Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Objective:To observe the clinical efficacy of different treatment methods in treating older patients with oral papilloma.Methods:A randomized controlled study was conducted on 40 older patients with oral papilloma who visited the Department of Stomatology of Beijing Hospital from August 2022 to November 2024.They were randomly divided into a surgical resection group and a 5-aminolevulinic acid (ALA) application group.There were 15 males and 25 females, with ages ranging from 60 to 82 (70.20 ± 6.53) years old.The ALA application group received ALA photodynamic therapy (PDT), while the surgical resection group underwent surgical resection of the papilloma.Visual analog scale (VAS) and self-assessment anxiety and depression scale were used to evaluate the two groups of patients at different periods.Results:All lesions in both groups achieved complete healing, with no recurrence observed during the 6-month follow-up period.Although the ALA application group received more treatment sessions than the surgical resection group, postoperative VAS scores and the duration of postoperative pain were both significantly lower [VAS score: (2.95±0.83) vs. (4.95±1.32) points; pain duration: (4.65±0.67) vs.(6.20±1.06) days]( t=5.755 and 5.540, respectively; both P<0.001). Before treatment, there was no statistically significant difference in either self- assessed anxiety or self- assessed depression scores between the two groups (both P>0.05). Six months after treatment, the self- assessed anxiety score in the ALA application group was significantly higher than that in the surgical resection group ( P<0.05), whereas no significant difference was observed in the self- assessed depression score ( P>0.05). Conclusions:Both ALA-PDT and surgical resection can effectively treat oral papilloma in older patients.However, ALA-PDT has lighter and shorter duration of postoperative pain, making it more suitable for treating lesions in special anatomical areas such as the corners of the mouth and the duct openings of the parotid glands.

Objective:To construct the risk prediction model for early-onset peritoneal dialysis-associated peritonitis (PDAP) in peritoneal dialysis patients based on six machine learning algorithms.Methods:This study was retrospective. Convenience sampling was used to select peritoneal dialysis patients who were regularly followed up in the Department of Nephrology of Guizhou Provincial People's Hospital from December 2009 to August 2023 to collect general information, primary diseases, and laboratory indicators of the study population. It was randomly divided into a modeling set and validation set in the ratio of 7∶3. With the occurrence of early-onset PDAP as the dependent variable, the risk prediction model of early-onset PDAP in peritoneal dialysis patients was constructed based on six machine learning algorithms, namely, Logistic regression, decision tree, support vector machine, random forest, extreme gradient boosting, and artificial neural network, respectively. Model performance was evaluated based on the area under the receiver operating characteristic curve ( AUC) , accuracy, and F1 score to select the optimal model. Results:The final data of 890 peritoneal dialysis patients were analyzed, of which 86 patients developed early-onset PDAP, and the incidence of early-onset PDAP was 9.66%. The four prediction models, Logistic regression, support vector machine, extreme gradient boosting, and random forest, had high accuracy with AUC values of 0.703, 0.729, 0.782, and 0.814, respectively, with the random forest model having higher AUC value, accuracy, and F1 score. Further ranking of the importance of risk factors for early-onset PDAP based on the random forest model showed that the top five characteristic variables were C-reactive protein, triglycerides, platelet, ferritin, and leukocyte, in that order. Conclusions:The risk prediction model for early-onset PDAP in peritoneal dialysis patients constructed based on the random forest model has optimal performance, which can help medical and nursing staff assess and prevent early-onset PDAP at an early stage.

Objective:To construct the risk prediction model for early-onset peritoneal dialysis-associated peritonitis (PDAP) in peritoneal dialysis patients based on six machine learning algorithms.Methods:This study was retrospective. Convenience sampling was used to select peritoneal dialysis patients who were regularly followed up in the Department of Nephrology of Guizhou Provincial People's Hospital from December 2009 to August 2023 to collect general information, primary diseases, and laboratory indicators of the study population. It was randomly divided into a modeling set and validation set in the ratio of 7∶3. With the occurrence of early-onset PDAP as the dependent variable, the risk prediction model of early-onset PDAP in peritoneal dialysis patients was constructed based on six machine learning algorithms, namely, Logistic regression, decision tree, support vector machine, random forest, extreme gradient boosting, and artificial neural network, respectively. Model performance was evaluated based on the area under the receiver operating characteristic curve ( AUC) , accuracy, and F1 score to select the optimal model. Results:The final data of 890 peritoneal dialysis patients were analyzed, of which 86 patients developed early-onset PDAP, and the incidence of early-onset PDAP was 9.66%. The four prediction models, Logistic regression, support vector machine, extreme gradient boosting, and random forest, had high accuracy with AUC values of 0.703, 0.729, 0.782, and 0.814, respectively, with the random forest model having higher AUC value, accuracy, and F1 score. Further ranking of the importance of risk factors for early-onset PDAP based on the random forest model showed that the top five characteristic variables were C-reactive protein, triglycerides, platelet, ferritin, and leukocyte, in that order. Conclusions:The risk prediction model for early-onset PDAP in peritoneal dialysis patients constructed based on the random forest model has optimal performance, which can help medical and nursing staff assess and prevent early-onset PDAP at an early stage.

Objective:To observe the clinical efficacy of different treatment methods in treating older patients with oral papilloma.Methods:A randomized controlled study was conducted on 40 older patients with oral papilloma who visited the Department of Stomatology of Beijing Hospital from August 2022 to November 2024.They were randomly divided into a surgical resection group and a 5-aminolevulinic acid (ALA) application group.There were 15 males and 25 females, with ages ranging from 60 to 82 (70.20 ± 6.53) years old.The ALA application group received ALA photodynamic therapy (PDT), while the surgical resection group underwent surgical resection of the papilloma.Visual analog scale (VAS) and self-assessment anxiety and depression scale were used to evaluate the two groups of patients at different periods.Results:All lesions in both groups achieved complete healing, with no recurrence observed during the 6-month follow-up period.Although the ALA application group received more treatment sessions than the surgical resection group, postoperative VAS scores and the duration of postoperative pain were both significantly lower [VAS score: (2.95±0.83) vs. (4.95±1.32) points; pain duration: (4.65±0.67) vs.(6.20±1.06) days]( t=5.755 and 5.540, respectively; both P<0.001). Before treatment, there was no statistically significant difference in either self- assessed anxiety or self- assessed depression scores between the two groups (both P>0.05). Six months after treatment, the self- assessed anxiety score in the ALA application group was significantly higher than that in the surgical resection group ( P<0.05), whereas no significant difference was observed in the self- assessed depression score ( P>0.05). Conclusions:Both ALA-PDT and surgical resection can effectively treat oral papilloma in older patients.However, ALA-PDT has lighter and shorter duration of postoperative pain, making it more suitable for treating lesions in special anatomical areas such as the corners of the mouth and the duct openings of the parotid glands.

Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Objective:To investigate the effectiveness and safety of the coaxial needle technique in percutaneous liver biopsy for patients with coagulation function abnormalities.Methods:Clinical data of 210 patients who underwent percutaneous liver biopsy using the coaxial needle technique under ultrasound guidance from December 2018 to May 2021 in 3 centers were collected. A retrospective analysis was conducted to compare the puncture success rate, number of samples obtained, pathology qualification rate, intraoperative and postoperative bleeding rates between the group with coagulation function abnormalities and the group with normal coagulation function.Results:After propensity score matching, there were 105 patients in each group, with a puncture success rate of 100% in both groups. The pathology qualification rate was 100% for all samples.Intraoperative bleeding occurred in 78 cases (74.3%, 78/105) in the coagulation function abnormalities group and in 64 cases (61.0%, 64/105) in the normal coagulation function group, with a statistically significant difference between the two groups ( P=0.006). Postoperative bleeding occurred in 3 cases (2.9%, 3/105) in the coagulation function abnormalities group and in 0 case in the normal coagulation function group, with no statistically significant difference between the two groups ( P=0.081). Conclusions:The use of the coaxial needle technique for percutaneous liver biopsy in patients with coagulation function abnormalities not only allows for obtaining an adequate tissue sample but also demonstrates good safety.

Objective To observe the clinical efficacy and safety of external application of Piyan Formula in treating epidermal growth factor receptor tyrosine kinase inhibitor(EGFR-TKIs)-related rashes.Methods Sixty cases of EGFR-TKIs-related rash patients were randomly allocated into either a treatment group or a control group.The treatment group received external application of Piyan Formula to the rash area twice daily for 14 days.The control group received external application of fucidic acid cream to the rash area twice daily for 14 days.Changes in rash grading,itching grading,quality of life scores and adverse event were observed and recorded in both groups.At the same time,levels of hypersensitive C-reactive protein,interleukin(IL)-6,and IL-1β were measured before treatment and 24 hours after treatment.Results After treatment,the rash severity,itching severity,and quality of life scores were notably lower in the treatment group compared to the control group(P<0.05).The levels of hypersensitive C-reactive protein,IL-6,and IL-1β exhibited a significant decrease compared to their pre-treatment values.(P<0.05).Compared with the control group,the levels of hypersensitive C-reactive protein,IL-6,and IL-1β decreased in the treatment group,with statistically significant differences(P<0.05).No adverse events related to Piyan Formula or fucidic acid cream occurred during the treatment process.Conclusion External application of Piyan Formula in treating EGFR-TKIs-related rashes shows significant clinical efficacy,can effectively reduce the levels of inflammatory factors,and has high safety,thus warranting clinical promotion.

OBJECTIVES: With the increase in aging population in China, elderly Crohn's disease (CD) patients need to receive more attention. This study aims to explore the clinical characteristics and disease process of elderly onset CD (EOCD) patients in a single center. METHODS: From January 2002 to January 2022, a total of 221 patients with CD from the Seventh Medical Center of Chinese PLA General Hospital were enrolled. According to the Montreal CD classification standard, the patients were further divided into 4 groups: an EOCD group (≥60 years old, n=25), a middle age onset CD (MOCD) group (40-59 years old, n=46), a young onset CD (YOCD) group (17-40 years old, n=131), and a childhood onset CD (COCD) group (6-16 years old, n=19). We compared the clinical characteristics and long-term prognosis among them. RESULTS: Females were predominant in the EOCD group (15/25, 60%). The number of people without smoking in the EOCD group (80%) was lower than that in COCD group (100%), higher than that in the YOCD group (70.2%) and the MOCD group (69.6%) (all P<0.05). Patients with perianal diseases at diagnosis were rare in the EOCD group (0%), lower than that in the COCD group (21.1%) and the YOVD group (19.8%) (all P<0.05). Stenosis was the most common disease behavior in the EOCD group (63.0%), significantly higher than that in the COCD group (15.8%), the YOCD group (36.6%) and the MOCD group (43.5%) (all P<0.05). The EOCD group was easier to be misdiagnosed as tumor (24%), higher than that in the COCD group (0%), the YOCD group (6.9%) and the MOCD group (19.6%) (all P<0.05). The EOCD group was prone to comorbidities (52%), and 20% of them were complicated with multiple comorbidities (P<0.05). During the follow-up, the all-cause mortality of EOCD was 12%, and the CD-related mortality was 8%, which was significantly higher than the other groups (all P<0.05). The use of immunosuppressants in the EOCD group (4.8%) was lower than that in the COCD group (12.8%), the YOCD group (16.8%) and the MOCD group (16.1%), but there was no statistical significance among the 4 groups (P=0.467). In addition, there was no significant difference in the rate of intestinal resection among the 4 groups (P=0.062). CONCLUSIONS In EOCD patients, females were predominant, smoking was less common, and they were prone to comorbidity. At the initial stage of diagnosis, it is easy to be misdiagnosed as tumor, and the disease behavior mainly showed stricture type, less complicated with perianal diseases. During the follow-up, all-cause mortality and CD-related mortality of EOCD patients were significantly higher than those of the non-elderly onset CD patients.
Female ; Middle Aged ; Humans ; Aged ; Child ; Adult ; Adolescent ; Young Adult ; Crohn Disease/epidemiology* ; Prognosis ; Constriction, Pathologic ; Aging ; Hospitals, General

Objective:To explore the mechanism of early pancreatic exocrine function changes in severely scalded rats.Methods:The experimental research methods was used. Eighty male Sprague-Dawley rats aged 7-8 weeks were divided into simple sham injury group ( n=8), sham injury+cholecystokinin octapeptide (CCK8) group ( n=8), severe scald+CCK8 group ( n=32), and extremely severe scald+CCK8 group ( n=32) by the random number table, which were treated accordingly. Immediately after injury of rats in the 2 sham injury groups and 1, 2, 3, and 7 days after injury of rats in the 2 scald groups, the improved methods including pancreatic duct puncture and catheterization were used to dynamically collect the pancreatic-bile juice (PBJ) of rats. The PBJ secretory volume within 1 h was recorded, and the content of pancreatic lipase, α-amylase, and trypsin in PBJ was detected by enzyme-linked immunosorbent assay (ELISA), and the number of samples was 8. The femoral venous blood was collected, and the concentrations of pancreatic lipase and α-amylase in serum were detected by standard colorimetry to reflect their activity ( n=8). The pancreatic tissue was extracted, and the levels of interleukin-1β (IL-1β) and IL-6 in pancreatic tissue were detected by ELISA ( n=8), the expression of hypoxia-inducible factor 1α (HIF-1α) in pancreatic tissue was detected by immunofluorescence method, and the histopathological changes in pancreatic tissue were observed by hematoxylin-eosin staining, the severity of pancreatic tissue injury in the 2 scald groups was evaluated by modified Schmidt method ( n=6), and the ultrastructure of acinar cells in pancreatic tissue was observed by transmission electron microscopy. Data were statistically analyzed with analysis of variance for factorial design, Tukey test, independent sample t test, and least significant difference test. Results:Compared with the PBJ secretory volume (0.740±0.030) mL in the pancreatic tissue of rats in simple sham injury group within 1 h immediately after injury, the (0.823±0.033) mL in sham injury+CCK8 group was significantly increased ( t=4.92, P<0.05). Compared with that of rats in sham injury+CCK8 group immediately after injury, the PBJ secretory volume of rats within 1 h in severe scald+CCK8 group ((0.681±0.024), (0.608±0.056), (0.525±0.025), and (0.720±0.044) mL) and extremely severe scald+CCK8 group ((0.540±0.025), (0.406±0.021), (0.475±0.036), and (0.690±0.018) mL) was significantly decreased on 1, 2, 3, and 7 days after injury ( P<0.05). Compared with that in severe scald+CCK8 group, the PBJ secretory volume of rats within 1 h in extremely severe scald+CCK8 group was significantly decreased on 1 and 2 days after injury ( P<0.05). Compared with that of rats in simple sham injury group immediately after injury, the content of pancreatic lipase, α-amylase, and trypsin in PBJ of rats in sham injury+CCK8 group immediately after injury was significantly increased (with t values of 4.56, 3.30, and 4.99, respectively, P<0.05). Compared with that of rats in sham injury+CCK8 group immediately after injury, the content of pancreatic lipase and α-amylase in PBJ of rats in severe scald+CCK8 group and extremely severe scald+CCK8 group was significantly decreased on 1, 2, 3, and 7 days after injury ( P<0.05), the trypsin content in PBJ of rats in extremely severe scald+CCK8 group was significantly decreased on 2 days after injury ( P<0.05). Compared with that in severe scald+CCK8 group, the content of pancreatic lipase in PBJ of rats in extremely severe scald+CCK8 group was significantly decreased on 1, 2, and 3 days after injury ( P<0.05), and the content of α-amylase and trypsin in PBJ was significantly decreased on 1 and 2 days after injury ( P<0.05). There were no statistically significant differences in the activities of pancreatic lipase and α-amylase in serum of rats among the 4 groups at various time points after injury ( P>0.05). Compared with that of rats in sham injury+CCK8 group immediately after injury, the levels of IL-1β in pancreatic tissue of rats in severe scald+CCK8 group on 1, 2, and 3 days after injury and in extremely severe scald+CCK8 group on 1, 2, 3, and 7 days after injury were significantly increased ( P<0.05), and the levels of IL-6 in pancreatic tissue of rats in severe scald+CCK8 group and extremely severe scald+CCK8 group were significantly increased on 1, 2, 3, and 7 days after injury ( P<0.05). Compared with that in severe scald+CCK8 group, the IL-1β level in pancreatic tissue of rats in extremely severe scald+CCK8 group was significantly increased on 2 and 3 days after injury ( P<0.05), and IL-6 level in pancreatic tissue was significantly increased on 2 days after injury ( P<0.05). The expression levels of HIF-1α in pancreatic tissue of rats in simple sham injury group and sham injury+CCK8 group immediately after injury were lower; and compared with that in sham injury+CCK8 group immediately after injury, the expression levels of HIF-1α in pancreatic tissue of rats in the 2 scald groups increased to a certain extent at different time points after injury, and the expression position was transited from the edge of the pancreatic tissue to the whole pancreas, the expression levels of HIF-1α in pancreatic tissue of rats in the 2 scald groups tended to be normal on 7 days after injury. Compared with that in simple sham injury group immediately after injury, the proportion of acinar cell cytoplasm in pancreatic tissue of rats in sham injury+CCK8 group was increased; and with the increase of time after injury, edema, hemorrhage, necrosis, and inflammatory infiltration appeared in pancreatic tissue of rats in the 2 scald groups. Compared with that in severe scald+CCK8 group, the scores of edema, inflammatory cell infiltration, bleeding, and necrosis in pancreatic tissue of rats in extremely severe scald+CCK8 group were increased to varying degrees at various time points after injury, and the scores of pancreatic tissue of rats in the 2 scald groups basically recovered to normal on 7 days after injury. Compared with that in simple sham injury group immediately after injury, the number of enzyme granules in acinar cells of pancreatic tissue of rats in sham injury+CCK8 group was increased, and with the increase of time after injury, the enzyme granules in acinar cells of rats in the 2 scald groups were gradually reduced basically. Conclusions:The exocrine functions of pancreas, such as synthesis and secretion of pancreatic enzymes, are decreased in the early stage in severely scalded rats. And the greater the scalded area, the more significant the decline of pancreatic exocrine function. This change may be related to hypoxic injury and inflammation in pancreatic tissue after severe scald.