Objective To explore oropharyngeal swallowing disorders with videofluoroscopic swallowing study (VFSS). Methods 16 patients with dysphagia accepted VFSS with 10 ml of thin barium meal (50% w/v), thick barium meal (270% w/v), biscuit coated with thick barium meal in single swallow. Their swallowing function was observed on the lateral and anterior/posterior planes, including: symmetry of pyriform sinuses, oral transit time, presence of pharyngeal delay, pharyngeal transit time, oral and pharyngeal residue, and presence of aspiration.Results 5 patients demonstrated oral swallowing disorder. 3 patients demonstrated pharyngeal swallowing disorders, that was pharyngeal delay which caused in aspiration after swallowing. 8 patients demonstrated oropharyngeal swallowing disorders, and 3 of them presented aspiration,2 patients were silent aspirators, 1 was aspiration before and 1 after swallowing. The aspiration time could not be judged from the videofluoroscopy in the other one. For 4 patients with aspiration, 3 were severe, with more than 25% of the bolus aspirated, and 1 aspirated less than 5%. Conclusion VFSS can be helpful to plan individual rehabilitation.

Purpose/Significance To apply deep learning technology to achieve the purpose of tongue image analysis automation,so as to provide references for the standardization of tongue image of traditional Chinese medicine(TCM),and further promote the moderni-zation of TCM diagnosis and treatment technology.Method/Process It develops a new semantic segmentation loss function with region-based correlation and label relaxation to enhance the capability of tongue image segmentation model to learn pixel relationships and handle mislabeled data.Additionally,leveraging inherent color-related priors in tongue image features,the model is simplified by decomposing it into two multi-label classification tasks,thereby accelerating model training and reducing its complexity.Result/Conclusion The pro-posed algorithm is proven effective on a self-constructed dataset,attaining a high 96.57％MIoU in tongue segmentation,and demon-strating strong performance with a macro F1-score of 88.58％and average accuracy of 82.59％.

ObjectiveTo explore the association between triglyceride-glucose （TyG） index and major adverse cardiovascular events （MACEs） risk in coronary heart disease （CHD） patients with blood stasis syndrome after percutaneous coronary intervention （PCI）. MethodsA total of 857 CHD patients with blood stasis syndrome after PCI were enrolled and divided into four groups according to the baseline TyG index quartiles， Q1 （TyG ＜ 8.51）， Q2 （8.51 ≤ TyG ＜ 8.88）， Q3 （8.88 ≤ TyG ＜ 9.22）， and Q4 （TyG ≥ 9.22）. The clinical outcome was defined as a compound endpoint of cardiovascular events including cardiac death， non-fatal myocardial infarction， unplanned revascularization， in-stent restenosis and stroke. The machine learning Boruta algorithm was used for feature selection related to MACEs risk. Kaplan-Meier survival analysis and Cox proportional hazards regression model were used to compare the differences in MACEs risk among the four groups. Restricted cubic spline （RCS） and subgroup analysis were performed to determine the relationship between the TyG index and MACEs risk. The area under the receiver operating characteristic （ROC） curve （AUC）， calibration curve and Hosmer-Lemeshow test， and decision curve analysis （DCA） were plotted to evaluate the predictive value of the TyG index for MACEs risk. ResultsThe median follow-up time of the included patients was 2.45 years. During the follow-up period， 313 cases （36.52%） of new MACEs occurred. The incidence of MACEs in Q1， Q2， Q3， Q4 group was 28.17% （60/213）， 29.05% （61/210）， 39.45% （86/218） and 49.07% （106/216）， respectively. Kaplan-Meier survival analysis suggested statistically significant differences in MACEs risk among the four groups （P＜0.001）. Cox proportional hazards regression model analysis found that the risk of MACEs in patients with high TyG index increased by 60.1% （P＜0.01）. Using Q1 as the reference， the MACEs risk in Q2， Q3 and Q4 groups gradually increased， and the trend was statistically significant （P＜0.05）. RCS model suggested that the TyG index was nonlinearly associated with the MACEs risk （P＜0.001）. The TyG index had a good predictive performance for MACEs risk according to ROC analysis （AUC=0.758， 0.724-0.792） and Hosmer-Lemeshow test （χ² = 4.319， P = 0.827）. Additionally， DCA analysis also suggested a good clinical efficacy of the TyG index for predicting MACEs. Subgroup analysis showed that different baseline TyG index was positively correlated with the MACEs risk in the stratification of age， male， BMI， history of diabetes and hypertension， and low-density lipoprotein cholesterol （LDL-C）≥1.8 mmol·L^-1（P＜0.05）. ConclusionThe elevated TyG index is closely corrected with an increased risk of MACEs in CHD patients with blood stasis syndrome after PCI， indicating a guiding significance for early risk stratification and clinical decisions.

ObjectiveTo establish and validate a clinical prediction model for 1-year major adverse cardiovascular events（MACEs）risk after percutaneous coronary intervention （PCI） in coronary heart disease （CHD） patients with blood stasis syndrome. MethodThe consecutive CHD patients diagnosed with blood stasis syndrome in the Department of Integrative Cardiology at China-Japan Friendship Hospital from September 1， 2019 to March 31， 2021 were selected for a retrospective study， and basic clinical features and relevant indicators were collected. Eligible patients were classified into a derivation set and a validation set at a ratio of 7∶3， and each set was further divided into a MACEs group and a non-MACEs group. The factors affecting the outcomes were screened out by least absolute shrinkage and selection operator （Lasso） and used to establish a logistic regression model and identify independent prediction variables. The goodness-of-fit of the model was evaluated by the Hosmer-Lemeshow test， and the area under curve （AUC） of the receiver operating characteristic （ROC） curve， calibration curve， decision curve analysis （DCA）， and clinical impact curve （CIC） were employed to evaluate the discrimination， calibration， and clinical impact of the model. ResultA total of 731 consecutive patients were assessed and 404 eligible patients were enrolled， including 283 patients in the derivation set and 121 patients in the validation set. Lasso identified ten variables influencing outcomes， which included age， sex， fasting plasma glucose （FPG）， triglyceride （TG）， low-density lipoprotein cholesterol （LDL-C）， homocysteine （Hcy）， brachial-ankle pulse wave velocity （baPWV）， flow-mediated dilatation （FMD）， left ventricular ejection fraction （LVEF）， and Gensini score. The multivariate Logistic regression preliminarily identified age， FPG， TG， Hcy， LDL-C， LVEF， and Gensini score as the independent variables that influenced the outcomes. Of these variables， male， high FMD and high LVEF were protective factors， and the rest were risk factors. The prediction model for 1-year MACEs risk after PCI in CHD patients with blood stasis syndrome showed χ²=12.371 （P=0.14） in Hosmer-Lemeshow test and the AUC of 0.90. With the threshold probability > 10%， the model showed better prediction performance for 1-year MACEs risk after PCI in CHD patients with blood stasis syndrome than for that in all the patients. With the threshold probability > 60%， the estimated value was much closer to the real number of patients. ConclusionThe established clinical prediction model facilitates the early prediction of 1-year MACEs risk after PCI in CHD patients with blood stasis syndrome， which can provide ideas for the precise treatment of CHD patients after PCI and has guiding significance for improving the prognosis of the patients. Meanwhile， multi-center studies with larger sample sizes are expected to further validate， improve， and update the model.