Objective:To investigate the effects of external application of Sanying Plaster on the size of thyroid nodules and the states of depression and anxiety in patients with benign thyroid nodules.Methods:A randomized controlled trial was conducted. A total of 120 patients with benign thyroid nodules from the outpatient clinic of the Department of Thyroid Diseases at Shanghai Traditional Chinese Medicine Hospital from June to December 2022 were selected as the subjects of the study. They were divided into two groups using the random number table method, with 60 patients in each group. The control group received lifestyle intervention treatment, while the treatment group received Sanying Ointment in addition to the treatment of the control group. Both groups were treated for 3 months. TCM syndrome scores were measured before and after treatment; the maximum diameter of thyroid nodules was measured using a color Doppler ultrasound transverse section; the quality of life was assessed using the short form 36 (SF-36); the degree of anxiety and depression was evaluated using the self-rating anxiety scale (SAS) and the self-rating depression scale (SDS); adverse reactions during the treatment period were recorded, and the clinical efficacy was evaluated.Results:During the treatment period, 4 cases in the treatment group and 3 cases in the control group did not complete the treatment. Finally, 56 cases in the treatment group and 57 cases in the control group entered the efficacy evaluation. The total effective rate of the treatment group was 71.4% (40/56), and that of the control group was 14.0% (8/57), with a statistically significant difference between the two groups ( χ2=26.82, P<0.001). After treatment, the TCM syndrome score of the treatment group (10.02±3.65 vs. 16.65±3.44, t=-10.24) was lower than that of the control group ( P<0.001); the maximum diameter of thyroid nodules [11.00 (4.65, 19.93) mm vs. 15.00 (7.15, 28.50) mm, Z=-2.43] was lower than that of the control group ( P<0.05); the SF-36 score [121.83 (117.00, 130.00) vs. 114.42 (104.25, 127.50), Z=-2.62] was higher than that of the control group ( P<0.01); the SDS (46.72±4.59 vs. 57.02±5.99, t=14.80) and SAS (42.25±5.72 vs. 50.60±7.12, t=10.04) scores were lower than those in the control group ( P<0.001). The incidence of adverse reactions during the treatment period in the treatment group was 3.5% (2/57), and no adverse reactions occurred in the control group. Conclusion:The external application of Sanying Ointment helps to reduce the size of thyroid nodules in patients with benign thyroid nodules, improve the quality of life and anxiety and depression, and increase clinical efficacy with good safety.

Background: This study aimed to develop a diabetic kidney disease (DKD) prediction model using long short term memory (LSTM) neural network and evaluate its performance using accuracy, precision, recall, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Methods: The study identified DKD risk factors through literature review and physician focus group, and collected 7 years of data from 6,040 type 2 diabetes mellitus patients based on the risk factors. Pytorch was used to build the LSTM neural network, with 70% of the data used for training and the other 30% for testing. Three models were established to examine the impact of glycosylated hemoglobin (HbA1c), systolic blood pressure (SBP), and pulse pressure (PP) variabilities on the model’s performance. Results: The developed model achieved an accuracy of 83% and an AUC of 0.83. When the risk factor of HbA1c variability, SBP variability, or PP variability was removed one by one, the accuracy of each model was significantly lower than that of the optimal model, with an accuracy of 78% (P<0.001), 79% (P<0.001), and 81% (P<0.001), respectively. The AUC of ROC was also significantly lower for each model, with values of 0.72 (P<0.001), 0.75 (P<0.001), and 0.77 (P<0.05). Conclusion The developed DKD risk predictive model using LSTM neural networks demonstrated high accuracy and AUC value. When HbA1c, SBP, and PP variabilities were added to the model as featured characteristics, the model’s performance was greatly improved.