[Objective] To evaluate the feasibility of a novel outpatient infusion model for blinatumomab in two acute lymphoblastic leukemia (ALL) patients, aiming to address challenges of poor treatment tolerance, high healthcare costs, and compromised quality of life, thereby providing clinical insights for broader adoption of this approach. [Methods] Two post-allogeneic hematopoietic stem cell transplantation (allo-HSCT) patients undergoing blinatumomab maintenance therapy were selected to evaluate the efficacy of the outpatient infusion model. Patient selection criteria, nursing protocols, standardized workflows, and advancements in infusion practices were systematically analyzed combined with a review of global developments in this field. [Results] Both patients completed outpatient blinatumomab infusion without severe adverse events, demonstrating preliminary feasibility and safety of this model. The novel approach enhanced treatment convenience, reduced hospitalization costs, and improved quality of life. [Conclusion] Despite the limited sample size, this pilot study highlights the potential of outpatient blinatumomab administration as a viable alternative to traditional inpatient regimens.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

In recent years, the deep integration of artificial intelligence (AI) into medical education has created new opportunities for teaching Biochemistry and Molecular Biology, while also offering innovative solutions to the pedagogical challenges associated with protein structure and function. Focusing on the case of anaplastic lymphoma kinase (ALK) gene mutations in non-small-cell lung cancer (NSCLC), this study integrates AI into case-based learning (CBL) to develop an AI-CBL hybrid teaching model. This model features an intelligent case-generation system that dynamically constructs ALK mutation scenarios using real-world clinical data, closely linking molecular biology concepts with clinical applications. It incorporates AI-powered protein structure prediction tools to accurately visualize the three-dimensional structures of both wild-type and mutant ALK proteins, dynamically simulating functional abnormalities resulting from conformational changes. Additionally, a virtual simulation platform replicates the ALK gene detection workflow, bridging theoretical knowledge with practical skills. As a result, a multidimensional teaching system is established—driven by clinical cases and integrating molecular structural analysis with experimental validation. Teaching outcomes indicate that the three-dimensional visualization, dynamic interactivity, and intelligent analytical capabilities provided by AI significantly enhance students’ understanding of molecular mechanisms, classroom engagement, and capacity for innovative research. This model establishes a coherent training pathway linking “fundamental theory-scientific research thinking-clinical practice”, offering an effective approach to addressing teaching challenges and advancing the intelligent transformation of medical education.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective:To assess the level of moral distress among pediatric nurses in China and explore its influencing factors, providing a reference for future interventions.Methods:A cross-sectional survey was conducted using a convenience sampling method from May 2022 to March 2023. Pediatric nurses meeting the inclusion and exclusion criteria were selected from children′s specialized hospitals, general hospitals, and maternal and child health hospitals across 16 provinces in China. Moral distress was assessed using the Chinese version of the Moral Distress Scale-Revised (MDS-R). Data analysis included descriptive statistics, non-parametric analysis, and multiple linear regression.Results:A total of 509 pediatric nurses participated in the survey, including 10 males and 499 females. Among them, 45 were aged ≤25 years, 268 were aged 26-35 years, 172 were aged 36-45 years, and 24 were aged >45 years.The median moral distress score was 58.00 (26.00, 77.50). Factors independently associated with higher levels of moral distress included having a master′s degree ( t = 2.33), working in a ward with more than 40 beds ( t = 3.38), working in a ward without parental accompaniment ( t = 2.60), being passively assigned to the nursing profession ( t = 2.63), and considering resignation but not leaving the job ( t = 3.85) (all P<0.05). Conclusions:Pediatric nurses in China experience a moderate level of moral distress. Further research is needed to understand its underlying causes and to develop preventive and intervention strategies.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective:To assess the level of moral distress among pediatric nurses in China and explore its influencing factors, providing a reference for future interventions.Methods:A cross-sectional survey was conducted using a convenience sampling method from May 2022 to March 2023. Pediatric nurses meeting the inclusion and exclusion criteria were selected from children′s specialized hospitals, general hospitals, and maternal and child health hospitals across 16 provinces in China. Moral distress was assessed using the Chinese version of the Moral Distress Scale-Revised (MDS-R). Data analysis included descriptive statistics, non-parametric analysis, and multiple linear regression.Results:A total of 509 pediatric nurses participated in the survey, including 10 males and 499 females. Among them, 45 were aged ≤25 years, 268 were aged 26-35 years, 172 were aged 36-45 years, and 24 were aged >45 years.The median moral distress score was 58.00 (26.00, 77.50). Factors independently associated with higher levels of moral distress included having a master′s degree ( t = 2.33), working in a ward with more than 40 beds ( t = 3.38), working in a ward without parental accompaniment ( t = 2.60), being passively assigned to the nursing profession ( t = 2.63), and considering resignation but not leaving the job ( t = 3.85) (all P<0.05). Conclusions:Pediatric nurses in China experience a moderate level of moral distress. Further research is needed to understand its underlying causes and to develop preventive and intervention strategies.

Objective Advances in synthetic DNA technology have made it much easier to fake human DNA samples.There are literature reports that fake human DNA can be synthesized by different methods and implanted in the field to confuse the investigation or mislead the trial.Therefore,distinguishing authentic human DNA from synthetic DNA and performing individual identification has become a critical scientific challenge.Methods We define a novel composite genetic marker(methylation-microhaplotype)by combining CpG sites stably hypermethylated or hypomethylated in natural human DNA and nearby immediately adjacent microhaplotype sites.A total of 19 locis were obtained according to the screening criteria,and a composite detection system for methylation-microhaplotypes was established using MPS technology.Random volunteer DNA samples were extracted and synthetic DNA samples were prepared based on whole genome amplification techniques.Population DNA samples were analyzed to evaluate forensic parameters and methylation variability of the methylation-microhaplotype markers.Comparative analyses of human and synthetic DNA were conducted to assess the markers'ability to discriminate between the two and to detect/type both components in mixed mixed samples.Results The composite detection system composed of 19 locis demonstrated high individual identification ability,achieving a cumulative individual identification probability of 0.999 999 999 996 86.12 hypermethylated locis and 7 hypomethylated locis had relatively stable methylation levels in 57 human DNA samples.According to the allele methylation rate(Ram)value,the system can effectively identify natural and synthetic DNA samples.Meanwhile,for mixed DNA samples,the presence of human and synthetic DNA samples can be found and genotyped.Conclusion Methylation-microhaplotype genetic markers,which can discover human DNA and synthetic DNA and can detect the presence and genotyping of them from mixed samples,is a potential useful tool for forensic DNA analysis.

Objective:To observe the effect of high-frequency repetitive transcranial magnetic stimulation (rTMS) at different frequencies on cognitive impairment due to high-altitude hypoxia.Methods:Sixty officers and soldiers displaying cognitive impairment in a hypoxic high-altitude environment were randomly divided into 15Hz, 20Hz and 25Hz groups, each of 20. They were given rTMS at those frequencies for 30 days. Before the stimulation and after 15 and 30 days, event-related potentials, latencies of mismatched negativity (MMN) and P300 signals were recorded. The participants′ cognition was also evaluated using the Montreal Cognitive Assessment Scale (MoCA). Correlation between the electrophysiological indexes and the MoCA scores was computed.Results:After 15 days, all had shorter MMN latencies, higher total MoCA scores and better memory scores. The only significant difference among the three groups was in the average memory scores. After 15 days, MMN latency was significantly negatively correlated with the memory scores in all three groups ( r=0.44 to -0.54). Conclusions:rTMS at frequencies above 15Hz can effectively relieve cognitive impairment, especially memory dysfunction, resulting from high-altitude hypoxia.