Objective: To investigate the effect of auricular therapy on sleep improvement and the GABAergic system pathway in a rat model of insomnia and to explore its possible mechanism. Methods: According to the random number table, 60 male SD rats were randomly divided into blank control, model, auricular point sticking, auricular bloodletting, and auricular bloodletting combined with sticking groups, with 12 rats per group. Insomnia was induced by intraperitoneal injection of p-chlorophenylalanine. After establishing the insomnia model, 36 rats were treated once a day with auricular point sticking or bloodletting for 5 consecutive days. After the intervention, the general condition and body weight of rats were observed; the righting reflex test was used to detect the sleep latency and duration; HE staining was used to observe the morphology of hypothalamic neuron cells; and an enzyme-linked immunosorbent assay was used to detect the GABA and glutamate content in rat serum. Immunohistochemistry(IHC) and real-time fluorescence quantitative PCR were used to detect GABA ARα1 and GABA ARγ2 protein and mRNA expression in the hypothalamus of rats, and Western blotting(WB) was used to detect GABA ARα1, GABA ARγ2, GAD65/67, GAT-1, and GABA-T protein expression in the hypothalamus of rats. Results: Compared with the blank control group, the model group had a lower body weight, a significantly shorter sleep duration (P<0.05), severe damage to the morphological structure of hypothalamic neurons with disordered cell arrangement, larger intercellular gaps, enlarged cell bodies, and a vacuolated appearance. All the intervention groups had significantly higher body weight and longer sleep duration than the model group (P<0.05). Compared with the other intervention groups, the auricular point sticking group had a longer sleep duration (P<0.05), and the hypothalamic neuron cells in all intervention groups improved, with the auricular point sticking group showing more apparent improvement. The model group had a lower GABA and higher glutamate contents, and GABA ARα1, GABA ARγ2, and GAD65/67 protein expression in the hypothalamus were lower than in the blank control group. In contrast, GAT-1 and GABA-T protein expression was higher, and GABA ARα1 and GABA ARγ2 mRNA expression was lower (P<0.05). The serum GABA content in the auricular point sticking and auricular bloodletting groups was higher, and the serum glutamate content in the auricular point sticking and auricular bloodletting combined sticking groups was lower than in the model group. GABA ARα1 mRNA expression in the hypothalamus of each intervention group was significantly increased, and GABA ARγ2 mRNA expression in the hypothalamus of the auricular point sticking and auricular bloodletting combined sticking groups increased. GABA ARα1(IHC, WB), GABA ARγ2(WB), and GAD65/67 protein expression in the hypothalamus of the auricular point sticking group increased, whereas GAT-1 and GABA-T protein expression decreased. GABA ARα1 and GABA ARγ2 protein expression(IHC, WB) in the hypothalamus of the auricular bloodletting group increased, whereas GABA-T protein expression decreased. GABA ARγ1(IHC) and GABA ARγ2(WB) protein expression in the hypothalamus of the auricular bloodletting combined sticking group increased, whereas GAT-1 and GABA-T protein expression decreased (P<0.05). Compared with in the inventation groups, the serum GABA content in the auricular point sticking group increased, the serum glutamate content decreased, GABA ARα1 and GABA ARγ2 mRNA expression in the hypothalamus increased, and GABA ARα1(IHC), GAD65/67 protein expression increased. In contrast, GABA-T protein expression decreased (P<0.05), and GABA ARγ2 protein expression(IHC) in the hypothalamus of the auricular bloodletting group increased (P<0.05). Conclusion Auricular therapy, particularly auricular point sticking, may have modulated the GABAergic system pathway by upregulating hypothalamic GABA ARα1, GABA ARγ2, and GAD65/67 protein expression while downregulating GAT-1 and GABA-T protein expression to alleviate symptoms in an insomnia rat model.

Objective:To evaluate the utility of pulse oximetry-derived parameters—specifically, the pulse oximetry plethysmographic waveform area under the curve (POP AUC) and the peripheral perfusion index (PPI)—in assessing disease severity and predicting prognosis in patients with sepsis. Methods:In this prospective descriptive study, 68 patients with sepsis were categorized based on illness severity into septic shock and non-shock groups, and by 28-day outcome into survival and non-survival groups. POP AUC, PPI, and lactate (Lac) levels were recorded at 0, 24, 48, 72, and 96 hours after admission. APACHEⅡ and SOFA scores were calculated within the first 24 hours. The prognostic value of these parameters was evaluated. Results:Significant differences were observed between the septic shock and non-shock groups in POP AUC, PPI, Lac (all P < 0.05 except at 96 h), APACHEⅡ, and SOFA scores (all P < 0.05). These differences were most pronounced at admission: POP AUC0 (2475.1 ± 899.0) vs. (4260.3 ± 1028.5), PPI 0 (0.78 ± 0.74) vs. (3.13 ± 2.18), Lac 0 (4.95 ± 4.32) vs. (2.07 ± 1.55), APACHE Ⅱ (16.78 ± 5.59) vs. 11.82 ± 4.89), and SOFA (8.89 ± 3.25) vs. (5.06 ± 2.60). Optimal prognostic cut-off values were 2741.43 for POP AUC, 0.97 for PPI, 2.05 for Lac, 12.5 for APACHEⅡ, and 5.5 for SOFA. ROC curve analysis showed that at 24 hours, POP AUC and PPI had significantly larger AUC values than Lac ( P < 0.05), while no significant differences were found among other parameters. Significant differences between non-survivors and survivors were also found in POP AUC, PPI (at 0, 24, and 48 h), APACHE II, and SOFA (all P < 0.05). No significant differences were observed in PPI (72 h and 96 h) or Lac between the two outcome groups. Conclusions:POP AUC and PPI, as derived from pulse oximetry, are non-inferior to Lac, SOFA, and APACHEⅡ scores in evaluating disease severity and predicting 28-day mortality in sepsis patients. These parameters show promise as practical and non-invasive tools for clinical assessment in sepsis.

Objective:To investigate the value of habitat radiomic features based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI in establishing a predictive model for cytokeratin 19 (CK19) expression in hepatocellular carcinoma (HCC) and to evaluate its role in prognostic risk stratification.Methods:This multicenter case-control study retrospectively enrolled 489 patients with pathologically confirmed HCC who underwent Gd-EOB-DTPA-enhanced MRI between June 2016 and June 2024. Among them, 346 patients from the First Affiliated Hospital of Soochow University were divided into a training cohort ( n=245) and an internal test cohort ( n=101) via stratified sampling at a 7∶3 ratio. And 143 patients from Nantong Third Hospital Affiliated to Nantong University served as an external validation cohort. The training cohort included 53 CK19-positive and 192 CK19-negative patients. The internal test cohort included 21 CK19-positive and 80 CK19-negative patients. The external validation cohort included 30 CK19-positive and 113 CK19-negative patients. Univariate logistic regression analysis was performed to identify potential factors associated with CK19 expression, and a clinical-radiologic model was constructed. The k-means clustering algorithm was applied to segment target HCC lesions into 3 subregions. Radiomic features were extracted and selected from these habitat subregions. Habitat radiomics models were constructed for the arterial phase (AP), portal venous phase, hepatobiliary phase (HBP), and combined phases (CP). Multivariate logistic regression analysis identified independent clinical and radiologic predictors of CK19 expression, and the optimal habitat model score was integrated to build a clinical-radiologic-habitat combined model. The area under the receiver operating characteristic curve (AUC) was used to evaluate model predictive performance. Recurrence-free survival (RFS) was analyzed using the Kaplan-Meier method and the differences in survival curves were compared with the log-rank test. Results:Univariate logistic regression analysis revealed that alpha-fetoprotein (AFP) ( OR=2.629, 95% CI 1.412-4.896, P=0.002), AP enhancement ( OR=3.636, 95% CI 1.642-8.052, P=0.001), AP peritumoral enhancement ( OR=2.219, 95% CI 1.084-4.542, P=0.029), and HBP peritumoral hypointensity ( OR=2.010, 95% CI 1.004-4.021, P=0.049) were potential factors associated with CK19 expression, which were incorporated into the clinical-radiologic model. In the internal and external validation cohorts, the AUC of the clinical-radiologic model was 0.690 (95% CI 0.590-0.778) and 0.650 (95% CI 0.565-0.727), respectively. The habitat radiomics model based on CP images demonstrated the highest performance. It achieved AUC of 0.729 (95% CI 0.622-0.836) and 0.725 (95% CI 0.607-0.842) in the internal and external validation cohorts, respectively. Multivariate analysis identified AFP ( OR=2.494, 95% CI 1.163-5.348, P=0.019), AP enhancement ( OR=5.230, 95% CI 1.868-14.643, P=0.002) and habitat radiomics model score ( OR=4.105, 95% CI 2.643-6.368, P<0.001) as independent predictors of CK19 positivity. Based on these factors, a combined clinical-radiologic-habitat combined model was established. The clinical-radiologic-habitat combined model achieved AUCs of 0.767 (95% CI 0.671-0.846) and 0.730 (95% CI 0.649-0.801) in the internal and external validation cohorts, respectively. Significant differences in RFS were observed between the CK19-positive group (25.1 month) and CK19-negative group (51.0 month) as predicted by the clinical-radiologic-habitat model ( χ2=4.17, P=0.041). Conclusion:The clinical-radiologic-habitat combined model based on Gd-EOB-DTPA-enhanced MRI habitat radiomics demonstrates good predictive performance for CK19 expression in HCC and offers valuable prognostic stratification for clinical practice.

Objective:To explore the value of the deep learning model based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced MRI in preoperatively predicting vessels completely encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC).Methods:This study adopted a case-control design to retrospectively analyze 420 patients with HCC confirmed by postoperative pathology who underwent Gd-EOB-DTPA enhanced MRI between June 2016 and March 2023. A total of 420 patients were divided into a training set ( n=305) from the First Affiliated Hospital of Soochow University and an external validation set ( n=115) from Affiliated Nantong Hospital 3 of Nantong University. Based on postoperative pathological findings, patients were stratified into VETC-positive and VETC-negative groups. The training set comprised 161 VETC-positive cases and 144 VETC-negative cases, while the external validation set included 55 VETC-positive cases and 60 VETC-negative cases. Tumor regions of interest in arterial, portal venous, and hepatobiliary phases were manually delineated using ITK-SNAP software. Pre-trained Vgg19, Densenet121, and Vision Transformer (ViT) models were employed for transfer learning, extracting deep learning features from each image. Feature data were processed using FAE software, and 12 logistic regression models (arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase models) were constructed to select the optimal deep learning model. Independent predictors in clinical characteristics were identified through univariate and multivariate logistic analyses to establish a clinical model for predicting VETC pattern. Subsequently, a clinical-deep learning fusion model was developed by integrating these clinical predictors with the optimal deep learning features. Model performance in predicting VETC-positive HCC was evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). Results:In the external validation set, the area under the curve (AUC) of the Vgg19 model in the arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase, respectively were 0.799,0.756,0.789,0.821, which were higher than those of Densenet121 (AUC: 0.544,0.581,0.544,0.583) and ViT (AUC: 0.740,0.752,0.785,0.767) model. The three-phase combined Vgg19 model achieved the highest AUC of 0.821 (95% CI 0.746-0.897). Multivariate logistic regression identified alpha-fetoprotein level ( OR=1.826,95% CI 1.069-3.120, P=0.028) and tumor diameter ( OR=1.329,95% CI 1.206-1.466, P<0.001) as independent predictors of VETC-positive HCC, forming the clinical model with an AUC of 0.789 (95% CI 0.703-0.859). The clinical-deep learning fusion model further achieved the AUC of 0.825 (95% CI 0.749-0.900). Calibration curves confirmed high concordance between predicted and actual probabilities for the three-phase Vgg19 model, while DCA revealed greater net clinical benefit for the combined Vgg19 and fusion models compared with the clinical model alone. Conclusions:The deep learning model based on Gd-EOB-DTPA enhanced MRI can be used to predict VETC of HCC preoperatively, among which the three-phase combined Vgg19 model and the clinical-deep learning model provide high predictive value.

Objective To explore the correlation between the expression of serum human leukocyte antigen B27(HLA-B27) and serum amyloid A(SAA) in patients with pulmonary tuberculosis and the severity of the disease and the infection of other pulmonary pathogens. Methods From September 2021 to September 2023,120 patients with pulmonary tuberculosis complicated with pulmonary infection in Beijing Ditan Hospital Affiliated to Capital Medical University were selected as the research group,and another 120 patients with pulmonary tuberculosis were selected as the control group. According to the pneumonia severity index (PSI),the study group patients were divided into low-risk group (n=47),medium risk group (n=42) and high-risk group (n=31). Collected patient sputum for pathogen detection. Enzyme-linked immunosorbent assay (ELISA) was applied to measure the expression levels of HLA-B27 and SAA in serum. Multivariate Logistic regression was applied to analyze the factors that affected the severity of pulmonary tuberculosis combined with pulmonary infection in patients. Receiver operating characteristic (ROC) curve was applied to analyze the diagnostic efficacy of serum HLA-B27 and SAA for the severity of pulmonary tuberculosis combined with pulmonary infection in patients. Results Compared with the control group,the positive rate of serum HLA-B27(72.50％ vs 19.17％)in the study group,expression level of SAA (9.32±2.32 ng/ml vs 4.64±1.04 ng/ml)were significantly increased,and the differences were statistically significant(x2=68.744,t=20.164,all P<0.05). A total of 84 strains of pathogenic bacteria were isolated by the research group,including 46 Gram negative bacteria,34 Gram positive bacteria,and 4 fungi,with Klebsiella pneumoniae accounting for the highest proportion (15.48％). Compared with the low-risk group,the positive rate of HLA-B27(76.19％,93.55％ vs 55.32％),the expression level of SAA(9.35±2.35ng/ml,10.94±2.42ng/ml vs 8.23±2.23ng/ml)and the PSI score(108.63±12.47score,145.93±12.44 score vs 54.48±17.31 score) in the middle-risk group and the severe-risk group were significantly higher,and the differences were statistically significant (x2=4.256,13.130,t=2.306,5.077;15.021,25.384,all P<0.05). Serum HLA-B27 and SAA levels in patients with pulmonary tuberculosis complicated with pulmonary infection were positively correlated with PSI score (r=0.385,0.522,all P<0.05). The results of multivariate Logistic regression analysis showed that HLA-B27 positivity and SAA were risk factors affecting the severity of pulmonary tuberculosis combined with pulmonary infection in patients (P<0.05). The combined diagnosis of serum HLA-B27 and SAA had the highest area under the curve (AUC) for the severity of pulmonary infection in patients,which was superior to the individual diagnosis of serum HLA-B27 and elevated SAA expression levels (Z=3.132,2.131,P=0.002,0.033). Conclusion The pathogenic bacteria in patients with pulmonary tuberculosis and pulmonary infection are mainly Gram negative bacteria. The increases in serum HLA-B27 positive rate and SAA expression level are closely related to the disease progression in patients with pulmonary tuberculosis and pulmonary infection. The combination of the two can better diagnose the severity of the disease in patients with pulmonary infection.

Objective:To explore the experience of emotion management and program needs of patients with vasovagal syncope (VVS) from the doctor-nurse-patient perspective.Methods:This study was a phenomenological study in qualitative research. Using purposive sampling method, four medical specialists, four nursing specialists, and 10 patients with VVS from the Syncope Center of Shanghai East Hospital, Tongji University were selected from March to May 2024 for semi-structured interviews. Colaizzi's phenomenological data analysis was used to analyze the data.Results:Theme 1 was the initial perception and experience of emotion management, in which the doctor-nurse perspective included two sub-themes of emotion management met the actual needs of clinical patients and the management program was too specialized and unknown, and the patient perspective included three sub-themes of differences in the ability of individuals to recognize their own emotional state, lack of knowledge related to emotion management, and lack of social support. Theme 2 was the need for emotion management programs, in which the doctor-nurse perspective involved two sub-themes of multidisciplinary cooperation, suitable for clinical operation and follow-up, and the combination of online and offline, and in-hospital and out-of-hospital linkage, and the patient perspective involved two sub-themes of the need for healthcare guidance, easy to operate, and the diversification of forms, personalization, and meeting the needs of different populations.Conclusions:The content of emotion management is relatively unknown to doctors, nurses and patients, and even more so to patients. VVS emotion management work is still in its infancy, and emotion management as a branch of rehabilitation needs to be emphasized for its development, and psychological assessment and intervention work should be incorporated into the routine of syncope rehabilitation.

OBJECTIVE To explore the application of multiple hospital branches management mode in control of risk of hospital-acqueird infections in a general hospital so as to move forward the infection control threshold.METHODS The risk management closed loop,known as the infection index monitoring-risk assessment-risk re-sponse-effect evaluation-infection index monitoring,was adopted by People's Hospital of Ningxia Hui Autono-mous Region from Jan.to Jun.2024.The risk of infection at different levels of hospital zones,disciplines,clinical departments and risk indices was evaluated by risk matrix method.The correlation between the risk indices of clin-ical department and the risk scores was observed,and the dynamic monitoring was carried out for the change of risk of infection in the clinical departments.RESULTS The risk score was higher in the headquarter and Ningnan Branch than in the Xixia branch;the interquartile range(IQR)value from high to low was as follows:Xixia branch,hospital headquarter,Ningnan branch.The intensive care unit(ICU),nerve center and radiotherapy de-partment were the disciplines at extremely high risk of infection.The ICU,cardiac vascular surgery department and gastroenterology department of the hospital headquarters,the ICU,neurosurgery department and neurology department of Ningnan branch and the ICU and cardiac vascular surgery department of Xixia branch were the de-partments at extremely high risk of infection.The etiological submission rate before drug therapy,implementation of prevention measures for multidrug-resistant organisms(MDROs),cleaning and disinfection and missing report of hospital-acqueird infection cases were the major supervision indices.The absolute values of Spearman related co-efficient between clinical department risk scores and 4 indices-including the isolation rate of MDROs and the inci-dence of hospital-acqueird infection was greater than 0.5.CONCLUSION The risk management closed loop that is applied in the 'one hospital and multiple branches' medical institution may facilitate the dynamic monitoring,as-sessment and intervention the high-risk hospital branches,disciplines,departments and indices,and boost the ca-pability of risk management of infections in medical institutions.

Objective:To investigate the value of habitat radiomic features based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI in establishing a predictive model for cytokeratin 19 (CK19) expression in hepatocellular carcinoma (HCC) and to evaluate its role in prognostic risk stratification.Methods:This multicenter case-control study retrospectively enrolled 489 patients with pathologically confirmed HCC who underwent Gd-EOB-DTPA-enhanced MRI between June 2016 and June 2024. Among them, 346 patients from the First Affiliated Hospital of Soochow University were divided into a training cohort ( n=245) and an internal test cohort ( n=101) via stratified sampling at a 7∶3 ratio. And 143 patients from Nantong Third Hospital Affiliated to Nantong University served as an external validation cohort. The training cohort included 53 CK19-positive and 192 CK19-negative patients. The internal test cohort included 21 CK19-positive and 80 CK19-negative patients. The external validation cohort included 30 CK19-positive and 113 CK19-negative patients. Univariate logistic regression analysis was performed to identify potential factors associated with CK19 expression, and a clinical-radiologic model was constructed. The k-means clustering algorithm was applied to segment target HCC lesions into 3 subregions. Radiomic features were extracted and selected from these habitat subregions. Habitat radiomics models were constructed for the arterial phase (AP), portal venous phase, hepatobiliary phase (HBP), and combined phases (CP). Multivariate logistic regression analysis identified independent clinical and radiologic predictors of CK19 expression, and the optimal habitat model score was integrated to build a clinical-radiologic-habitat combined model. The area under the receiver operating characteristic curve (AUC) was used to evaluate model predictive performance. Recurrence-free survival (RFS) was analyzed using the Kaplan-Meier method and the differences in survival curves were compared with the log-rank test. Results:Univariate logistic regression analysis revealed that alpha-fetoprotein (AFP) ( OR=2.629, 95% CI 1.412-4.896, P=0.002), AP enhancement ( OR=3.636, 95% CI 1.642-8.052, P=0.001), AP peritumoral enhancement ( OR=2.219, 95% CI 1.084-4.542, P=0.029), and HBP peritumoral hypointensity ( OR=2.010, 95% CI 1.004-4.021, P=0.049) were potential factors associated with CK19 expression, which were incorporated into the clinical-radiologic model. In the internal and external validation cohorts, the AUC of the clinical-radiologic model was 0.690 (95% CI 0.590-0.778) and 0.650 (95% CI 0.565-0.727), respectively. The habitat radiomics model based on CP images demonstrated the highest performance. It achieved AUC of 0.729 (95% CI 0.622-0.836) and 0.725 (95% CI 0.607-0.842) in the internal and external validation cohorts, respectively. Multivariate analysis identified AFP ( OR=2.494, 95% CI 1.163-5.348, P=0.019), AP enhancement ( OR=5.230, 95% CI 1.868-14.643, P=0.002) and habitat radiomics model score ( OR=4.105, 95% CI 2.643-6.368, P<0.001) as independent predictors of CK19 positivity. Based on these factors, a combined clinical-radiologic-habitat combined model was established. The clinical-radiologic-habitat combined model achieved AUCs of 0.767 (95% CI 0.671-0.846) and 0.730 (95% CI 0.649-0.801) in the internal and external validation cohorts, respectively. Significant differences in RFS were observed between the CK19-positive group (25.1 month) and CK19-negative group (51.0 month) as predicted by the clinical-radiologic-habitat model ( χ2=4.17, P=0.041). Conclusion:The clinical-radiologic-habitat combined model based on Gd-EOB-DTPA-enhanced MRI habitat radiomics demonstrates good predictive performance for CK19 expression in HCC and offers valuable prognostic stratification for clinical practice.

Objective:To explore the value of the deep learning model based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced MRI in preoperatively predicting vessels completely encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC).Methods:This study adopted a case-control design to retrospectively analyze 420 patients with HCC confirmed by postoperative pathology who underwent Gd-EOB-DTPA enhanced MRI between June 2016 and March 2023. A total of 420 patients were divided into a training set ( n=305) from the First Affiliated Hospital of Soochow University and an external validation set ( n=115) from Affiliated Nantong Hospital 3 of Nantong University. Based on postoperative pathological findings, patients were stratified into VETC-positive and VETC-negative groups. The training set comprised 161 VETC-positive cases and 144 VETC-negative cases, while the external validation set included 55 VETC-positive cases and 60 VETC-negative cases. Tumor regions of interest in arterial, portal venous, and hepatobiliary phases were manually delineated using ITK-SNAP software. Pre-trained Vgg19, Densenet121, and Vision Transformer (ViT) models were employed for transfer learning, extracting deep learning features from each image. Feature data were processed using FAE software, and 12 logistic regression models (arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase models) were constructed to select the optimal deep learning model. Independent predictors in clinical characteristics were identified through univariate and multivariate logistic analyses to establish a clinical model for predicting VETC pattern. Subsequently, a clinical-deep learning fusion model was developed by integrating these clinical predictors with the optimal deep learning features. Model performance in predicting VETC-positive HCC was evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). Results:In the external validation set, the area under the curve (AUC) of the Vgg19 model in the arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase, respectively were 0.799,0.756,0.789,0.821, which were higher than those of Densenet121 (AUC: 0.544,0.581,0.544,0.583) and ViT (AUC: 0.740,0.752,0.785,0.767) model. The three-phase combined Vgg19 model achieved the highest AUC of 0.821 (95% CI 0.746-0.897). Multivariate logistic regression identified alpha-fetoprotein level ( OR=1.826,95% CI 1.069-3.120, P=0.028) and tumor diameter ( OR=1.329,95% CI 1.206-1.466, P<0.001) as independent predictors of VETC-positive HCC, forming the clinical model with an AUC of 0.789 (95% CI 0.703-0.859). The clinical-deep learning fusion model further achieved the AUC of 0.825 (95% CI 0.749-0.900). Calibration curves confirmed high concordance between predicted and actual probabilities for the three-phase Vgg19 model, while DCA revealed greater net clinical benefit for the combined Vgg19 and fusion models compared with the clinical model alone. Conclusions:The deep learning model based on Gd-EOB-DTPA enhanced MRI can be used to predict VETC of HCC preoperatively, among which the three-phase combined Vgg19 model and the clinical-deep learning model provide high predictive value.

Objective:To summarize the clinical characteristics of congenital chylothorax (CC) in neonates, and to analyze the effects of conservative treatment and the prognosis.Methods:A case control study was conducted.Clinical data of neonates with CC treated in the Department of Neonatal Surgical Intensive Care Unit, Guangzhou Women and Children′s Medical Center Guangzhou Medical University, from January 2015 to April 2023 were collected.The patients were divided into a survival group and a death group according to the outcome.SPSS 26.0 software was used for statistical analysis, and binary Logistic regression was used for the analysis of risk factors for death.Results:A total of 55 patients were included in this study, including 35 males and 20 females.The gestational age at birth and birth weight were 37.1 (34.7, 38.7) weeks and 3 250 (2 640, 3 540) g, respectively.Among the patients included, 30 cases had bilateral pleural effusion, 25 cases had unilateral pleural effusion, and 22 cases had hydrops fetalis; 50 cases were prenatally diagnosed with pleural effusion, with the mean gestational age at diagnosis being 31.0(26.0, 34.6) weeks.Additionally, 21 cases had polyhydramnios, and 18 cases had mediastinal displacement.Ten cases received intrauterine treatment and 17 cases were treated with octreotide.The maximum daily amount of pleural effusion was 31.7(12.0, 62.5) mL/kg, and pleural effusion resolved within 14 (6, 22) days.The length of hospital stay was 23 (12, 36) days.Forty-four cases survived, while 11 cases died.The differences in polyhydramnios, gestational age, bilateral pleural effusion, hydrops fetalis and Apgar score were significant between the survival and death groups (all P<0.05).Binary Logistic regression analysis revealed that bilateral pleural effusion and a low 5-minute Apgar score were independent risk factors for early death in neonates with CC (all P<0.05).A total of 38 children were followed up at the age of 2.30 (1.24, 3.46) years.There was 1 case of recurrence, and none of the patients experienced recurrent respiratory infections. Conclusions:CC is most common in full-term infants and has a predominantly bilateral effusion, its long-term prognosis with conservative treatment is promising.However, neonates with CC who present with bilateral pleural effusion or low 5-minute Apgar scores have an increased risk of early mortality.