Objectives: We aimed to test our expectation that additional administration of Traditional Chinese medicine (TCM), maxingshigan-weijing decoction, is more effective in the management of COVID-19 patients compared to those treated with routine supportive care alone. Trial design: This is a multicenter, open-label 2-arm (1:1 ratio) randomized controlled trial. Participants: Patients will be recruited from 3 hospitals in Wenzhou China: the First Affiliated Hospital of Wenzhou Medical University, the Second Affiliated Hospital of Wenzhou Medical University and Wenzhou Center Hospital. The inclusion and exclusion criteria are as follows: Inclusion criteria 1. Participants are 18-85 years of age, either male or female. 2. Diagnosed as positive for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) 3. Symptomatic. Mild (mild clinical symptoms without signs of pneumonia in chest X-ray) and Moderate (fever or respiratory symptom with signs of pneumonia in chest X-ray) . 1. Signed the informed consent before treatment. 2. Agreed not to enroll in any other clinical trials. 3. Inpatients Exclusion criteria 1. < 18 or > 85 years old. 2. Pregnancy and lactation. 3. Serious heart, liver, kidney and hematopoietic system diseases, abnormal liver or kidney function. 4. Suffering from other known virus pneumonia. 5. Allergic to Chinese herbal medicine or suffering from allergies. 6. Critical patients (respiratory failure treated by mechanical ventilation or shock or multiple organ failure). Intervention and comparator: Patients in the control group will receive routine supportive clinically care including the therapies of anti-viral, anti-bacterial and ameliorating the related symptoms, while patients in TCM group will be asked to take maxingshigan-weijing decoction (composed of 14 Chinese herbal medicines), orally 200 mL 2 times daily, for 14 consecutive days in addition to routine supportive care as mentioned above. Maxingshigan-weijing decoction consists of 10 g of Herba Ephedra (Mahuang), 10 g of Amygdalus Communis Vas (Xingren), 45 g of Gypsum Fibrosum (Shigao), 30 g of Rhizoma phragmitis (Lugen), 20 g of Peach kernel (Taoren), 20 g of Winter Melon kernel (Dongguaren), 30 g of Trichosanthes Kirilowii Maxim (Gualou), 12 g of Pericarpium Citri Reticulatae (Chenpi), 12 g of Rhizoma Pinelliae (Jiangbanxia), 12 g of caulis bambusae in taeniis (Zhuru), 30 g of semen lepidii (Tingliz), 15 g of semen lepidii (Shichangpu), 10 g of curcuma zedoary (ezhu) and 5 g of Radix Glycyrrhizae (Gancao). Main outcomes: The primary outcome will be the number of days until the clinical symptom of fever improves in the first 14 days of treatment following randomisation. Fever will be defined as an improvement when the temperature is less than 37°C. Secondary outcomes will be TCM Syndrome Scores, the time it takes until individuals have negative test results for SARS-CoV-2 nucleic acid, the proportion of cases with chest X-ray improvements and the rate of symptom (fever, cough, malaise, shortness of breath) recovery. TCM Syndrome Scoring System is a checklist covering 4 main, 7 secondary and 13 accompanying items. The 4 main items consisting of fever, cough, malaise and shortness of breath, use a four-point scale (0, 2, 4 and 6) depending on the severity; the 7 secondary items including dysphoria, diarrhea, pharyngalgia, expectoration, muscular soreness, nasal obstruction and rhinorrhoea use 0-3-point scale; the 13 accompanying items contain chest pain, headache, aversion to cold, dizziness, nausea and vomiting, anorexia, abdominal distension, dry mouth, anxiety, spontaneous sweating, insomnia, wheezing and blood tinged sputum, and each item is rated on 0-1 scale ( 0 stands for asymptomatic, 1 stands for symptomatic ). The total scores sum up to a range from 0 to 58, with higher scores indicating more severe levels of disease. Randomization: Minimization method will be used, balancing the two arms for pneumonia severity. Patients are randomized (1:1 ratio) to each group. Clinical researchers will get a random sequence number which is automatically generated by a random number generator (IBM Corp., Armonk, NY, USA), and sequentially number them in an opaque envelope. Researchers will open random allocation envelopes and assign participants accordingly. Eligible patients will be randomly divided into a routine supportive care group and a routine supportive care plus oral administration of traditional Chinese medicine group, with 70 patients in each group. Blinding (masking): This is an open-label study. The statistical analysis will be carried out by the Professor of Statistics at Wenzhou Medical University, who is blinded to patient allocation. Numbers to be randomised (sample size): The previous study reported the efficacy of TCM for COVID-19 and H1N1 influenza patients, the median survival time in the TCM group is estimated as 3 days; this time will be 1.5 times longer in the control group. Accordingly, Kaplan-Meier method and log-rank test will be used. And assuming a statistical power of 70% (one-sided type-1 error of α = 5%, β = 30%) and a rate of withdrawal and loss to follow-up of 10%, we plan to include 140 participants in both groups ( TCM group = 70, control group = 70). Trial Status: The trial protocol is Version 2.0, October 14, 2020. Recruitment began March, 2020, and is anticipated to be completed by December 31, 2020. Trial registration: Chinese Clinical Trial Registry, ChiCTR2000030759. Registered on 13 March 2020. Full protocol: The full protocol is attached as an additional file, accessible from the Trials website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this Letter serves as a summary of the key elements of the full protocol.

Background: The aim of the present study was to investigate the intrinsic relationship between cultural values and social network index among college students. In addition, the present study explored the mediating role of self-monitoring in the relationship between horizontal collectivism cultural values and social network index, as well as the moderating role of self-efficacy, to provide a theoretical approach based on the intrinsic mechanism for college students to establish a good social network.Methods: A simple random cluster sampling method was used to investigate 376 college students with cultural values scale, self-monitoring scale, self-efficacy scale, and social network index scale, structural equation model was constructed using M-plus and SPSS.Results: The result indicated that individual horizontal collectivist cultural values positively predict social network index (β = 0.477). Self-monitoring plays an intermediary role between cultural values and social network index, and self-efficacy plays a moderating role between self-monitoring and social network index.Conclusion: The level of an individual’s social network activity is affected by the cultural values of horizontal collectivism and self-monitoring. Improving individual self-monitoring ability and self-efficacy can effectively improve the interpersonal relationships of college students.

Accurately distinguishing benign from malignant adrenal lesions remains a clinical challenge, especially in oncology patients with indeterminate imaging findings. This study aimed to develop and interpret machine learning (ML) models for classifying adrenal lesions based on 18 F-FDG PET/CT imaging and clinical parameters. A retrospective cohort of 255 patients undergoing 18 F-FDG PET/CT was analyzed. Imaging features—including adrenal SUVmax, SUVpeak, tumor diameter, CT attenuation, and tumor-to-liver SUVmax ratio (T/L SUVmax)—along with clinical variables were extracted. Two classification tasks were constructed: (1) differentiation of benign and malignant adrenal lesions; and (2) subtyping of malignant lesions into lung cancer metastases or lymphoma. Seven ML models were trained and evaluated using 10-fold cross-validation. SHAP (SHapley Additive exPlanations) analysis was applied to elucidate feature contributions. For the benign/malignant classification, ensemble models (Random Forest, Bagging, XGBoost) achieved outstanding performance (AUC > 0.99), with Bagging yielding 100% recall. T/L SUVmax, adrenal SUVmax, and CT attenuation emerged as top predictors. In malignancy subtyping, the artificial neural network (ANN) attained the highest AUC (0.887) and F1-score (0.851). SHAP analysis highlighted distinct metabolic patterns, with lymphoma showing higher SUVmax and T/L ratios, and lung metastases associated with higher CT values. Machine learning models based on PET/CT-derived features enable highly accurate and interpretable classification of adrenal lesions. Integrating metabolic and anatomical parameters improves diagnostic precision, while SHAP analysis offers clinical transparency, supporting personalized decision-making in adrenal lesion management.

Background: Patients with differentiated thyroid cancer (DTC) may have occult lung metastases before ¹³¹ iodine ( ¹³¹ I) treatment. Identifying occult lung metastases before ¹³¹ I treatment is of great clinical value for the correct staging of patients and the establishment of ¹³¹ I treatment plans. Our research is of great significance in establishing statistical models for clinical data using machine learning algorithms to study the prediction of lung metastasis before ¹³¹ I treatment. Methods: Patients were selected from Zhejiang cancer hospital and data was from two groups of DTC patients treated with ¹³¹ I, where the experimental group consisted of 55 patients who showed no lung metastases on CT but tested positive on ¹³¹ I-whole body scan ( ¹³¹ I-WBS). The control group included 316 patients who tested negative for metastases across CT, ultrasound, and ¹³¹ I-WBS. Six machine learning algorithms such as Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbors (KNN) were employed to predict models and AUC, sensitivity, accuracy, precision, specificity, F1 Score were used to compare the performance between each models. Finally, the SHAP algorithm was used to explain the importance rank of the features. Results: A total of 371 thyroid cancer patients were included in this study, 55 patients with occult lung metastasis and 316 patients in the control group. The data is divided into a training set and a testing set in a 7:3 ratio. Eleven acceptable variables analyzed including gender, age, T stage, N stage, tumor size, degree of invasion, number of lymph node metastases count, Thyroid Stimulating Hormone (TSH), thyroglobulin (Tg), Thyroglobulin antibodies (Tgab), and administrated activity were screened out by multivariate Cox regression. Evaluation indicators of the best model- LR were as following: accuracy (0.91), recall rate (0.64), precision (0.92), F1-s core (0.70), Area Under Curve (AUC) value (0.93), and the Specificity score (0.96). Conclusion: The logistic model (LR) showed the best performance in predicting occult lung metastases of thyroid cancer patients before ¹³¹ I-WBS. Lymph nodes metastases and throglobulin have the most significant impact on the prediction.