Objective To compare the segmenting efficacy of automatic segmentation models for advanced gastric cancer(AGC)on CT virtual monoenergetic images(VMI),non-linear blending images(NLBI)and mixed-energy images(MEI)based on 3D-nnU-Net.Methods Totally 216 cases of AGC were retrospectively enrolled,among them 185 cases were used to construct,train and validate models and divided into training set(n=154)and test set(n=31)at the ratio of 5∶1,while the other 31 cases were used as validation set to evaluate the generalization of the models.The 70 keV energy level VMI(VMI70 keV),NLBI and MEI were reconstructed with whole-abdominal dual-energy mode venous CT,and automatic segmentation models of AGC,including VMI70 keV,NLBI and MEI models were constructed using 3D-nnU-Net,respectively.Taken manually segmented results as golden standards,the efficacy of each model for segmenting all lesions and T2 stage lesions in test set and validation set were evaluated using Dice similarity coefficient(DSC),intersection over union(IoU)and average symmetric surface distance(ASSD).Results For all lesions in test and validation sets,DSC of 3 models were all＞0.80.DSC and IoU of VMI70 keV and NLBI models were both higher,while their ASSD was lower than those of MEI model(all P＜0.05).For T2 stage AGC in both test set and validation set(each n=5),DSC of MEI model was lower than that of VMI70 keV and NLBI models(both P＜0.05),while IoU of MEI model was lower than that of VMI70 keV model(P＜0.05),and its ASSD was higher than that of NLBI model(P＜0.05).Conclusion All 3D-nnU-Net-based VMI70 keV,NLBI and MEI models could effectively segment AGC on dual-energy CT images,and the segmentation efficacy of the former two were better.

Objective:To investigate the causal impact of maternal smoking around birth(MSAB)on off-spring's risk of attention deficit hyperactivity disorder(ADHD),autism spectrum disorder(ASD),bipolar disorder(BD),and major depressive disorder(MDD).Methods:The datasets for MSAB and 4 psychiatric disorders were extracted from genome-wide association studies(GWAS).Mendelian randomization(MR)was employed,using in-verse variance weighting(IVW)as the primary analysis method.Sensitivity analyses and outlier correction were conducted using weighted median(WM),MR-Egger regression,and MR-PRESSO.The results were expressed as odds ratios(OR)and corrected for false discovery rate(FDR).Results:MR analysis showed significant causal re-lationships between MSAB and increased risk of ADHD(OR=5.36,95％CI=2.58-7.63,PFDR=0.003),MDD(OR=1.92,95％CI=1.29-2.88,PFDR=0.003),and BD(OR=6.33,95％CI=1.56-8.73,PFDR=0.013).However,no statistically significant association was found between MSAB and ASD(OR=1.66,95％CI=0.23-5.87,PFDR=0.616).Conclusion:This study suggests a potential causal link between maternal smoking around the time of birth and an increased risk of attention deficit hyperactivity disorder,bipolar disorder,and major depressive disorder in offspring.

Objective To compare the segmenting efficacy of automatic segmentation models for advanced gastric cancer(AGC)on CT virtual monoenergetic images(VMI),non-linear blending images(NLBI)and mixed-energy images(MEI)based on 3D-nnU-Net.Methods Totally 216 cases of AGC were retrospectively enrolled,among them 185 cases were used to construct,train and validate models and divided into training set(n=154)and test set(n=31)at the ratio of 5∶1,while the other 31 cases were used as validation set to evaluate the generalization of the models.The 70 keV energy level VMI(VMI70 keV),NLBI and MEI were reconstructed with whole-abdominal dual-energy mode venous CT,and automatic segmentation models of AGC,including VMI70 keV,NLBI and MEI models were constructed using 3D-nnU-Net,respectively.Taken manually segmented results as golden standards,the efficacy of each model for segmenting all lesions and T2 stage lesions in test set and validation set were evaluated using Dice similarity coefficient(DSC),intersection over union(IoU)and average symmetric surface distance(ASSD).Results For all lesions in test and validation sets,DSC of 3 models were all＞0.80.DSC and IoU of VMI70 keV and NLBI models were both higher,while their ASSD was lower than those of MEI model(all P＜0.05).For T2 stage AGC in both test set and validation set(each n=5),DSC of MEI model was lower than that of VMI70 keV and NLBI models(both P＜0.05),while IoU of MEI model was lower than that of VMI70 keV model(P＜0.05),and its ASSD was higher than that of NLBI model(P＜0.05).Conclusion All 3D-nnU-Net-based VMI70 keV,NLBI and MEI models could effectively segment AGC on dual-energy CT images,and the segmentation efficacy of the former two were better.

Objective:To explore the cognition of nursing undergraduate students towards learner reputation in the digital education environment, providing a basis for the construction of learner reputation incentive mechanisms.Methods:This study was descriptive and qualitative. Purposive sampling was used to select 26 nursing undergraduate students from six schools of nursing for the study from July to November 2023 for semi-structured interviews. Traditional content analysis method was used to analyze the data.Results:A total of three themes and 7 sub-themes were refined, including personal literacy reputation (self-directed learning ability in online learning, integrity quality in digital learning environment, learning potential stimulated by digital resources), behavioral competence reputation (role positioning and responsibility in digital learning tasks, outcome benefits in digital learning tasks), and interactive identity reputation (shaping professional image and self-identity, obtaining external evaluation and good reputation) .Conclusions:Building learner reputation incentive mechanism is crucial in digital education, which motivates nursing students, empowers professional development, and lays a solid foundation for personal growth and future career development.

Objective To develop an automated system that can accurately determine the relationship between the mandibular third molar and the mandibular nerve canal from panoramic images.Methods A dataset consisting of 600 panoramic images of the oral cavi-ty was selected,and the positions of the mandibular third molar and the mandibular nerve canal were accurately labeled.We compared the research designed TI-YOLOv5 with PANet,Faster R-CNN,Mask R-CNN,ResNeSt-101,and the original YOLOv5 in image seg-mentation tasks,with evaluation metrics of AP and AP50.Results TI-YOLOv5 achieved AP(average precision)54.0％and AP5094.9％,an increase of 4.9 and 6.7 percentage points respectively compared to the original YOLOv5(AP 49.1％,AP50 88.2％),and surpassed other SOTA methods such as Mask R-CNN(AP 45.1％,AP50 84.2％).Conclusion TI-YOLOv5 is significantly superior to mainstream networks in automatic positioning and relationship classification of mandibular wisdom teeth and neural tubes,with high de-tection accuracy and discrimination accuracy,and can provide reliable technical support for preoperative risk assessment of mandibular wisdom tooth extraction.

Objective To develop an automated system that can accurately determine the relationship between the mandibular third molar and the mandibular nerve canal from panoramic images.Methods A dataset consisting of 600 panoramic images of the oral cavi-ty was selected,and the positions of the mandibular third molar and the mandibular nerve canal were accurately labeled.We compared the research designed TI-YOLOv5 with PANet,Faster R-CNN,Mask R-CNN,ResNeSt-101,and the original YOLOv5 in image seg-mentation tasks,with evaluation metrics of AP and AP50.Results TI-YOLOv5 achieved AP(average precision)54.0％and AP5094.9％,an increase of 4.9 and 6.7 percentage points respectively compared to the original YOLOv5(AP 49.1％,AP50 88.2％),and surpassed other SOTA methods such as Mask R-CNN(AP 45.1％,AP50 84.2％).Conclusion TI-YOLOv5 is significantly superior to mainstream networks in automatic positioning and relationship classification of mandibular wisdom teeth and neural tubes,with high de-tection accuracy and discrimination accuracy,and can provide reliable technical support for preoperative risk assessment of mandibular wisdom tooth extraction.

Objective:To explore the clinical features of nivolumab-induced Stevens-Johnson syndrome/toxic epidermal necrolysis (SJS/TEN).Methods:Relevant databases at home and abroad (as of December 31, 2023) were searched to collect case reports of nivolumab-induced SJS/TEN, and the demographic characteristics, nivolumab application, combination drugs, clinical manifestations, intervention measures, and outcomes were extracted and analyzed descriptively and statistically.Results:A total of 27 case reports were included and 29 patients were enrolled in the study, including 18 males and 11 females. The age ranged from 45 to 86 years, with an average age of 67 years. The primary diseases were mainly melanoma, stomach cancer, and lung cancer. Twelve patients had records of nivolumab administration, and the dosage was within the recommended range in the labels; 13 patients had records of combination drugs, mainly other antineoplastic drugs, hypoglycemic drugs, antihypertensive drugs, lipid-regulating drugs, etc. The time from using nivolumab to the diagnosis of SJS/TEN was 7 d to 3 years, and 20 patients were <8 weeks. The clinical manifestations were mainly diffuse erythema, flaky skin peeling and erosion, mucosal involvement, etc. Sixteen patients had skin biopsy records, all of which met the histopathological characteristics of SJS/TEN. After the diagnosis of SJS/TEN, 17 patients discontinued nivolumab and received symptomatic treatments, of which 15 patients had improved skin symptoms, one patient had worsened skin symptoms, and one patient had no record of skin outcome; 12 patients had no record of whether or not discontinuing nivolumab, of which 8 patients had improved skin symptoms, 2 patients had worsened skin symptoms, one patient had no record of skin outcome, and one had no record of prognosis. One patient rechallenged nivolumab, severe SJS/TEN recurred. Thirteen of 29 patients died. Of them, 1 died due to cardiac arrest, 4 due to worsened skin rash, and 8 due to primary disease progression.Conclusions:SJS/TEN caused by nivolumab mostly occurs within 8 weeks of treatment, and the clinical manifestations were similar to those caused by other drugs. The mortality rate of nivolumab-induced SJS/TEN is high, and skin rash could be improved after withdrawal of nivolumab and symptomatic treatments.

Objective:To explore the cognition of nursing undergraduate students towards learner reputation in the digital education environment, providing a basis for the construction of learner reputation incentive mechanisms.Methods:This study was descriptive and qualitative. Purposive sampling was used to select 26 nursing undergraduate students from six schools of nursing for the study from July to November 2023 for semi-structured interviews. Traditional content analysis method was used to analyze the data.Results:A total of three themes and 7 sub-themes were refined, including personal literacy reputation (self-directed learning ability in online learning, integrity quality in digital learning environment, learning potential stimulated by digital resources), behavioral competence reputation (role positioning and responsibility in digital learning tasks, outcome benefits in digital learning tasks), and interactive identity reputation (shaping professional image and self-identity, obtaining external evaluation and good reputation) .Conclusions:Building learner reputation incentive mechanism is crucial in digital education, which motivates nursing students, empowers professional development, and lays a solid foundation for personal growth and future career development.

Objective:To investigate the causal impact of maternal smoking around birth(MSAB)on off-spring's risk of attention deficit hyperactivity disorder(ADHD),autism spectrum disorder(ASD),bipolar disorder(BD),and major depressive disorder(MDD).Methods:The datasets for MSAB and 4 psychiatric disorders were extracted from genome-wide association studies(GWAS).Mendelian randomization(MR)was employed,using in-verse variance weighting(IVW)as the primary analysis method.Sensitivity analyses and outlier correction were conducted using weighted median(WM),MR-Egger regression,and MR-PRESSO.The results were expressed as odds ratios(OR)and corrected for false discovery rate(FDR).Results:MR analysis showed significant causal re-lationships between MSAB and increased risk of ADHD(OR=5.36,95％CI=2.58-7.63,PFDR=0.003),MDD(OR=1.92,95％CI=1.29-2.88,PFDR=0.003),and BD(OR=6.33,95％CI=1.56-8.73,PFDR=0.013).However,no statistically significant association was found between MSAB and ASD(OR=1.66,95％CI=0.23-5.87,PFDR=0.616).Conclusion:This study suggests a potential causal link between maternal smoking around the time of birth and an increased risk of attention deficit hyperactivity disorder,bipolar disorder,and major depressive disorder in offspring.

With the rapid development of digital technology, digital twin technology shows great potential for application in the medical and nursing fields. This paper reviews the main elements and key aspects of digital twins, their application scenarios and effects in medicine and nursing, and application challenges faced, with a view to providing innovative solution ideas for healthcare professionals and promoting the application and development of digital twins in medicine and nursing.