Alzheimer’s disease (AD) is a prevalent neurodegenerative condition characterized by progressive cognitive decline and memory loss. As the incidence of AD continues to rise annually, researchers have shown keen interest in the active components found in natural plants and their neuroprotective effects against AD. Quercetin, a flavonol widely present in fruits and vegetables, has multiple biological effects including anticancer, anti-inflammatory, and antioxidant. Oxidative stress plays a central role in the pathogenesis of AD, and the antioxidant properties of quercetin are essential for its neuroprotective function. Quercetin can modulate multiple signaling pathways related to AD, such as Nrf2-ARE, JNK, p38 MAPK, PON2, PI3K/Akt, and PKC, all of which are closely related to oxidative stress. Furthermore, quercetin is capable of inhibiting the aggregation of β‑amyloid protein (Aβ) and the phosphorylation of tau protein, as well as the activity of β‑secretase 1 and acetylcholinesterase, thus slowing down the progression of the disease.The review also provides insights into the pharmacokinetic properties of quercetin, including its absorption, metabolism, and excretion, as well as its bioavailability challenges and clinical applications. To improve the bioavailability and enhance the targeting of quercetin, the potential of quercetin nanomedicine delivery systems in the treatment of AD is also discussed. In summary, the multifaceted mechanisms of quercetin against AD provide a new perspective for drug development. However, translating these findings into clinical practice requires overcoming current limitations and ongoing research. In this way, its therapeutic potential in the treatment of AD can be fully utilized.

Objective To develop a machine learning-based risk prediction model for postoperative acute kidney injury(AKI)and a model for mortality in obese patients admitted to intensive care unit(ICU)in order to improve early warning and prognostic evaluation to support clinical decision-making.Methods Data of obese postoperative ICU patients were retrospectively retrieved from the MIMIC-Ⅳ and eICU databases for statistical analysis.Ultimately,2 520 patients(670 from MIMIC-Ⅳ and 1 850 from eICU databases)were included to build the risk prediction models for AKI and mortality.The data included demographic information,vital signs,laboratory findings,surgical types,comorbidities,and medication use.After data cleaning and preprocessing,Boruta feature selection was applied,followed by the construction of prediction models using 7 machine learning algorithms,that is,Gradient Boosting Machine(GBM),Generalized Linear Model(GLM),k-Nearest Neighbors(KNN),Na?ve Bayes(NB),Neural Network(NNET),Support Vector Machine(SVM),and XGBoost.Model performance was evaluated through cross-validation and external validation.Results In the risk prediction models of AKI,the SVM model achieved the highest AUC value of 0.80 in the testing set and 0.71 in the external validation test.For the risk prediction models of mortality,the GBM model outperformed others in the prediction,attaining an AUC value of 0.91 in the testing set.Conclusion Risk predictive models for postoperative AKI and mortality in obese ICU patients are successfully constructed,and are valuable tools for clinicians to optimize early intervention and improve clinical outcomes for the patients.

Objective To comparatively analyze the clinical characteristics of primary bilateral macronodular adrenal hyperplasia(PBMAH)and adrenal cortisol-producing Adenoma(CPA),and enhance the understanding of two diseases.Methods The clinical data of 85 PBMAH patients(PBMAH group)and 195 CPA patients(CPA group)diagnosed at Department of Endocrinology,the First Medical Center of Chinese PLA General Hospital,from September 2014 to August 2024 were retrospectively analyzed.The demographic characteristics,comorbidities,biochemical indicators,adrenocorticotropic hormone-cortisol(ACTH-F)levels,and adrenal imaging features and treatment conditions were compared between the two groups.Results(1)General characteristics:Compared with CPA group,PBMAH group had older age at diagnosis and a higher proportion of male patients.(2)Clinical characteristics:Compared with CPA group,PBMAH group had a longer disease duration,a higher proportion of subclinical Cushing's syndrome(CS),and a higher proportion of hypertension,impaired glucose tolerance/diabetes,bone mass reduction or osteoporosis,with higher serum potassium levels,and the differences were statistically significant(P<0.01).(3)Hormone levels:Both PBMAH and CPA groups showed ACTH-F rhythm disorder,significantly increased cortisol levels and suppressed ACTH.Compared with PBMAH group,CPA group had stronger autonomous cortisol secretion ability,manifested by increased midnight serum cortisol(F0:00),16:00 serum cortisol(F16:00),24-hour urinary free cortisol(24 h UFC)levels and lower 8:00 serum ACTH(ACTH8:00)and 16:00 serum ACTH(ACTH16:00)(P<0.01).After low-dose dexamethasone suppression test(LDDST),CPA group showed lower suppression rates of ACTH and cortisol,and higher proportions of paradoxical elevation in serum cortisol and 24 h UFC compared with PBMAH(P<0.01).Conclusions PBMAH has a longer disease course and higher proportions of comorbid metabolic disorders than CPA,mostly manifested as subclinical Cushing's syndrome.CPA has stronger autonomous cortisol secretion ability,with cortisol less likely to be suppressed after LDDST and more obvious paradoxical elevation of cortisol and 24 h UFC.

Objective To investigate the clinical and pathological characteristics of adrenal cortical carcinoma(ACC),compare differences between hypercortisolism and non-functional ACC,and assess the diagnostic value of indicators such as Ki-67 index.Methods The clinical data of 57 ACC patients admitted to the First Medical Center of Chinese PLA General Hospital from January 2015 to March 2025 were retrospectively analyzed.According to the results of endocrine function assessment,47 of these patients were divided into hypercortisolism group(n=19)and non-functional group(n=28).The differences in clinical and pathological characteristics between the two groups were compared,and non-parametric tests and Spearman correlation analysis were used to explore the relationship between Ki-67 index and tumor stage as well as imaging features.Results Among the 57 patients,there were 20 males and 37 females,with a male-to-female ratio of 1:1.85.The age ranged from 16 to 76 years,and the age at diagnosis was(48.7±13.3)years.The tumor diameter was(10.53±4.14)cm.The tumors were located on the right side in 12 cases(21.1%),on the left side in 34 cases(59.6%),and bilaterally in 11 cases(19.3%).Among them,16 cases(28.1%)were complicated with glucose metabolism disorders,31 cases(54.3%)had hypertension,and 20 cases(35.1%)had hypokalemia.According to ENSAT staging,there were 0 cases in stage Ⅰ,15 cases(26.3%)in stage Ⅱ,24 cases(42.1%)in stage Ⅲ,and 18 cases(31.6%)in stage Ⅳ.Endocrine function assessment was completed in 47 of the 57 patients,including 28 cases(59.6%)of non-functional ACC and 19 cases(40.4%)of hypercortisolism(including 1 case of hypercortisolism combined with increased sex hormone secretion).Compared with non-functional group,hypercortisolism group had a significantly higher prevalence of hypertension(P=0.014),later ENSAT stage(P=0.010),and a higher proportion of hypervascularization(P=0.048).The median Ki-67 index was 20%(10%-40%),showing no significant correlation with either the maximum tumor diameter or SUVmax value,but it was related to ENSAT staging,with Ki-67 index in stageⅣ patients being significantly higher than that in stage Ⅱ(P=0.032).Immunohistochemistry results showed that the positive rate of Inhibin-α was 84.8%,and the positive rate of Melan-A was 40.9%.Conclusions ACC is a rare malignant endocrine tumor.ACC patients with hypercortisolism are more likely to be complicated with hypertension,have later staging,and more common hypervascular manifestations.Clinically,their endocrine function should be prioritized for assessment,and more active treatment strategies should be adopted.Diagnosis should be combined with imaging characteristics(such as hypervascularization)and immunohistochemical indicators(Ki-67,Inhibin-α,Melan-A).The significant increase in Ki-67 is in the advanced stage can serve as an important prognostic indicator to guide individualized treatment.

Objective To characterize multimodal metabolic disorders in subclinical Cushing's syndrome(SCS)patients with different cortisol levels,providing a reference for clinical diagnosis and treatment.Methods A retrospective analysis was conducted on the clinical data of 165 SCS patients diagnosed at the First Medical Center of Chinese PLA General Hospital due to adrenal masses from January 2014 to October 2024.Using the serum cortisol levels after the midnight 1 mg dexamethasone suppression test(1 mg DST)as the cut-off point,SCS patients were divided into high-level group(1 mg DST-F>138 nmol/L,n=96)and low-level group(50 nmol/L<1 mg DST-F≤138 nmol/L,n=69).The differences in age,gender,body mass index(BMI),blood pressure,glucolipid metabolism indices,electrolytes,hormone levels,and imaging features of adrenal adenoma(such as CT values)were compared between the two groups.Multivariate linear regression was used to analyze the correlation between CT values and metabolic indices.Results Compared with low-level group,patients in high-level group were younger(54.0±11.3 vs.57.7±10.3,P=0.034),while there were no statistically significant differences in gender ratio or BMI between the two groups(P>0.05).Both groups exhibited decreased adrenocorticotropic hormone(ACTH)levels and disrupted circadian rhythm.Compared with low-level group,high-level group showed significantly higher F0:00 levels[250.00(170.07,422.53)nmol/L vs.110.00(82.74,133.90)nmol/L]and 24-hour urinary free cortisol(24 h UFC)[568.40(377.80,875.45)nmol/24 h vs.369.40(265.40,494.69)nmol/24 h](P<0.001),with no significant differences in serum F8:00,or 1 mg DST ACTH0:00 levels(P>0.05).Except for the fasting C-peptide level in the high-level group being higher than that in low-level group[(2.88±1.01)ng/ml vs.(2.46±0.78)ng/ml,P=0.024],there were no significant differences in blood pressure,blood lipids,glycated hemoglobin(HbA1c),fasting blood glucose,fasting insulin,serum electrolytes,uric acid,and other indices between the two groups(P>0.05).The CT value of adrenal adenoma during contrast-enhanced scanning was higher in high-level group[80.00(17.80,93.00)Hu vs.52.00(35.50,75.00)Hu,P=0.006]compared with low-level group.Multivariate linear regression analysis revealed that diastolic blood pressure was positively correlated with CT values of adrenal adenomas in both plain scanning(β=0.49,95%CI 0.09-0.90)and contrast-enhanced scanning(β=2.08,95%CI 0.76-3.39),while triglyceride levels were negatively correlated with plain scanning CT values(β=-5.77,95%CI-10.88--0.66).Conclusion Patients with SCS at different cortisol levels differ in age,fasting C-peptide levels,and CT values.CT values may serve as potential imaging markers to assess metabolic risk in SCS patients.

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.