ObjectiveTo study the effect of Zuoguiwan on the development of skin barrier in the neonatal rat model of congenital kidney deficiency and unveil the underlying mechanism. MethodsSixty rats were paired in a female-to-male ratio of 2∶1， and the pregnant rats were assigned into control， congenital kidney deficiency， and low- and high-dose （2 and 8 g·kg^-1， respectively） Zuoguiwan groups. The pregnant rats in other groups except the control group were exposed to chronic unpredictable mild stress for the modeling of congenital kidney deficiency. The rats in the control group and congenital kidney deficiency group were administrated with normal saline by gavage， and those in Zuoguiwan groups with Zuoguiwan suspension by gavage from day 1 of pregnancy. The serum level of interleukin-6 （IL-6） in the neonatal rats on the day of birth was determined by enzyme-linked immunosorbent assay. The full-thickness skin of neonatal rats on the day of birth was removed from the same position on the back and stained with hematoxylin-eosin for observation of histopathological changes， measurement of skin thickness， and counting of hair follicles. Terminal deoxynucleotidyl transferase-mediated nick end labeling was used to detect the apoptosis of skin tissue cells. The expression of interleukin-6 receptor （IL-6R） and interleukin-17A （IL-17A） in the skin tissue was assessed by immunohistochemistry and Western blot， and the expression of occludin， connexin 43 （Cx43）， and zonula occludens-1 （ZO-1） in the skin tissue was assessed by immunofluorescence and Western blot. ResultsCompared with those in the control group， the neonatal rats in the congenital kidney deficiency group showed a rise in the serum IL-6 level （P<0.01）， decreases in stratum corneum thickness， skin thickness， and number of hair follicles （P<0.01）， increases in the expression of IL-6R and IL-17A in the skin tissue （P<0.01） and the number of apoptotic cells （P<0.01）， and decreases in the expression of occludin， Cx43， ZO-1 （P<0.05）. Compared with the congenital kidney deficiency group， the low- and high-dose Zuoguiwan groups showed declines in serum IL-6 level （P<0.05）. The low-dose group showed increased number of hair follicles （P<0.05）， and the high-dose group presented thickened stratum corneum （P<0.01）， increased number of hair follicles （P<0.01）， and down-regulated expression of IL-6R and IL-17A in the skin tissue （P<0.05， P<0.01）. Both Zuoguiwan groups showcased decreased number of apoptotic cells （P<0.05， P<0.01）， and the high-dose group showed up-regulated expression of occludin， Cx43， and ZO-1 in the skin tissue （P<0.05， P<0.01）. ConclusionZuoguiwan can reduce the levels of IL-6 in the serum and IL-6R and IL-17A in the skin tissue and improve the expression of intercellular junction proteins， thereby ameliorating the abnormal development of the skin barrier in the neonatal rat model of congenital kidney deficiency.

ObjectiveTo study the effect of Zuoguiwan on the development of skin barrier in the neonatal rat model of congenital kidney deficiency and unveil the underlying mechanism. MethodsSixty rats were paired in a female-to-male ratio of 2∶1， and the pregnant rats were assigned into control， congenital kidney deficiency， and low- and high-dose （2 and 8 g·kg^-1， respectively） Zuoguiwan groups. The pregnant rats in other groups except the control group were exposed to chronic unpredictable mild stress for the modeling of congenital kidney deficiency. The rats in the control group and congenital kidney deficiency group were administrated with normal saline by gavage， and those in Zuoguiwan groups with Zuoguiwan suspension by gavage from day 1 of pregnancy. The serum level of interleukin-6 （IL-6） in the neonatal rats on the day of birth was determined by enzyme-linked immunosorbent assay. The full-thickness skin of neonatal rats on the day of birth was removed from the same position on the back and stained with hematoxylin-eosin for observation of histopathological changes， measurement of skin thickness， and counting of hair follicles. Terminal deoxynucleotidyl transferase-mediated nick end labeling was used to detect the apoptosis of skin tissue cells. The expression of interleukin-6 receptor （IL-6R） and interleukin-17A （IL-17A） in the skin tissue was assessed by immunohistochemistry and Western blot， and the expression of occludin， connexin 43 （Cx43）， and zonula occludens-1 （ZO-1） in the skin tissue was assessed by immunofluorescence and Western blot. ResultsCompared with those in the control group， the neonatal rats in the congenital kidney deficiency group showed a rise in the serum IL-6 level （P<0.01）， decreases in stratum corneum thickness， skin thickness， and number of hair follicles （P<0.01）， increases in the expression of IL-6R and IL-17A in the skin tissue （P<0.01） and the number of apoptotic cells （P<0.01）， and decreases in the expression of occludin， Cx43， ZO-1 （P<0.05）. Compared with the congenital kidney deficiency group， the low- and high-dose Zuoguiwan groups showed declines in serum IL-6 level （P<0.05）. The low-dose group showed increased number of hair follicles （P<0.05）， and the high-dose group presented thickened stratum corneum （P<0.01）， increased number of hair follicles （P<0.01）， and down-regulated expression of IL-6R and IL-17A in the skin tissue （P<0.05， P<0.01）. Both Zuoguiwan groups showcased decreased number of apoptotic cells （P<0.05， P<0.01）， and the high-dose group showed up-regulated expression of occludin， Cx43， and ZO-1 in the skin tissue （P<0.05， P<0.01）. ConclusionZuoguiwan can reduce the levels of IL-6 in the serum and IL-6R and IL-17A in the skin tissue and improve the expression of intercellular junction proteins， thereby ameliorating the abnormal development of the skin barrier in the neonatal rat model of congenital kidney deficiency.

Paroxysmal nocturnal hemoglobinuria (PNH) is an acquired clonal hematopoietic stem cell disease caused by abnormal expression of glycosylphosphatidylinositol (GPI) on the cell membrane due to mutations in the phosphatidylinositol glycan class A(PIGA) gene. It is commonly characterized by intravascular hemolysis, repeated thrombosis, and bone marrow failure, as well as multiple systemic involvement symptoms such as renal dysfunction, pulmonary hypertension, swallowing difficulties, chest pain, abdominal pain, and erectile dysfunction. Due to the rarity of PNH and its strong heterogeneity in clinical manifestations, multidisciplinary collaboration is often required for diagnosis and treatment. Peking Union Medical College Hospital, relying on the rare disease diagnosis and treatment platform, has invited multidisciplinary clinical experts to form a unified opinion on the diagnosis and treatment of PNH, and formulated the Expert Consensus of Multidisciplinary Diagnosis and Treatment for Paroxysmal Nocturnal Hemoglobinuria (2024), with the hope of promoting the standardization of PNH diagnosis and treatment.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.

Objective:To explore the effectiveness of a hysteroscopic endometrial lesion diagnosis model de-veloped based on deep learning(DL)algorithm combined with gradient-weighted class activation mapping(Grad-CAM)visualization technology.Methods:303 hysteroscopy videos(4781 images)of 291 patients who un-derwent hysteroscopy examination in the Department of Gynecology,Renmin Hospital of Wuhan University from June 1,2021 to December 31,2022 were selected.The dataset was divided into a training set(3703 images)and a test set(1078 images)by weight sampling method.After the training set was used for model learning and train-ing,two model architectures,residual neural network(ResNet18)and efficient neural network(EfficientNet-B0),were selected to verify the model in the test set by five-class and two-class classification tasks,respectively.Tak-ing histopathology as the gold standard,the diagnostic efficacy was evaluated to select the optimal model,and the Grad-CAM layer was embedded in the optimal model to output hysteroscopy images of Grad-CAM.Results:①In the five-class classification tasks,the accuracy of EfficientNet-B0 model(93.23％)was higher than that of Res-Net18 model(84.23％);the area under the curve(AUC)of EfficientNet-B0 model in the diagnosis of five disea-ses,including atypical endometrial hyperplasia,endometrial polyps,endometrial cancer,endometrial atypical hy-perplasia,and submucous myoma,was slightly higher than that of ResNet18 model,and the AUC of both models was almost above 0.980.②In the binary classification task of accuracy and the evaluation of specificity,the two models were similar,both above 93.00％,and the sensitivity of EfficientNet-B0 model(91.14％)was significantly better than that of ResNet18 model(77.22％).③EfficientNet-B0 model combined with Grad-CAM algorithm could identify the abnormal areas in the image.After biopsy and pathological examination,it was confirmed that about 95％of the marked areas in the model's output heatmap were lesion areas.Conclusions:The hysteroscopy di-agnostic model developed by EfficientNet-B0 model combined with Grad-CAM has high diagnostic accuracy,sen-sitivity,and specificity,and has application value in the diagnosis of endometrial lesions.