Objective To propose a lightweight end-to-end neural network model for automated Korotkoff sound phase recognition and subsequent blood pressure (BP) measurement, aiming to improve measurement accuracy and population adaptability. Methods We developed a streamlined architecture integrating depthwise separable convolution (DSConv), multi-head attention (MHA), and bidirectional gated recurrent unit (BiGRU). The model directly processes Korotkoff sound time-series signals to identify auscultatory phases. Systolic BP (SBP) and diastolic BP (DBP) were determined using phase Ⅰ and phaseⅤdetections, respectively. Given the clinical relevance of phase Ⅳ for specific populations (e.g., children and pregnant women, denoted as DBPⅣ), BP values from this phase were also recorded.Results The study enrolled 106 volunteers with 70 males and 36 females at mean age of (40.0±12.0) years. The model achieved 94.25% phase recognition accuracy. Measurement errors were (0.1±2.5) mm Hg (SBP), (0.9±3.4) mm Hg (DBPⅣ), and (0.8±2.6) mm Hg (DBP). Conclusion Our method enables precise phase recognition and BP measurement, demonstrating potential for developing population-adaptive blood pressure monitoring systems.

The European Society of Cardiology (ESC) and the European Association for Cardio-Thoracic Surgery (EACTS) have recently updated and published the 2024 ESC guidelines for the management of atrial fibrillation. Based on the latest evidences, the guidelines have been updated in many aspects, such as diagnostic criteria for atrial fibrillation, AF-CARE treatment principles, comorbidities and risk factor management. In particular, there are significant changes in the recommendations for surgical management of atrial fibrillation in the guidelines. Therefore, this paper aims to interpret the content updates of the guidelines in AF-CARE treatment principles, diagnostic criteria and surgical treatment of atrial fibrillation, especially highlighting the updates and new suggestions about surgical treatment of atrial fibrillation.

Objective: Based on the theoretical framework of Risk Perception-Efficacy Appraisal-Behavioral Response, the study aims to explore the group heterogeneity in high temperature health risk perception and behavioral responses among college students in Chongqing, so as to provide a scientific basis for implementing differentiated health interventions. Methods: A multi stage cluster sampling method was used to select 856 students from five universities in Chongqing. Data were collected using a validated questionnaire. One way analysis of variance and independent samples t-test were used to analyze individual differences, Pearson correlation analysis was employed to examine relationships between variables, multiple linear regression was used to identify influencing factors, a structural equation model was constructed to validate the theoretical pathways, and the Bootstrap method was applied to test mediating effects. Results: In the risk perception dimension, the severity score of high temperature health hazards among college students (3.28±0.89) was higher than that of susceptibility score (2.94±0.93). Efficacy appraisal showed that the response efficacy score was the highest (3.91±0.81). In behavioral responses, adaptive behaviors were most prominent (5.43±2.75), while emergency preparedness behaviors were the lowest (2.71±1.33). The structural equation model validated the pathway of "threat appraisal → efficacy appraisal → behavioral response" ( χ 2/df=2.49, RMSEA =0.05). Self efficacy played a fully mediating role between threat appraisal and behavioral response, with a mediation effect value of 0.10 (95% CI =0.02-0.19). K means cluster analysis categorized the subjects into three groups, with the core barriers to behavior being economic constraints (22.3%), lack of motivation (34.8%), and insufficient cognition (34.1%), respectively. Conclusions Decision making regarding high temperature health behaviors among college students follows psychological pathway of "cognition-appraisal-action" with self efficacy serving as a key mediating variable driving behavioral change. Targeted interventions should be implemented for groups with different characteristics.

Objective:To summarize the safety and efficacy of thoracoscopic minimally invasive " one-stop" ablation for the treatment of atrial fibrillation(AF).Methods:A retrospective study was conducted on all patients with isolated atrial fibrillation who underwent thoracoscopic radiofrequency ablation combined with left atrial appendage clipping(LAAC) at West China Hospital of Sichuan University from September 2019 to October 2023. Preoperative baseline data, perioperative complications, and 3-month, 6-month, and 12-month postoperative follow-up data were collected and analyzed.Results:A total of 87 patients were included, with a mean age of(60.5±9.0) years old. Among them, 47 were males and 40 were females. Of these patients, 12 had paroxysmal AF, and 75 had persistent AF. Fourteen patients had a prior history of catheter-based radiofrequency ablation, and 11 had a history of transient ischemic attack(TIA) or stroke. All procedures were successfully completed without conversion to open thoracotomy, perioperative mortality, or perioperative stroke events. During the follow-up period, one patient died, no strokes or left atrial appendage reconnection events were observed. The sinus rhythm maintenance rates at 3、6 and 12 months postoperatively were 89.6%(78/87)、82.8%(72/87) and 75.9%(66/87), respectively. Multivariate logistic regression analysis identified a preoperative left atrial anteroposterior diameter>40 mm as an independent risk factor for postoperative AF recurrence. Conclusion:Thoracoscopic minimally invasive ablation combined with left atrial appendage clipping as a " one-stop" procedure is a safe and effective method for the treatment of isolated atrial fibrillation, achieving satisfactory surgical ablation success rates while effectively preventing stroke.

Objective:To summarize the safety and efficacy of thoracoscopic minimally invasive " one-stop" ablation for the treatment of atrial fibrillation(AF).Methods:A retrospective study was conducted on all patients with isolated atrial fibrillation who underwent thoracoscopic radiofrequency ablation combined with left atrial appendage clipping(LAAC) at West China Hospital of Sichuan University from September 2019 to October 2023. Preoperative baseline data, perioperative complications, and 3-month, 6-month, and 12-month postoperative follow-up data were collected and analyzed.Results:A total of 87 patients were included, with a mean age of(60.5±9.0) years old. Among them, 47 were males and 40 were females. Of these patients, 12 had paroxysmal AF, and 75 had persistent AF. Fourteen patients had a prior history of catheter-based radiofrequency ablation, and 11 had a history of transient ischemic attack(TIA) or stroke. All procedures were successfully completed without conversion to open thoracotomy, perioperative mortality, or perioperative stroke events. During the follow-up period, one patient died, no strokes or left atrial appendage reconnection events were observed. The sinus rhythm maintenance rates at 3、6 and 12 months postoperatively were 89.6%(78/87)、82.8%(72/87) and 75.9%(66/87), respectively. Multivariate logistic regression analysis identified a preoperative left atrial anteroposterior diameter>40 mm as an independent risk factor for postoperative AF recurrence. Conclusion:Thoracoscopic minimally invasive ablation combined with left atrial appendage clipping as a " one-stop" procedure is a safe and effective method for the treatment of isolated atrial fibrillation, achieving satisfactory surgical ablation success rates while effectively preventing stroke.

Objective To explore the value of deep learning image reconstruction(DLIR)algorithm to improve the quality of low keV monochromatic portal vein images of energy spectrum CT.Methods Fifty patients who underwent enhanced upper abdominal energy spectrum CT scan were selected.Mixed-model adaptive statistical iterative reconstruction-Veo(50%ASIR-V)algorithm and high-deep learning image reconstruction(DLIR-H)algorithm were used to obtain monochromatic images at 40-70 keV(with intervals of 10 keV).The CT and standard deviation(SD)values of the portal vein trunk,left and right branches,and erector spinae muscle were measured in the transverse position,and the signal-to-noise ratio(SNR)and portal vein contrast-to-noise ratio(CNR)were calculated for objective evaluation.The portal vein image quality between the two algorithms and different energy was subjectively scored by two physicians.Results In terms of objective evaluation:compared with 50%ASIR-V,the CNR and SNR of portal vein in monochromatic DLIR-H images at the same keV between 40-70 keV energy levels were increased while the SD value was decreased(P＜0.05),and the CT value was unchanged;there was no statistical difference in the magnitude of change in CNR between the two algorithms at different energy levels(P＞0.05);there was a statistically significant difference in the magnitude of change in SNR and SD value(P＜0.05)and the magnitude of change was the largest at 40 keV;comparison between different energy levels of DLIR-H,the CNR and SD value of 40 keV DLIR-H were the highest(P＜0.05),and there was no significant difference in the SNR(P＞0.05).In terms of subjective evaluation:there was no significant difference between the subjective scores of the two algorithms at the same keV from 40-70 keV(P＞0.05),and the two reconstruction algorithms at 40 keV and 50 keV had the highest subjective scores between different keV.Conclusion The DLIR algorithm can reduce the noise of low keV monochromatic images,improve the image quality of portal vein.

Objective To explore the value of deep learning image reconstruction(DLIR)algorithm to improve the quality of low keV monochromatic portal vein images of energy spectrum CT.Methods Fifty patients who underwent enhanced upper abdominal energy spectrum CT scan were selected.Mixed-model adaptive statistical iterative reconstruction-Veo(50%ASIR-V)algorithm and high-deep learning image reconstruction(DLIR-H)algorithm were used to obtain monochromatic images at 40-70 keV(with intervals of 10 keV).The CT and standard deviation(SD)values of the portal vein trunk,left and right branches,and erector spinae muscle were measured in the transverse position,and the signal-to-noise ratio(SNR)and portal vein contrast-to-noise ratio(CNR)were calculated for objective evaluation.The portal vein image quality between the two algorithms and different energy was subjectively scored by two physicians.Results In terms of objective evaluation:compared with 50%ASIR-V,the CNR and SNR of portal vein in monochromatic DLIR-H images at the same keV between 40-70 keV energy levels were increased while the SD value was decreased(P＜0.05),and the CT value was unchanged;there was no statistical difference in the magnitude of change in CNR between the two algorithms at different energy levels(P＞0.05);there was a statistically significant difference in the magnitude of change in SNR and SD value(P＜0.05)and the magnitude of change was the largest at 40 keV;comparison between different energy levels of DLIR-H,the CNR and SD value of 40 keV DLIR-H were the highest(P＜0.05),and there was no significant difference in the SNR(P＞0.05).In terms of subjective evaluation:there was no significant difference between the subjective scores of the two algorithms at the same keV from 40-70 keV(P＞0.05),and the two reconstruction algorithms at 40 keV and 50 keV had the highest subjective scores between different keV.Conclusion The DLIR algorithm can reduce the noise of low keV monochromatic images,improve the image quality of portal vein.

This article provides an interpretive review of the "2023 ACC/AHA/ACCP/HRS guideline for the diagnosis and management of atrial fibrillation", which was updated and published by the American College of Cardiology (ACC), the American Heart Association (AHA), the American College of Chest Physicians (ACCP), and the Heart Rhythm Society (HRS) based on the latest clinical evidence. It delves into the classification and management strategies for atrial fibrillation (AF), grounded in the most current evidence-based medical research. The guideline offers significant updates in various aspects such as the definition and staging of AF, clinical evaluation and treatment, modification of risk factors, prevention of thromboembolism, and management of specific populations. Notably, the introduction of a new staging model for AF and corresponding management strategies stands out, underscoring the importance of prevention and early intervention. This article focuses on the three pillars of integrated AF management—stroke risk assessment, modification of risk factors, and management of specific patient groups, in addition to rate and rhythm control, analyzes their substantial significance in clinical practice and guides clinicians in providing more precise treatment.

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 effect of 3D printed heart models in the training of young cardiac surgeons, and evaluate their application value in surgical simulation and skill improvement. Methods Eight young cardiac surgeons were selected form West China Hospital as the trainees. Before training, the Hands-On Surgical Training-Congenital Heart Surgery (HOST-CHS) operation scores of the 8 cardiac surgeons were obtained after operating on 2 pig heart models of ventricular septal defect (VSD). Subsequently, simulation training was conducted on a 3D printed peri-membrane VSD heart model for 6 weeks, once a week. After the training, all trainees completed 2 pig heart VSD repair surgeries. The improvement of doctors’ skills was evaluated through survey questionnaires, HOST-CHS scores, and operation time after training. Results Before the training, the average HOST-CHS score of the 8 trainees was 52.2±6.3 points, and the average time for VSD repair was 54.7±7.1 min. During the 6-week simulation training using 3D printed models, the total score of HOST-CHS for the 8 trainees gradually increased (P<0.001), and the time required to complete VSD repair was shortened (P<0.001). The trainees had the most significant improvement in scores of surgical cognition and protective awareness. The survey results showed that trainees were generally very satisfied with the effectiveness of 3D model simulation training. Conclusion The 3D printed VSD model demonstrates significant application advantages in the training of young cardiac surgeons. By providing highly realistic anatomical structures, 3D models can effectively enhance surgeons’ surgical skills. It is suggested to further promote the application of 3D printing technology in medical education, providing strong support for cultivating high-quality cardiac surgeons.