Objective To identify the heart sounds of aortic stenosis by deep learning model based on DenseNet121 architecture, and to explore its application potential in clinical screening aortic stenosis. Methods We prospectively collected heart sounds and clinical data of patients with aortic stenosis in Tianjin Chest Hospital, from June 2021 to February 2022. The collected heart sound data were used to train, verify and test a deep learning model. We evaluated the performance of the model by drawing receiver operating characteristic curve and precision-recall curve. Results A total of 100 patients including 11 asymptomatic patients were included. There were 50 aortic stenosis patients with 30 males and 20 females at an average age of 68.18±10.63 years in an aortic stenosis group (stenosis group). And 50 patients without aortic valve disease were in a negative group, including 26 males and 24 females at an average age of 45.98±12.51 years. The model had an excellent ability to distinguish heart sound data collected from patients with aortic stenosis in clinical settings: accuracy at 91.67%, sensitivity at 90.00%, specificity at 92.50%, and area under receiver operating characteristic curve was 0.917. Conclusion The model of heart sound diagnosis of aortic stenosis based on deep learning has excellent application prospects in clinical screening, which can provide a new idea for the early identification of patients with aortic stenosis.
Objective The purpose of this study was to establish and validate a risk prediction model for post-thrombotic syndrome (PTS) in patients after interventional treatment for acute lower extremity deep vein thrombosis (LEDVT). MethodsA retrospective study was conducted to collect data from 234 patients with acute LEDVT who underwent interventional treatment at Xuzhou Central Hospital between December 2017 and June 2022, serving as the modeling set. Factors influencing the occurrence of PTS were analyzed, and a nomogram was developed. An additional 98 patients from the same period treated at Xuzhou Tumor Hospital were included as an external validation set to assess the reliability of the model. ResultsAmong the patients used to establish the model, the incidence of PTS was 25.2% (59/234), while in the validation set was 31.6% (31/98). Multivariate logistic regression analysis of the modeling set identified the following factors as influencing PTS: age (OR=1.076, P=0.001), BMI (OR=1.163, P=0.004), iliac vein stent placement (OR=0.165, P<0.001), history of varicose veins (OR=5.809, P<0.001), and preoperative D-dimer level (OR=1.341, P<0.001). These 5 factors were used to construct the risk prediction model. The area under the ROC curve (AUC) of the model was 0.869 [95%CI (0.819, 0.919)], with the highest Youden index of 0.568, corresponding to a sensitivity of 79.7% and specificity of 77.1%. When applied to the validation set, the AUC was 0.821 [95%CI (0.734, 0.909)], with sensitivity of 77.4%, specificity of 76.1%, and accuracy of 76.6%. ConclusionsThe risk prediction model for PTS established in this study demonstrates good predictive performance. The included parameters are simple and practical, providing a useful reference for clinicians in the preliminary screening of high-risk PTS patients.