Objective: To systematically evaluate the performance of machine learning (ML) models in predicting non suicidal self injury (NSSI) behavior among adolescents, providing an evidence based foundation for the development of clinically applicable risk assessment tools. Methods: A comprehensive search was conducted in PubMed, Embase, Web of Science, CNKI, and Wanfang databases for relevant studies from their inception to July 21, 2025. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to evaluate the methodological quality of the included studies. Stata 18 software was used to calculate the area under the receiver operating characteristic curve (AUC) of the models, and publication bias assessment, sensitivity analysis, and Egger s test were performed. Results: The total of 12 studies (42 prediction models) involving 58 070 adolescents were included. There were 15 machine learning algorithms in total, among which Random Forest, Logistic Regression, XGBoost, and Support Vector Machines were the most frequently utilized. The most common predictors were gender (female), family function, depression, emotion regulation, and age. All 12 included studies exhibited a high risk of bias. The pooled AUC was 0.80 (95% CI =0.78-0.82), although heterogeneity was substantial ( I 2=95.8%, P <0.01). Sensitivity analysis confirmed the robustness of these findings (no overlap in 95% CI ), while Egger s test indicated the presence of publication bias ( P <0.05). Conclusions Machine learning demonstrates potential in the risk prediction of adolescent NSSI, but existing models have a high risk of bias. Future research should focus on improving methodological quality and optimizing model reliability through rigorous external validation.

OBJECTIVE To assess the bleeding risk signals associated with the concomitant use of direct oral anticoagulants （DOACs） and triazole antifungals， and to provide pharmacovigilance evidence for the safety evaluation and monitoring of combined clinical use. METHODS Adverse event reports involving the concomitant use of DOACs and triazole antifungals were extracted from the US FDA Adverse Event Reporting System （FAERS） from the first quarter of 2004 to the third quarter of 2025. Nine bleeding-related preferred terms （PTs） were selected. The Ω shrinkage measure， additive model， multiplicative model， and combined risk ratio method were employed to detect drug-drug interaction signals. The strength of positive signals was further analyzed based on the Ω shrinkage measure. RESULTS A total of 790 adverse event reports involving the concomitant use of DOACs and triazole antifungals were included， among which 229 reports involved nine bleeding-related PTs. A total of 13 signals were consistently identified as posit ive by all four methods. These signals involved six drug combinations： apixaban-fluconazole， apixaban-posaconazole， rivaroxaban-itraconazole， dabigatran etexilate-fluconazole， apixaban-voriconazole， and dabigatran etexilate-itraconazole. The Ω shrinkage measure showed that the apixaban-posaconazole combination exhibited stronger signals for bleeding （ Ω ＝2.73， Ω 025 ＝2.05） and hemoptysis （ Ω ＝2.17， Ω 025 ＝0.83）； the apixaban-fluconazole combination exhibited stronger signals for hematoma （ Ω ＝2.30， Ω 025 ＝1.47） and hematuria （ Ω ＝1.71， Ω 025 ＝0.74）； the rivaroxaban-itraconazole combination exhibited stronger signals for epistaxis （ Ω ＝2.01， Ω 025 ＝0.90） and hematoma （ Ω ＝1.93， Ω 025 ＝0.42）； no positive Ω signals were observed for intracranial hemorrhage or upper gastrointestinal hemorrhage. CONCLUSION S This study suggests that the concomitant use of DOACs and triazole antifungals may increase the risk of bleeding-related events， with differences in signal strength and signal distribution across various drug combinations. In clinical practice， particular attention should be paid to the concomitant use of apixaban or rivaroxaban with strong cytochrome P450 3A4 or P-glycoprotein inhibitors such as posaconazole and itraconazole. For other DOAC-triazole antifungal combinations， close monitoring for bleeding-related manifestations and timely adjustment of anticoagulation or antifungal regimens are also warranted.

Effective symptom management can alleviate the physical and psychological distress experienced by patients with cancer, improve quality of life, and contribute to treatment adherence and improve clinical outcomes. However, most existing guidelines are developed for healthcare professionals, and patients and the public have limited access to standardized and comprehensible guidance on symptom management. To address this gap and to facilitate effective communication and shared decision-making, this study proposes the development of a patient version of the cancer symptom management guideline. The development process will adhere to the methodological framework recommended by the Guidelines International Network and the World Health Organization. The GRADE approach will be employed to assess the certainty of evidence and to formulate recommendations. In addition, the process will be informed by the Appraisal of Guidelines for Research and Evaluation Ⅱ (AGREE Ⅱ) instrument and the Reporting Items for Practice Guidelines in Healthcare-Public or Patient Versions of Guidelines (RIGHT-PVG). This protocol outlines the establishment of the guideline working group, the identification and prioritization of key questions, evidence retrieval and appraisal, and the formulation of recommendations, with the aim of ensuring methodological rigor and transparency in the development of the patient guideline and providing methodological reference for similar guideline initiatives.

Objective This study aims to evaluate the effectiveness of intelligent bed management model in integrating bed resources in a large comprehensive hospital.Methods Inpatient data from a tertiary hospital between January 2021 and De-cember 2024 were collected.An intelligent hospital-wide bed management platform was constructed to implement bed resource sharing mechanisms and establish a standardized bed reservation grading system.The implementation effect of the system was e-valuated from the perspective of bed occupancy rate,average length of stay,and patient satisfaction.Results After implementa-tion,bed occupancy rates in key monitored departments moved into a reasonable range:Rehabilitation Medicine Department fell from 113.18％to 101.48％(t=4.26,P＜0.01),while Neurology Department increased from 88.18％to 96.20％(t=3.85,P＜0.01).Annual inpatient admissions increased from 83,931 to 103,852(x2=156.82,P＜0.001),and average length of stay shortened from 7.15 days to 6.21 days(t=4.73,P＜0.01).The admission waiting time was cut by 72.7 hours(-43.1％),and satisfaction with bed allocation rationality improved by 11.2 points(t=5.94,P＜0.001).Staff time spent on bed-assignment fell by 42 minutes per shift(t=8.92,P＜0.001),and cross-department transfers increased by 378 episodes per month(x2=145.26,P＜0.001).Conclusion The intelligent bed management model can effectively improve hospital bed utili-zation efficiency,enhance healthcare service quality,reduce staff workload,and merits wider application in similar hospitals.

Objective To explore the application effect of constructing a data sharing-based multidrug-resistant or-ganism(MDRO)information reminder system combined with multidisciplinary standardized measures on the whole-process closed-loop management of MDRO.Methods Hospitalized patients from whom MDRO were detected from January 1 to July 31,2024 were taken as the control group,those from August 1,2024,to May 31,2025 were as the intervention group.The control group adopted the traditional manual reporting mode for MDRO,while the in-tervention group adopted the combination of MDRO reminder system and multidisciplinary management mode.Differences in isolation order issuing rate for MDRO and process-and outcome-indicators for multidisciplinary spe-cialty before and after system implementation were compared.Results After implementing information reminder system combined with multidisciplinary measures,issuing rates of ≤24 hour and＜4 hour MDRO isolation orders in the intervention group were both higher than in the control group([90.20％vs 65.23％,P＜0.05],[80.64％vs 55.08％,P＜0.001],respectively).Antimicrobial use rate in the intervention group was lower than in the con-trol group(36.27％vs 43.41％),with a statistically significant difference(P＜0.05).The implementation rates of MDRO prevention and control measures,pathogen detection rates,and fluorescence labeling clearance rates in the intervention group were all higher than those in the control group,all with statistically significant differences(all P＜0.05).The detection rate of MDRO decreased compared with the control group(10.83％vs 16.49％),and the in-cidence of MDRO healthcare-associated infection in the intervention group was lower than that in the control group(0.09％vs 0.19％),both with statistically significant differences(both P＜0.001).The treatment expense in the intervention group reduced by 27 422 Yuan compared with the control group.Conclusion This study constructed an MDRO reminder system,realized full-chain monitoring system for the multidisciplinary MDRO information interac-tion platform,strengthened multidisciplinary in-depth integration,and improved the prevention and control effect for MDRO.

Objective:To analyze the relationship between Cardiovascular Health(CVH)and Pelvic Inflamma-tory Disease(PID)using data from the National Health and Nutrition Examination Surveys(NHANES).Meth-ods:Participants from the NHANES database were extracted based on the inclusion of PID,LE8 scores,and mul-tiple potential confounding factors,excluding those with missing variables.Multivariate Logistic regression analysis was conducted using R to assess the relationship between the CVH and the risk of PID.Additionally,subgroup a-nalysis and interaction tests were performed for age,race,poverty,marital status,education,BMI,menstrual regu-larity,and pregnancy history.Results:A total of 3934 female participants were included,with an average age of 39.95±11.42 years.Multivariable Logistic regression analysis showed that after adjusting for age,race,BMI,edu-cation level,marital status,household income,menstrual cycle,and pregnancy history,the risk of PID gradually decreased with an increase in CVH assessment metric LE8 scores(OR 0.98,95％CI 0.97-0.99,P＜0.001).Stratified analysis indicated significant interactions between age,race,and marital status in the association be-tween CVH and PID(interaction P＜0.05 for all),while household income level,education level,BMI,menstrual regularity,and pregnancy history showed no significant interactions with the CVH and PID association(P＞0.05).Conclusions:There is a significant negative relationship between CVH and PID in adult women in the United states,suggesting that better cardiovascular health may help reduce the risk of PID.

Objective:To investigate the impact of different CT reconstruction kernels on the quantitative analysis of small pulmonary vessels in patients with chronic obstructive pulmonary disease (COPD) and high-risk patients.Methods:This study was a cross-sectional study. Clinical and imaging data of 73 COPD and high-risk patients visiting the China-Japan Friendship Hospital between March and April 2024 were retrospectively analyzed. All patients underwent high-resolution CT of the chest and pulmonary function tests, with the ratio of forced expiratory volume in one second to forced vital capacity (FEV 1/FVC) obtained. The raw CT data were reconstructed using different kernels: the FC86 group used the adaptive iterative dose reduction(AIDR) 3D standard lung sharp reconstruction algorithm, the FC18 group used the AIDR 3D standard Body standard reconstruction algorithm, the advanced intelligent clear-IQ engine(AiCE) Lung group used the AiCE deep learning reconstruction algorithm for lung, and the AiCE Body group used the AiCE deep learning reconstruction algorithm for body. Image signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and image noise were calculated. The pulmonary vessel segmentation & Measurement software was used to segment and extract pulmonary arteries and veins of four groups in thin-slice whole-lung CT imaging, obtaining the ratio of small pulmonary arteries (%V artery<5) and the ratio of small pulmonary veins (%V vein<5). The One-way repeated measures ANOVA or Friedman test was used to compare the differences in SNR, CNR, image noise, %V artery<5, and %V vein<5 among the four groups, followed by Bonferroni post hoc or Bonferroni-Dunn test with P-value correction to analysis differences between subgroups. The correlations between %V artery<5 and FEV 1/FVC, as well as between %V vein<5 and FEV 1/FVC were analyzed using Spearman rank correlation analysis in all four groups. Results:The overall differences in image noise, SNR, and CNR in the AiCE Lung, AiCE Body, FC18, and FC86 groups were statistically significant ( P<0.001). Except for the difference in CNR values between the AiCE Lung group and the FC18 group, which was not statistically significant ( P=0.192), all differences were statistically significant ( P<0.016 7). The overall differences in %V artery<5 values and %V vein<5 values in the AiCE Lung, AiCE Body, FC18, and FC86 groups were statistically significant ( P<0.001). The %V artery<5 and %V vein<5 values in the FC18 group were lower than those in the AiCE Lung, AiCE Body, and FC86 groups ( P<0.016 7), and the rest of the differences were not statistically significant ( P>0.016 7). %V artery<5 and %V vein<5 were positively correlated with FEV 1/FVC in all 4 groups ( P<0.05), with the highest correlation coefficient between %V vein<5 and FEV 1/FVC in the AiCE Body group ( r=0.501, P=0.001). Conclusions:DLR-AiCE-based kernel reconstruction optimizes image quality and significantly affects the results of quantitative parameters of small pulmonary vessels. The reconstruction kernel prioritized for quantitative analysis of small vessels within the lungs in COPD based on the CT scanner in this study is AiCE Body.

Objective:To study the alternation of plasma ghrelin in patients with acute pancreatitis (AP) and to evaluate the efficacy of gastric slow wave analysis in predicting the severity of AP.Methods:Clinical data and blood samples of 129 patients with AP and 16 individuals for normal physical examination in the Department of Gastroenterology, Jiangnan University Affiliated Central Hospital (Wuxi No.2 People's Hospital) from September 2018 to August 2024 were prospectively collected. Individuals with normal physical examinations were included in the normal control group, including 9 males and 7 females, aged (50.9±14.2) years. The finally enrolled 125 patients with AP included 82 males and 43 females, aged (49.5±15.6) years, which were grouped according to disease severity. Mild AP (MAP) was included in the MAP group ( n=84), while moderate to severe and severe acute AP were included in the non-MAP group ( n=41). The surface gastrogram of all AP patients was detected on the 2nd and 4th day after admission. The slow waves of gastric electricity were recorded, and gastric growth hormone-releasing hormone, C-reactive protein (CRP), etc. were detected simultaneously. Univariate and multivariate logistic regression analyses were conducted to analyze the influencing factors of AP severity (MAP or non-MAP). Receiver operating characteristic (ROC) curve was used to evaluate the indicators in predicting the severity of AP. Results:The levels of gastric growth hormone-releasing hormone in both the non-MAP group and MAP group on the 2nd and 4th day after admission were lower than those in normal control group (all P<0.05). The percentages of normal gastric electrical slow waves in the first and fourth leads, the mean percentages of normal gastric electrical slow waves in the four leads, and the main frequency on the 2nd day of admission in the non-MAP group were lower than those in the normal control group, and the main power and C-reactive protein were higher than those in the MAP group, the differences were statistically significant (all P<0.05). Multivariate logistic regression analysis showed the percentage of normal gastric electrical slow wave in the first lead on the 2nd day of admission ( OR=0.914, 95% CI: 0.869-0.961, P=0.001) and CRP ( OR=1.008, 95% CI: 1.002-1.013, P=0.012) were the influencing factors of the severity of AP. The area under the ROC curve of the percentage of normal gastric electrical slow wave in the first lead on the 2nd day of admission in predicting the severity of AP was 0.705, with a sensitivity of 97.6% and a specificity of 35.7%. Conclusion:The plasma gastric growth hormone-releasing hormone in patients with AP decreases in the early stage. The low percentage of normal slow waves in the first lead of gastric electrocardiogram on the 2nd day of admission is a risk factor for the severity of AP and can be used for the early prediction of the severity.

Objective To observe the value of T1WI deep learning models for evaluating brain injury of neonatal hyperbilirubinemia(NHB).Methods Totally 106 NHB(defined as newborns with neonatal behavioral neurological assessment≤37,NHB group)and 119 non-NHB newborns(control group)in center A,as well as 34 NHB and 18 non-NHB newborns in center B were collected.ROI was delineated based on bilateral globus pallidus on T1WI.A total of 690 slices were obtained by preprocessing data of center A and then were divided into training set(n=552)and test set(n=138)at a ratio of 8∶2.ResNet18,DenseNet121 and EfficientNetB0 models was established,respectively.External validation was performed based on data of center B.Receiver operating characteristic curves were drawn,area under the curves(AUC)were calculated to evaluate the performance of models for assessing NHB brain injuries compared with traditional visual analysis.Results The AUC of ResNet18 model for evaluating NHB brain injury was 0.910-0.990,significantly higher than that of DenseNet121 model(0.710-0.820)and EfficientNetB0 model(0.640-0.740)(all P＜0.001).The accuracy,sensitivity and precision of ResNet18 model for evaluating NHB brain injury were all higher than those of visual analysis(all P＜0.05),while no significant difference of specificity was found between the above two(P＞0.05).Conclusion T1WI ResNet18 model showed excellent performance and generalization ability for evaluating NHB brain injury.

Objective To develop high-immunogenicity antigens targeting the BA.5 variant of SARS-CoV-2 and to screen for monoclonal antibodies with high neutralizing and blocking activity,providing new strategies for the development of vaccines and diagnostic reagents.Methods The ZP protein gene fragment from zebrafish vitel-logenin and the HIS protein tag were inserted into the pCDNA3.4 plasmid to construct the recombinant plasmid pCDNA3.4-RBD(BA.5)-ZP-HIS,which was then transfected into 293F cells to express the RBD-ZP protein.The expression of the protein was verified by SDS-PAGE and its binding capabilities to ACE2 receptor molecules and aluminum adjuvant were detected.The immunogenicity of the fusion protein was evaluated using a BALB/c mouse model,and monoclonal antibodies were prepared through hybridoma technology.Monoclonal antibodies with strong neutralizing and blocking activity were screened and their neutralizing activity was detected by blocking ELISA.Results The ZP gene and HIS protein tag sequence were successfully inserted into the pCDNA3.4 vector and the RBD-ZP protein with a molecular weight of 50 kDa was successfully expressed.The immunogenicity test results showed that the ZP protein effectively enhanced the immunogenicity of the RBD protein and improved its binding capability to the ACE2 receptor.After immunizing mice with the RBD-ZP protein,8 monoclonal antibodies that specifically bind to both the mutant and wild-type strains were cloned and screened through hybridoma technology,among which 3 could effectively block the binding of the SARS-CoV-2 RBD protein to the human ACE2 receptor.Conclusion This study successfully expressed the RBD-ZP fusion protein,which significantly enhanced the immunogenicity and receptor binding capability of the RBD protein.Three monoclonal antibodies with high neutral-izing and blocking activity were screened out,providing strong support for the development of COVID-19 vaccines and diagnostic reagents..