ObjectiveTo explore the construction of a machine learning model for the diagnosis of traditional Chinese medicine （TCM） syndromes in chronic cough and the optimization of this model using the Voting ensemble algorithm. MethodsA retrospective analysis was conducted using clinical data from 921 patients with chronic cough treated at the Respiratory Department of Dongfang Hospital， Beijing University of Chinese Medicine. After standardized processing， 84 clinical features were extracted to determine TCM syndrome types. A specialized dataset for TCM syndrome diagnosis in chronic cough was formed by selecting syndrome types with more than 50 cases. The synthetic minority over-sampling technique （SMOTE） was employed to balance the dataset. Four base models， logistic regression （LR）， decision tree （dt）， multilayer perceptron （MLP）， and Bagging， were constructed and integrated using a hard voting strategy to form a Voting ensemble model. Model performance was evaluated using accuracy， recall， precision， F1-score， receiver operating characteristic （ROC） curve， area under the curve （AUC）， and confusion matrix. ResultsAmong the 921 cases， six syndrome types had over 50 cases each， phlegm-heat obstructing the lung （294 cases）， wind pathogen latent in the lung （103 cases）， cold-phlegm obstructing the lung （102 cases）， damp-heat stagnating in the lung （64 cases）， lung yang deficiency （54 cases）， and phlegm-damp obstructing the lung （53 cases）， yielding a total of 670 cases in the specialized dataset. High-frequency symptoms among these patients included cough， expectoration， odor-induced cough， throat itchiness， itch-induced cough， and cough triggered by cold wind. Among the four base models， the MLP model showed the best diagnostic performance （test accuracy： 0.9104； AUC： 0.9828）. Compared with the base models， the Voting ensemble model achieved superior performance with an accuracy of 0.9289 on the training set and 0.9253 on the test set， showing a minimal overfitting gap of 0.0036. It also achieved the highest AUC （0.9836） in the test set， outperforming all base models. The model exhi-bited especially strong diagnostic performance for damp-heat stagnating in the lung （AUC： 0.9984） and wind pathogen latent in the lung （AUC： 0.9970）. ConclusionThe Voting ensemble algorithm effectively integrates the strengths of multiple machine learning models， resulting in an optimized diagnostic model for TCM syndromes in chronic cough with high accuracy and enhanced generalization ability.

ObjectiveTo observe the clinical efficacy and possible mechanisms of Xianglian Huazhuo Granules （香连化浊颗粒， XHG） in the treatment of chronic atrophic gastritis with intestinal metaplasia. MethodsA total of 140 patients with chronic atrophic gastritis and intestinal metaplasia were randomly divided into a treatment group and a control group， with 70 cases in each group. The treatment group received 12.5 g of XHG orally， twice daily. The control group received 12.5 g of placebo orally， twice daily. Both groups were treated for 6 months. The traditional Chinese medicine （TCM） symptom scores， pathological types， serum tumor markers of the digestive system， and serum bile acids （TBA）， interleukin-23 （IL-23）， and Dickkopf-related protein 1 （DKK-1） levels were observed before and after treatment. Safety indicators and adverse events were recorded. After treatment， TCM syndrome efficacy and pathological types were evaluated， and patients were followed up for 18 months with gastric endoscopy and pathological results， which were compared with the results after treatment finished. ResultsTwo patients dropped out in the control group， and a total of 168 cases were included in the final analysis， 70 in the treatment group and 68 in the control group. The treatment group showed a significant reduction in TCM symptom scores， serum TBA， IL-23， and DKK-1 levels， and a significant increase in alpha-fetoprotein （AFP）， carbohydrate antigen 125 （CA125）， carbohydrate antigen 199 （CA199） levels； in the control group， carcinoembryonic antigen （CEA）， CA125， CA199 levels significantly increased （P＜0.05 or P＜0.01）； and carbohydrate antigen 242 （CA242） level in both the treatment group and the control group decreased significantly （P＜0.01）. The treatment group had lower TCM symptom scores and lower levels of serum TBA， IL-23， and DKK-1 compared to the control group （P＜0.05）. The effective rate for TCM syndrome efficacy in the treatment group was 80.00% （56/70）， significantly higher than the 20.59% （14/68） in the control group （P < 0.05）. The effective rate for pathological classification in the treatment group was 72.73% （8/11） for mixed intestinal metaplasia， significantly better than 46.15% （6/13） in the control group （P＜0.05）. No adverse events were reported in either group. Among 40 patients who had a follow-up endoscopy after one year， 21 were from the treatment group， of whom 11 showed reduced intestinal metaplasia， 9 showed no significant changes， and 1 had worsened； while 19 patients in the control group had 4 with reduced intestinal metaplasia， 13 with no significant changes， and 2 with worsened conditions. No cancer was detected in either group. The treatment group showed significantly better improvement in intestinal metaplasia on follow-up gastric endoscopy pathology than the control group （P＜0.05）. ConclusionXHG can significantly improve the clinical symptoms in patients with chronic atrophic gastritis and intestinal metaplasia and reduce the degree of mixed intestinal metaplasia. The mechanism may involve lowering serum TBA， DKK-1， and IL-23 levles， thus delaying the progression from inflammation to cancer.

Objective: To create a prediction model of multidrug resistant bacterial infections for inpatients with pneumonia, so as to provide the reference for the early identification and intervention of multidrug resistant bacterial infections. Methods: The inpatients with pneumonia in the Second Affiliated Hospital of Bengbu Medical University from October 2022 to June 2024 were selected as the research subjects. Basic information and clinical data of the patients were collected. Respiratory secretions were collected for etiological culture and drug sensitivity tests to analyze the infection situation of multidrug resistant bacteria. LASSO regression and a multivariable logistic regression model were used to screen predictive factors and establish a predictive model of multidrug resistant bacterial infections for inpatients with pneumonia. The predictive effect of the model was assessed by receiver operating characteristic (ROC) curve, calibration curve, and decision curve. Results: A total of 368 inpatients with pneumonia were recruited, including 215 males (58.42%) and 153 females (41.58%). The median age was 71.00 (interquartile range, 20.00) years. There were 168 cases of multidrug resistant bacterial infections detected, with a detection rate of 45.65%. The multivariable logistic regression analysis showed that long-term bedridden patients (OR=2.699, 95%CI: 1.120-6.504), use of antibiotics within 30 days (OR=8.623, 95%CI: 2.949-25.216), respiratory failure (OR=2.407, 95%CI: 1.058-5.478), intensive care unit treatment (OR=3.995, 95%CI: 1.313-12.161), and hypoproteinemia (OR=2.129, 95%CI: 1.012-4.480) were predict factors of multidrug resistant bacterial infections for inpatients with pneumonia. The area under the ROC curve of the established multidrug resistant bacterial infection prediction model was 0.909 (95%CI: 0.879-0.939). The calibration curve after repeated sampling calibration approached the standard curve, and the predicted values were highly consistent with the measured values. The decision curve showed that when the probability threshold is 0.27-0.99, the clinical net benefit for predicting the risk of multidrug resistant bacterial infection is relatively high. Conclusion The prediction model of multidrug resistant bacteria infection constructed has a good predictive value for multidrug resistant bacterial infection among inpatients with pneumonia

Objective:To analyze the association between sleep status and ambulatory blood pressure monitoring indicators in community-dwelling hypertensive patients.Methods:It was a cross sentional study. Hypertensive patients who underwent 24-hour ambulatory blood pressure monitoring from May 2021 to April 2023 in Shanghai Xinzhuang Town were enrolled. The demographic information and sleep status of patients were obtained from the questionnaire. A TM-2430 blood pressure monitor was used to measure 24-hour ambulatory blood pressure, and the relevant indicators, including blood pressure level and blood pressure coefficient of variation were documented. The association between sleep status and blood pressure indicators was analyzed with multivariate linear regression model.Results:A total 1 135 patients aged (65.07±12.61) years were enrolled, and 473 (41.67%) of whom were males. The sleep time was<7 hours in 76 cases, 7- 8 hours in 219 cases and >8 hours in 840 cases; the bedtime was earlier than 22∶00 in 415 cases, between 22∶00 and 23∶00 in 474 cases and later than 23∶00 in 246 cases; the wake-up time was before 6∶00 in 230 cases, between 6∶00 and 7∶00 in 521 cases and after 7∶00 in 384 cases. Multivariate linear regression analysis showed that after controlling for gender and age, the sleep time was negatively associated with diurnal, noctumal and 24-hour diastolic blood pressure levels (all P<0.05), and positively associated with diurnal and noctumal systolic blood pressure coefficient of variation, noctumal diastolic blood pressure coefficient of variation, and 24-hour systolic blood pressure coefficient of variation (all P<0.05).The bedtime was positively associated with diurnal, noctumal and 24-hour diastolic blood pressure (all P<0.05), diastolic blood pressure (all P<0.05); and negatively associated with diurnal systolic blood pressure coefficient of variation, diurnal diastolic blood pressure coefficient of variation, noctumal systolic blood pressure coefficient of variation, 24-hour systolic blood pressure coefficient of variation, and 24-hour diastolic blood pressure coefficient of variation (all P<0.05). The wake-up time was positively associated with diurnal systolic blood pressure, diurnal, noctumal and 24-hour diastolic blood pressure (all P<0.05), and positively associated with diurmal systolic blood pressure and diastolic blood pressure (both P<0.05). Conclusion:Sleep status is closely associated with ambulatory blood pressure monitoring indicators in community-dwelling hypertensive patients.

ObjectiveTo investigate the effect of Dendrobium officinale polysaccharide （DOP）on CCl₄-induced hepatic fibrosis（HF）and its mechanism. MethodsA total of 56 male SD rats were randomly divided into seven groups： normal group（NG），model group（MG），colchicine group（CG， 0.1 mg/kg）， Fuzheng Huayu group（FG， 0.45 g/kg），low-dose DOP group（LDG， 0.05 g/kg），middle-dose DOP group（MDG， 0.1 g/kg）and high-dose DOP group（HDG，0.2 g/kg），with 8 rats in each group. HF rat model was established by subcutaneous injection with 40% CCl₄ olive oil mixture， every 3-day for 10 weeks. At the end of the sixth week， the drug groups were treated with colchicine， Fuzheng Huayu and DOP solution by gavage respectively， once a day for 4 weeks. NG and MG groups were similarly handled with an equal amount of 0.9 % normal saline. Liver histopathology was detected using hematoxylin-eosin （HE）， Masson and Sirius red staining； blood biochemistry was tested for liver function and four indicators of HF； RT-qPCR and Western Blot were used to measure the expression of α-SMA， Col-I， E-cadherin， and ZEB1 genes and proteins in the liver tissues of rats， respectively. ResultsHE， Masson， and Sirius red staining showed that the liver tissue of MG rats had typical pathologic features of HF， and the degree of HF was alleviated in LDG， MDG， and HDG rats， respectively. Liver function test results showed that the serum AST， TBIL， and AKP levels were significantly lower in LDG， MDG， and HDG， compared with those of the MG （P < 0.05 or < 0.01）. Meanwhile， ALT levels in serum deceased remarkably except in LDG （P < 0.05 or < 0.01）. The four results of HF showed that the serum HA， LN， PC-Ⅲ， and COL-Ⅳ levels in LDG， MDG， and HDG rats were significantly decreased compared with those of the MG （P < 0.05 or < 0.01）. The relative expressions of α-SMA， COL-I， and ZEB1 genes and proteins were significantly decreased in the liver tissues of LDG， MDG， and HDG （P < 0.05 or < 0.01）， and the relative expression of E-cadherin gene and protein increased （P < 0.05 or < 0.01）. In addition， the expressions of HA， α-SMA， COL-I， ZEB1 and E-cadherin were dependent on the dose of DOP. ConclusionDOP alleviated the degree of CCl₄ induced HF in rats by inhibiting the epithelial-mesenchymal transition in liver tissue.

Objective:Based on the questionnaire, to analyze the current status of children′s bone age assessment in China, especially the application of artificial intelligence (AI)-assisted bone age assessment system in the clinic.Methods:This was a cross-sectional study. The questionnaire was adapted by ourselves through the literature method and expert interview method, and the whole volume included 22 questions, which were released in the form of WeChat applet questionnaire star to the physician groups of several associations and entrusted to the radiology and paediatricians with senior titles. The results of the different types of questions were summarised and analyzed, and the chi-square test was used to compare the count data.Results:A total of 450 valid questionnaires were collected from 162 medical institutions in 26 provinces and cities and autonomous regions, of which 232 (51.6%) were from 87 (53.7%) tertiary hospitals and 218 (48.4%) from 75 (46.3%) secondary hospitals. Of the respondents, 115 (25.6%) were senior, 137 (30.4%) middle and 198 (44.0%) junior. Child bone age measurement was performed at 75.9% (66/87) of tertiary care organizations and 26.7% (20/75) of secondary care organizations, and the difference was statistically significant ( χ2=39.10, P<0.001). Left wrist radiographs were predominantly used for bone age assessment (76.0%, 123/162), with 72.8% (118/162) of sites using the ATLAS method of assessment and 17.9% (29/162) using the scoring method. A total of 98.4% (443/450) of respondents agreed that AI technology should be used to assist in bone age assessment, but only 9.3% (15/162) of healthcare organizations used AI-assisted technology. Conclusion:At present, bone age assessment is widely used in medical institutions, but there are problems with non-standardized examination methods, inconsistent assessment standards, and imprecise assessment results. Expectations for AI technology-assisted diagnosis exist among a wide range of physicians, but there are fewer users.

Perimenopausal syndrome （MPS）， a common endocrine system disease， is one of the diseases responding specifically to traditional Chinese medicine （TCM）. The China Association of Chinese Medicine organized experts in endocrinology， gynecology， and interdisciplinary fields of both Western and Chinese medicine to discuss the advantages and challenges of diagnosing and treating MPS with Western medicine， TCM， and integrative medicine. Experts at the conference believe that MPS is initiated by estrogen decline and rooted in deficiency， with the pathogenesis being imbalance between Yin and Yang in the kidney. The hormone replacement therapy in Western medicine for menopause can rapidly alleviate related symptoms by quickly restoring the estrogen level and timely detect and delay complications of menopause， whereas such a therapy has certain risks， necessitating close monitoring of adverse reactions. Moreover， the various contraindications and precautions limit the clinical application of the hormone replacement therapy. TCM has advantages in synergistically alleviating symptoms such as hot flashes， sweating， sleep disorders， and emotional abnormalities of MPS without causing obvious adverse reactions. However， its efficacy is slower than the hormone replacement therapy， and the TCM evidence for preventing and treating complications of menopause remains unclear. Three suggestions were proposed for the future development of both Western and TCM for ameliorating MPS. First， an integrated diagnosis and treatment system for MPS with both Western and Chinese medicine should be established. Second， high-quality evidence-based interventions for MPS should be developed with TCM alone or in combination with Western medicine. Third， efforts should be made to promote the new TCM drug development and the interdisciplinary cooperation for treating MPS.

AIM: To analyze the mechanism of Usher syndrome(USH)caused by Adgrv1 gene variation through the Hedgehog(Hh)signaling pathway.METHODS: Based on Adgrv1 gene variant mice(Adgrv1-/-), taking wild type(WT)C57BL/6 mice as controls, the expression of Adgrv1 gene and the structure of retina and cell cilia were analyzed by qRT-PCR, HE, transmission electron microscopy, and immunofluorescence. Additionally, the changes of key factors in the Hh signaling pathway caused by Adgrv1 gene variation were observed.RESULTS: The Adgrv1 gene was expressed in both the retina and primary cultured lung fibroblasts of Adgrv1-/- mice, but the expression levels were significantly decreased. The Adgrv1 gene variation can cause dissolution of the outer disc membrane of the retinal photoreceptors and significantly shorten the cilia length in primary lung fibroblasts. In the Hh signaling pathway, the expression of Ptch1 and Gli genes of Adgrv1-/- was significantly reduced, while the expression of PKA genes was increased.CONCLUSION:The Adgrv1 gene variation leads to shortened cell cilia and dissolution of the outer disc membrane of the retinal photoreceptors, resulting in retinitis pigmentosa, which is related to decreased expression of PTCH1 and GLI1 proteins in the Hh pathway.

Objective:To investigate the clinical significance of color Doppler ultrasonography combined with detection of thyroid autoantibodies in the early diagnosis of thyroid cancer.Methods:A total of 108 patients with thyroid cancer who treated in Shaoxing Central Hospital Medical Community General Hospital from September 2019 to September 2021 were selected as the research group, and 108 patients with benign thyroid lesions during the same period were selected as the control group. The ultrasound examination results and the levels of serum thyroglobulin antibody (TgAb), thyroid peroxidase antibody (TPOAb) and thyroid receptor antibody (TRAb) were compared between the two groups. The relationship between the thyroid autoantibodies index and the early diagnosis of thyroid cancer were analyzed by Spearman correlation analysis; the value of early diagnosis by color Doppler ultrasonography combined with detection of thyroid autoantibodies were evaluated by the receiver operating characteristic (ROC) curve.Results:The main features of ultrasonic images in the research group were unclear edge, low echo, irregular shape, chaotic blood flow distribution, internal micro calcification, no envelope and blood flow resistance index ≥0.7. The sensitivity of ultrasonography for the diagnosis of thyroid cancer was 86.11% (93/108), the specificity was 87.18% (102/117) and the accuracy was 90.28% (195/216). The levels of serum TgAb, TPOAb and TRAb in the research group were higher than those in control group: (32.28 ± 2.85) kU/L vs. (21.96 ± 2.54) kU/L, (81.28 ± 7.32) kU/L vs. (51.53 ± 5.86) kU/L, (4.48 ± 1.25) U/L vs. (2.35 ± 0.63 ) U/L, there were statistical differences ( P<0.05). The levels of serum TgAb, TPOAb and TRAb in patients with lymph node metastasis were higher than those in the patients without lymph node metastasis: (36.28 ± 3.12) kU/L vs. (30.60 ± 2.54) kU/L, (93.51 ± 8.57) kU/L vs. (76.13 ± 6.62) kU/L, (5.73 ± 1.54) U/L vs. (3.95 ± 1.12) U/L, there were statistical differences ( P<0.05). The levels of serum TgAb, TPOAb and TRAb in patients with stage Ⅲ-Ⅳ were higher than those in the patients with stage Ⅰ-Ⅱ: (35.84 ± 3.28) kU/L vs. (29.74 ± 2.29) kU/L, (89.35 ± 8.16) kU/L vs. (75.52 ± 6.23) kU/L, (5.28 ± 1.49) U/L vs. (3.91 ± 1.25) U/L, there were statistical differences ( P<0.05). The results of Spearman correlation analysis showed that the levels of serum TgAb, TPOAb and TRAb were positively correlated with lymph node metastasis ( r = 0.758, 0.824, 0.695, P<0.05) and clinical stage of thyroid cancer ( r = 0.735, 0.796, 0.673, P<0.05). The results of ROC curve analysis showed that the area under the curve(AUC) of ultrasound examination combined with TgAb, TPOAb and TRAb for early diagnosis of thyroid cancer was 0.930, the sensitivity was 85.19%, and the specificity was 91.67%. The combined diagnostic value was better than single diagnosis. Conclusions:Ultrasound examination combined with serum TgAb, TPOAb and TRAb has high diagnostic value for early stage thyroid cancer, which is helpful to clinically clarify the condition, and provides a reliable basis for preoperative diagnosis and targeted individualized treatment plan.

High-risk neuroblastoma (NB) is highly aggressive and has poor prognosis. Treatment of NB mainly includes comprehensive therapies, of which radiotherapy serves as a part of consolidation therapy. For patients who receive complete resection of the primary lesion, usually an irradiation dose of 21-23.4 Gy is given; for patients with incomplete resection, further study focused on radiation dose is necessary. Recurrence is most commonly observed in the bone lesions involved at presentation. Currently, the principle of irradiation to the metastatic sites is to treat lesions where metaio-dobenzylguanidine (MIBG) uptake remains positive after induction chemotherapy, or those become negative uptake but still at high risk of recurrence. On the premise of lacking of MIBG imaging, positron emission tomography CT (PET-CT) may assist in screening for metastatic sites requiring irradiation. The late side effects of radiotherapy are mainly mild musculoskeletal abnormalities. No significant increase is observed in the incidence of second primary tumor during short-term follow-up.