Objective To propose a heart sound segmentation method based on multi-feature fusion network. Methods Data were obtained from the CinC/PhysioNet 2016 Challenge dataset (a total of 3 153 recordings from 764 patients, about 91.93% of whom were male, with an average age of 30.36 years). Firstly the features were extracted in time domain and time-frequency domain respectively, and reduced redundant features by feature dimensionality reduction. Then, we selected optimal features separately from the two feature spaces that performed best through feature selection. Next, the multi-feature fusion was completed through multi-scale dilated convolution, cooperative fusion, and channel attention mechanism. Finally, the fused features were fed into a bidirectional gated recurrent unit (BiGRU) network to heart sound segmentation results. Results The proposed method achieved precision, recall and F1 score of 96.70%, 96.99%, and 96.84% respectively. Conclusion The multi-feature fusion network proposed in this study has better heart sound segmentation performance, which can provide high-accuracy heart sound segmentation technology support for the design of automatic analysis of heart diseases based on heart sounds.

Objective:To explore the application of a scenario-based onsite first-aid skills station in objective structured clinical examination (OSCE).Methods:Based on common scenarios and cases in medical practice, an evaluation framework of the OSCE onsite first-aid skills station—containing assessment indicators, exam room setting, examiner training, and assessment process—was designed to evaluate the onsite first-aid competencies of medical graduates of the five-year program for three consecutive years. SPSS 24.0 was used to perform the Kruskal-Wallis test and Pearson correlation analysis to calculate the correlation between course examination scores and OSCE onsite first-aid skills station assessment scores. Excel was used to calculate the difficulty index and discrimination index of test items.Results:The graduates' OSCE onsite first-aid skills station assessment scores were improved year by year, with a mean score of about 80 points. The station assessment items showed a moderate difficulty level (0.7-0.8), a good discrimination level (>0.4), and good internal consistency (Cronbach's α>0.7). The examiners and examinees had a high recognition of the design and effectiveness of this station assessment method. There was a positive correlation between the OSCE scores and corresponding course scores (2016, r=0.245, P=0.001; 2017, r=0.108, P=0.026; 2018, r=0.198, P=0.006). Conclusions:Through scientific scoring and strict examination management, the OSCE scenario-based onsite first-aid skills station can effectively evaluate examinees' injury treatment competencies in different situations, which can provide a reference for course teaching.

Objective    To explore the application of Tsetlin Machine (TM) in heart beat classification. Methods    TM was used to classify the normal beats, premature ventricular contraction (PVC) and supraventricular premature beats (SPB) in the 2020 data set of China Physiological Signal Challenge. This data set consisted of the single-lead electro-cardiogram data of 10 patients with arrhythmia. One patient with atrial fibrillation was excluded, and finally data of the other 9 patients were included in this study. The classification results were then analyzed. Results    The classification results showed that the average recognition accuracy of TM was 84.3%, and the basis of classification could be shown by the bit pattern interpretation diagram. Conclusion    TM can explain the classification results when classifying heart beats. The reasonable interpretation of classification results can increase the reliability of the model and facilitate people's review and understanding.

Objective     To recognize the different phases of Korotkoff sounds through deep learning technology, so as to improve the accuracy of blood pressure measurement in different populations. Methods     A classification model of the Korotkoff sounds phases was designed, which fused attention mechanism (Attention), residual network (ResNet) and bidirectional long short-term memory (BiLSTM). First, a single Korotkoff sound signal was extracted from the whole Korotkoff sounds signals beat by beat, and each Korotkoff sound signal was converted into a Mel spectrogram. Then, the local feature extraction of Mel spectrogram was processed by using the Attention mechanism and ResNet network, and BiLSTM network was used to deal with the temporal relations between features, and full-connection layer network was applied in reducing the dimension of features. Finally, the classification was completed by SoftMax function. The dataset used in this study was collected from 44 volunteers (24 females, 20 males with an average age of 36 years), and the model performance was verified using 10-fold cross-validation. Results     The classification accuracy of the established model for the 5 types of Korotkoff sounds phases was 93.4%, which was higher than that of other models. Conclusion     This study proves that the deep learning method can accurately classify Korotkoff sounds phases, which lays a strong technical foundation for the subsequent design of automatic blood pressure measurement methods based on the classification of the Korotkoff sounds phases.

Currently, in precision cardiac surgery, there are still some pressing issues that need to be addressed. For example, cardiopulmonary bypass remains a critical factor in precise surgical treatment, and many core aspects still rely on the experience and subjective judgment of cardiopulmonary bypass specialists and surgeons, lacking precise data feedback. With the increasing elderly population and rising surgical complexity, precise feedback during cardiopulmonary bypass becomes crucial for improving surgical success rates and facilitating high-complexity procedures. Overcoming these key challenges requires not only a solid medical background but also close collaboration among multiple interdisciplinary fields. Establishing a multidisciplinary team encompassing professionals from the medical, information, software, and related industries can provide high-quality solutions to these challenges. This article shows several patents from a collaborative medical and electronic information team, illustrating how to identify unresolved technical issues and find corresponding solutions in the field of precision cardiac surgery while sharing experiences in applying for invention patents.

bjective    To use machine learning technology to predict the recurrence of atrial fibrillation (AF) after radiofrequency ablation, and try to find the risk factors affecting postoperative recurrence. Methods    A total of 300 patients with valvular AF who underwent radiofrequency ablation in West China Hospital and its branch (Shangjin Hospital) from January 2017 to January 2021 were enrolled, including 129 males and 171 females with a mean age of 52.56 years. We built 5 machine learning models to predict AF recurrence, combined the 3 best performing models into a voting classifier, and made prediction again. Finally, risk factor analysis was performed using the SHApley Additive exPlanations method. Results    The voting classifier yielded a prediction accuracy rate of 75.0%, a recall rate of 61.0%, and an area under the receiver operating characteristic curve of 0.79. In addition, factors such as left atrial diameter, ejection fraction, and right atrial diameter were found to have an influence on postoperative recurrence. Conclusion    Machine learning-based prediction of recurrence of valvular AF after radiofrequency ablation can provide a certain reference for the clinical diagnosis of AF, and reduce the risk to patients due to ineffective ablation. According to the risk factors found in the study, it can provide patients with more personalized treatment.

Objective    To evaluate the use of machine learning algorithms for the prediction and characterization of cardiac thrombosis in patients with valvular heart disease and atrial fibrillation. Methods    This article collected data of patients with valvular disease and atrial fibrillation from West China Hospital of Sichuan University and its branches from 2016 to 2021. From a total of 2 515 patients who underwent valve surgery, 886 patients with valvular disease and atrial fibrillation were included in the study, including 545 (61.5%) males and 341 (38.5%) females, with a mean age of 55.62±9.26 years, and 192 patients had intraoperatively confirmed cardiac thrombosis. We used five supervised machine learning algorithms to predict thrombosis in patients. Based on the clinical data of the patients (33 features after feature screening), the 10-fold nested cross-validation method was used to evaluate the predictive effect of the model through evaluation indicators such as area under the curve, F1 score and Matthews correlation coefficient. Finally, the SHAP interpretation method was used to interpret the model, and the characteristics of the model were analyzed using a patient as an example. Results    The final experiment showed that the random forest classifier had the best comprehensive evaluation indicators, the area under the receiver operating characteristic curve was 0.748±0.043, and the accuracy rate  reached 79.2%. Interpretation and analysis of the model showed that factors such as stroke volume, peak mitral E-wave velocity and tricuspid pressure gradient were important factors influencing the prediction. Conclusion    The random forest model achieves the best predictive performance and is expected to be used by clinicians as an aided decision-making tool for screening high-embolic risk patients with valvular atrial fibrillation.

Objective To study the curative effect and the prognostic factors of endoscopic traumatic optic neuropathy (TON). Methods The clinical data of 53 patients with TON from 2010 to 2015 years was retrospectively analyzed. Divided the patients into the surgery group and the non-surgery group, according to whether or not accept the treatment of endoscopic optic decompression. And evaluating the potential prognostic factors in chi-square test, group t-test and multiple regression analysis. Results In 53 patients (55 eyes ), 31 eyes have no visual acuity before treated: 8 eyes’ visual acuity was improved in 16 eyes (8/16) that accepted operation; 3 eyes’ visual acuity was improved in 15 eyes (3/15) that with non-operation;24 eyes have visual acuity before treated:11 eyes’ visual acuity was improved in 14 eyes (11/14) that accepted operation;3 eyes’ visual acuity was improved in 10 eyes (3/10) that with non-operation;19 eyes’ visual acuity was improved in 30 eyes (19/30) that accepted operation, the total effective rate was 63.3%, and there was no complications happened in the patients who accepted operation. The age, eye-side, sex, visual acuity, optic canal fracture , orbit fracture , all these factors have no correlation to the prognosis (P>0.05), but the interval time between injury and operation (less than 3 days) and the way of the treatment are benefit to improve vision (P<0.05). Conclusions The endoscopic optic decompression is an effective treatment in TON, and it’s better to improve vision in 3-day after TON.

Objective: To summarize our experience in the diagnosis of internal carotid artery trauma in patients with traumatic optic neuropathy, and to make recommendations for the treatment. Methods: The clinic data of 6 cases who had traumatic optic neuropathy with internal carotid artery trauma and who were admited in Department of Otorhinolaryngology, the Second Affiliated Hospital and Yuying Children′s Hospital of Wenzhou Medical University from Jan. 2013 to Dec. 2015 were analyzed retrospectively. Results: All 6 cases were monocular blindness. Four cases did not undergo nasal endoscopic optic nerve decompression because of the diagnoses of internal carotid artery trauma. One case was diagnosed after nasal endoscopic optic nerve decompression because of fatal bleeding during the operation. One case was diagnosed because of late-onset recurrent epistaxis. Among the 6 cases with internal carotid artery trauma, 3 cases were successfully treated with endovascular interventional treatment (stent embolization was used in one case, Coil embolization was used in two cases), and 3 patients refused treatment. Conclusions The patients with traumatic optic neuropathy have the possibility of severe carotid artery trauma. Endoscopic optic nerve decompression is not suitable for these cases. It should pay more attention to patients with traumatic optic neuropathy. For suspected cases, vascular-enhanced computed tomography screening and digital subtraction angiography should be recommended and patients should be treated by endovascular intervention in a timely manner.

Objective To explore the basic biological characteristics of lncRNA -uc.1 67,and its spatial dis-tribution,temporal expression pattern during the mouse embryonic development.Methods The UCSC genome browser of ENCODE was used to analyze preliminary bioinformatics of lncRNAs.Real -time (RT)-PCR was applied to detect the expression of uc.1 67 and neighboring genes in the embryonic mouse heart in different stages (P7.5,P1 1 .5,P1 4.5, P1 8.5).Dimethyl sulphoxide was used to induce P1 9 cell differentiation into the cardiomyocytes.RT -PCR was applied to detect the expression changes in uc.1 67 and neighboring genes on differential day 0,4,6,8 and 1 0.Results Full -length of human uc.167 was 201 bp,and human uc.167 was located in the genome 5q14.3 (chr5:88179623 -881 79824,GRCh37 /hg1 9).uc.1 67 mainly expressed in the ventricular muscle tissue.The expression of uc.1 67 was gradually decreased in the mouse embryonic heart development process(P7.5:1 .000 ±0.1 00,P1 1 .5:0.71 4 ±0.1 07, P1 4.5:0.393 ±0.043,P1 8.5:0.1 25 ±0.01 3),while the expression of its neighboring Mef2c gene was gradually in-creased(P7.5:1 .081 ±0.1 1 8,P1 1 .5:2.340 ±0.351 ,P1 4.5:3.958 ±0.542,P1 8.5:9.361 ±0.722),which showed an opposite trend.The expression of uc.1 67 during P1 9 cell differentiation into cardiomyocytes showed a an increase at first and then a decreasepattern,and the highest level expression of uc.1 67 was on differential day 4(d0:1 .071 ± 0.1 1 7,d4:4.71 4 ±0.501 ,d6:3.572 ±0.41 4,d8:2.550 ±0.31 4,d1 0:0.786 ±0.085).The expression of neigh-boring gene Mef2c was in an opposite trend(d0:1 .01 2 ±0.041 ,d4:0.353 ±0.037,d6:2.470 ±0.329,d8:6.706 ± 0.682,d1 0:7.765 ±0.705).Conclusions It is suggested that uc.1 67 may take part in the process of embryonic heart development and may play a role through negatively regulating its neighboring gene Mef2c.