomous Region through a package of strategies, including government leadership, construction of the joint prevention and control mechanism, establishment of dialogue platforms, collaboration of scientific researches, and personnel exchange and training; however, there are still challenges. Further deepening of collaboration is required to meet future needs for infectious disease prevention and control.

Objective To analyze the characteristics of facial and tongue chromaticity parameters in patients with gastrointestinal tumors by setting the inspection image characteristics of patients with gastrointestinal tumors as the main research content;To establish an auxiliary diagnostic model for gastrointestinal tumors.Methods One-way ANOVA,t-test,Mann-whitney U test,canonical correlation analysis and Spearman statistical methods were used to analyze the characteristics of inspection image indexes and correlation of tumor markers of the 391 cases in the control group and 359 patients with gastrointestinal tumors.Machine learning methods such as SVM,Random Forest,KNN,Naive Bayes,XG Boost and Ada Boost were used to establish an auxiliary diagnostic model for gastrointestinal tumors.Results In terms of facial indicators,there were differences in F-R,F-G and F-B indicators among the control group,early-stage gastrointestinal cancer patients,and mid-to late-stage gastrointestinal cancer patients,in the comparison of tongue features among,TC-L,TB-L and TB-a of the control group,patients with early gastrointestinal tumors,and patients with intermediate and advanced gastrointestinal tumors showed a gradual downward trend;the AUC of the auxiliary diagnosis model of gastrointestinal tumor disease based on the chromaticity parameters of face tongue image constructed by Ada Boost algorithm was 0.930.Conclusion The auxiliary diagnostic model of gastrointestinal diseases constructed by facial and tongue images has good diagnostic effect,which can provide objective data support for in-depth exploration of the complex relationship between diagnosis and disease.

Objective To construct an innovative CNN-Transformer dual-stream parallel network architecture integrating clinical data and imaging features for improving the predictive accuracy of pectoralis major myofascial metastasis in breast cancer,and to optimize the model performance by screening the optimal feature subset through genetic algorithm.Methods The proposed architecture concurrently processed clinical records and imaging data,including physical characteristics such as resolution,contrast,grayscale distribution,and texture features to identify their latent correlations.Meanwhile,genetic algorithms were employed to remove redundant features while retaining the most clinically and physically relevant features for pectoralis major myofascial metastasis prediction.Results The CNN-Transformer model that integrated imaging and clinical features showed superior performance across all evaluation metrics such as weighted F1 score and AUCROC,outperforming models relying only on imaging or clinical data.Conclusion The proposed dual-stream parallel network architecture combined with feature selection strategy significantly enhances the predictive accuracy of pectoralis major myofascial metastasis in breast cancer,and demonstrates the critical role of imaging features in improving model performance.

Objective:To develop a training curriculum targeting the core competences of neurosurgery nurses, so as to provide a reference for standardized training of neurosurgery nurses and to strengthen their professionality.Methods:Centering on the core competences required for neurosurgery nurses, we formed the curriculum framework based on the cell structure-inspired concept proposed by the School of Nursing of The Hong Kong Polytechnic University, and determined the contents through a literature analysis and two rounds of questionnaire-based Delphi consultations with 16 experts. We increased, reduced, or modified the items and dimensions, and finally estabilished the curriculum for neurosurgery nurse training. SPSS 18.0 software was used to analyze the general information of experts, coordination coefficient, variation coefficient, full mark ratio, and mean importance value. Categorical data were described as frequencies and percentages, and continuous data were described as mean±standard deviation. Ranked data were analyzed by using the chi-square test.Results:In the two rounds of expert consultations, questionnaires were both 100.00% returned, and the coefficients of expert authority were 0.873 and 0.888, respectively. The coordination coefficient of curriculum modules and curriculum contents were 0.416 and 0.221, respectively ( P<0.001). For individual items across the curriculum modules, the mean importance value was 3.188-3.938, the variation coefficient was 0.063-0.178, and the full mark ratio was 0.250-0.875. For content items, the mean importance value was 3.250-4.000, the variation coefficient was 0-0.238, and the full mark ratio was 0.375-1.000. The established clinical practice-directed curriculum for neurosurgery nursing training included 6 course modules (anatomy and physiology of the nervous system, neurosurgery patient evaluation and monitoring, neurosurgery disease nursing, commonly used neurosurgery nursing techniques, nursing management, and scientific research basis) and 77 content items. Conclusions:The established training curriculum targeting the core competences for neurosurgery nurses is reliable, which can provide a reference for standardized training of neurosurgery nurses.

Objective:To explore the application value of P1 response threshold of cortical auditory evoked potential（CAEP） in evaluating the rehabilitation effect of cochlear implant in young children. Methods:Thirty-three young children after cochlear implantation were divided into groups according to hearing age: Group A（hearing age 1-<2 years old） 10 people; Group B（hearing age 2-<3 years old） 13 people; Group C（hearing age 3-<4 years old） 10 people. The subjective assessment was carried out using the assessment tool for hearing-impaired children- "Criteria and Methods for assessing Auditory and language ability of hearing-impaired children" and objective electrophysiological examination was carried out using CAEP to evaluate the rehabilitation effect. SPSS 25.0 software was used for statistical analysis. Results:The results of subjective assessment of auditory ability and language ability in each group showed an increasing trend with the increase of auditory age. In this study, the P1 response threshold of CAEP in CI implanted children had a significant positive correlation with the 2 kHz hearing threshold after intervention, and the P1 response threshold of CAEP was negatively correlated with many items in subjective auditory ability and language ability assessment. Conclusion:The P1 response threshold of CAEP has a stable correlation with the results of speech audiometry, which can effectively and objectively evaluate the postoperative rehabilitation effect of young children with cochlear implantation.
Humans ; Child, Preschool ; Infant ; Male ; Female ; Evoked Potentials, Auditory ; Cochlear Implantation/rehabilitation* ; Cochlear Implants ; Auditory Threshold