Cardiac auscultation is the basic way for primary diagnosis and screening of congenital heart disease(CHD). A new classification algorithm of CHD based on convolution neural network was proposed for analysis and classification of CHD heart sounds in this work. The algorithm was based on the clinically collected diagnosed CHD heart sound signal. Firstly the heart sound signal preprocessing algorithm was used to extract and organize the Mel Cepstral Coefficient (MFSC) of the heart sound signal in the one-dimensional time domain and turn it into a two-dimensional feature sample. Secondly, 1 000 feature samples were used to train and optimize the convolutional neural network, and the training results with the accuracy of 0.896 and the loss value of 0.25 were obtained by using the Adam optimizer. Finally, 200 samples were tested with convolution neural network, and the results showed that the accuracy was up to 0.895, the sensitivity was 0.910, and the specificity was 0.880. Compared with other algorithms, the proposed algorithm has improved accuracy and specificity. It proves that the proposed method effectively improves the robustness and accuracy of heart sound classification and is expected to be applied to machine-assisted auscultation.
ObjectiveTo investigate the anesthesia management of transcatheter ultrasound-guided percutaneous interventional therapy for pediatric patients with congenital heart disease at a mobile surgical platform. Methods From March to July 2023, 13 patients in remote areas underwent interventional surgery on the mobile truck operating platform. The patients undergoing general anesthesia using non-tracheal intubation were collected. ResultsFinally, 8 patients received monitored anesthesia care (MAC) with local anesthesia-assisted sedation and analgesia drugs under the supervision of anesthesiologists (general anesthesia using non-tracheal intubation), due to the patients having difficulty cooperating with the surgery (young age, nervous mood, and crying), including 5 males and 3 females with an average age of 6.95±3.29 years and an average weight of 19.50±6.04 kg. There were 6 patients diagnosed with atrial septal defect, 1 patient with residual shunt after patent ductus arteriosus ligation, and 1 patient with severe pulmonary stenosis by transthoracic ultrasonography. The surgical process was smooth, analgesia was perfect, anesthesia and surgical effect were satisfactory, postoperative recovery was satisfactory, and there were no surgical or anesthesia complications. The anesthesia time was 41.53±8.62 min, the operation time was 39.88±8.52 min, and the recovery time was 41.50±14.56 min. Conclusion Transthoracic ultrasound-guided interventional surgery is a minimally invasive approach for congenital heart disease, offering the advantages of zero radiation exposure. Non-tracheal general anesthesia preserved spontaneous breathing can be safely and effectively administered to pediatric patients who cannot cooperate in mobile operating platform.