Patients with Takayasu arteritis combined with aortic valve disease often have a poor prognosis following surgical valve replacement, frequently encountering complications such as perivalvular leakage, valve detachment, and anastomotic aneurysm. This article presents a high-risk case wherein severe aortic valve insufficiency associated with Takayasu arteritis was successfully managed through transcatheter aortic valve implantation via the transapical approach. The patient had satisfactory valve function with no complications observed during the six-month postoperative follow-up. This case provides a minimally invasive and feasible alternative for the clinical management of such high-risk patients.

Objective To explore whether there is a causal relationship between intestinal flora and esophageal cancer. Methods Summary statistics of intestinal flora and esophageal cancer were obtained from the Genome-wide Association Studies (GWAS) database. Five methods, including inverse variance weighted (IVW), weighted median estimation, Mendelian randomization (MR)-Egger regression, single mode, and weighted mode, were used for analysis, with IVW as the main analysis method. Sensitivity analysis was used to evaluate the reliability of MR results. Results In the IVW method, Oxalobacteraceae [OR=1.001, 95%CI (1.000, 1.002), P=0.023], Faecalibacterium [OR=1.001, 95%CI (1.000, 1.002), P=0.028], Senegalimassilia [OR=1.002, 95%CI (1.000, 1.003), P=0.006] and Veillonella [OR=1.001, 95%CI (1.000, 1.002), P=0.018] were positively correlated with esophageal cancer, while Burkholderiales [OR=0.999, 95%CI (0.998, 1.000), P=0.002], Eubacterium oxidoreducens [OR=0.998, 95%CI (0.997, 0.999), P=0.038], Romboutsia [OR=0.999, 95%CI (0.998, 1.000), P=0.048] and Turicibacter [OR=0.998, 95%CI (0.997, 0.999), P=0.013] were negatively correlated with esophageal cancer. Sensitivity analysis showed no evidence of heterogeneity, horizontal pleiotropy and reverse causality. Conclusion Oxalobacteraceae, Faecalibacterium, Senegalimassilia and Veillonella increase the risk of esophageal cancer, while Burkholderiales, Eubacterium oxidoreducens, Romboutsia and Turicibacter decrease the risk of esophageal cancer. Further studies are needed to explore how these bacteria affect the progression of esophageal cancer.

Objective To explore the application of artificial intelligence (AI) in the standardized training of thoracic surgery residents, specifically in enhancing clinical skills and anatomical understanding through AI-assisted lung nodule identification and lung segment anatomy teaching. Methods Thoracic surgery residents undergoing standardized training at Peking Union Medical College Hospital from September 2023 to September 2024 were selected. They were randomly assigned to a trial group and a control group using a random number table. The trial group used AI-assisted three-dimensional reconstruction technology for lung nodule identification, while the control group used conventional chest CT images. After basic teaching and self-practice, the ability to identify lung nodules on the same patient CT images was evaluated, and feedback was collected through questionnaires. Results A total of 72 residents participated in the study, including 30 (41.7%) males and 42 (58.3%) females, with an average age of (24.0±3.0) years. The trial group showed significantly better overall diagnostic accuracy for lung nodules (91.9% vs. 73.3%) and lung segment identification (100.0% vs. 83.70%) compared to the control group, and the reading time was significantly shorter [ (118.5±10.5) s vs. (332.1±20.2) s, P<0.01]. Questionnaire results indicated that 94.4% of the residents had a positive attitude toward AI technology, and 91.7% believed that it improved diagnostic accuracy. Conclusion AI-assisted teaching significantly improves thoracic surgery residents’ ability to read images and clinical thinking, providing a new direction for the reform of standardized training.

Objective To systematically evaluate the predictive models for re-admission in patients with heart failure (HF) in China. Methods Studies related to the risk prediction model for HF patient re-admission published in The Cochrane Library, PubMed, EMbase, CNKI, and other databases were searched from their inception to April 30, 2024. The prediction model risk of bias assessment tool was used to assess the risk of bias and applicability of the included literature, relevant data were extracted to evaluate the model quality. Results Nineteen studies were included, involving a total of 38 predictive models for HF patient re-admission. Comorbidities such as diabetes, N-terminal pro B-type natriuretic peptide/brain natriuretic peptide, chronic renal insufficiency, left ventricular ejection fraction, New York Heart Association cardiac function classification, and medication adherence were identified as primary predictors. The area under the receiver operating characteristic curve ranged from 0.547 to 0.962. Thirteen studies conducted internal validation, one study conducted external validation, and five studies performed both internal and external validation. Seventeen studies evaluated model calibration, while five studies assessed clinical feasibility. The presentation of the models was primarily in the form of nomograms. All studies had a high overall risk of bias. Conclusion Most predictive models for HF patient re-admission in China demonstrate good discrimination and calibration. However, the overall research quality is suboptimal. There is a need to externally validate and calibrate existing models and develop more stable and clinically applicable predictive models to assess the risk of HF patient re-admission and identify relevant patients for early intervention.

Objective To analyze the relationship between neuroticism and gastroesophageal reflux disease (GERD) using the Mendelian randomization (MR) method. Methods Exposure and outcome data were downloaded from the Integrative Epidemiology Unit (IEU) database in August 2023, including summary statistics from genome-wide association studies (GWAS) for neuroticism (n=374 323) and GERD (n=602 604). MR was conducted using the weighted median method, MR-Egger method, inverse variance weighted method, weighted mode method, and simple mode method. The causal relationship between the two was assessed using odds ratio (OR), and sensitivity analyses were performed to ensure the accuracy of the results. Results Neuroticism was associated with an increased risk of GERD [OR=1.229, 95%CI (1.186, 1.274), P<0.001]. Similarly, GERD was associated with an increased risk of neuroticism [OR=1.786, 95%CI (1.623, 1.965), P<0.001]. Conclusion There is a bidirectional causal relationship between neuroticism and gastroesophageal reflux disease.

Artificial intelligence (AI) has been widely used in all walks of life, including healthcare, and has shown great application value in the auxiliary diagnosis of pulmonary nodules in the medical field. In the face of a large amount of lung imaging data, clinicians use AI tools to identify lesions more quickly and accurately, improving work efficiency, but there are still many problems in this field, such as the high false positive rate of recognition, and the difficulty in identifying special types of nodules. Researchers and clinicians are actively developing and using AI tools to promote their continuous evolution and make them better serve human health. This article reviews the clinical application and research progress of AI-assisted diagnosis of pulmonary nodules.

Objective To observe the effect of comorbidity for patients with non-small cell lung cancer (NSCLC) on exercise tolerance and cardiopulmonary function. Methods NSCLC patients who underwent cardiopulmonary exercise testing (CPET) before surgery were retrospectively included. According to the Charlson comorbidity index (CCI) score, patients were divided into two groups: a CCI≥3 group and a CCI＜3 group. The patients were matched with a ratio of 1 : 1 by propensity score matching according to the age, body mass index, sex, smoking history, exercise habits, pathological stage and type of surgery. After matching, CPET indexes were compared between the two groups to explore the differences in exercise tolerance and cardiopulmonary function. Results A total of 276 patients were included before matching. After matching, 56 patients were enrolled with 28 patients in each group, including 38 (67.9%) males and 18 (32.1%) females with an average age of (70.7±6.8) years. Compared with the CCI＜3 group, work rate at peak (WR peak), WR peak/predicted value (WR peak%), kilogram oxygen uptake at anaerobic threshold (VO2/kg AT), VO2/kg peak, VO2/kg peak%, peak carbon dioxide output, the minute ventilation to carbon dioxide production slope, O2 pulse peak and O2 pulse peak% of CCI≥3 group were statistically different (P＜0.05). Among them, the rate of postoperative pulmonary complication in the CCI≥3 group was higher than that in the CCI＜3 group (60.7% vs. 32.1%, P=0.032). Conclusion In the NSCLC patients, exercise tolerance and cardiopulmonary function decreased in patients with CCI≥3 compared with those with CCI<3. CPET can provide an objective basis for risk assessment in patients with comorbidity scored by CCI for pulmonary resection.

Objective To clarify the risk factors of diaphragmatic dysfunction (DD) after cardiac surgery with extracorporeal circulation. Methods A retrospective analysis was conducted on the data of patients who underwent cardiac surgery with extracorporeal circulation in the Department of Cardiovascular Surgery of Peking University People's Hospital from January 2023 to March 2024. Patients were divided into two groups according to the results of bedside diaphragm ultrasound: a DD group and a control group. The preoperative, intraoperative, and postoperative indicators of the patients were compared and analyzed, and independent risk factors for DD were screened using multivariate logistic regression analysis. Results A total of 281 patients were included, with 32 patients in the DD group, including 23 males and 9 females, with an average age of (64.0±13.5) years. There were 249 patients in the control group, including 189 males and 60 females, with an average age of (58.0±11.2) years. The body mass index of the DD group was lower than that of the control group [(18.4±1.5) kg/m2 vs. (21.9±1.8) kg/m2, P=0.004], and the prevalence of hypertension, chronic obstructive pulmonary disease, heart failure, and renal insufficiency was higher in the DD group (P<0.05). There was no statistical difference in intraoperative indicators (operation method, extracorporeal circulation time, aortic clamping time, and intraoperative nasopharyngeal temperature) between the two groups (P>0.05). In terms of postoperative aspects, the peak postoperative blood glucose in the DD group was significantly higher than that in the control group (P=0.001), and the proportion of patients requiring continuous renal replacement therapy was significantly higher than that in the control group (P=0.001). The postoperative reintubation rate, tracheotomy rate, mechanical ventilation time, and intensive care unit stay time in the DD group were higher or longer than those in the control group (P<0.05). Multivariate logistic regression analysis showed that low body mass index [OR=0.72, 95%CI (0.41, 0.88), P=0.011], preoperative dialysis [OR=2.51, 95%CI (1.89, 4.14), P=0.027], low left ventricular ejection fraction [OR=0.88, 95%CI (0.71, 0.93), P=0.046], and postoperative hyperglycemia [OR=3.27, 95%CI (2.58, 5.32), P=0.009] were independent risk factors for DD. Conclusion The incidence of DD is relatively high after cardiac surgery, and low body mass index, preoperative renal insufficiency requiring dialysis, low left ventricular ejection fraction, and postoperative hyperglycemia are risk factors for DD.

Cardiovascular diseases and psychological disorders represent two major threats to human physical and mental health. Research on electrocardiogram (ECG) signals offers valuable opportunities to address these issues. However, existing methods are constrained by limitations in understanding ECG features and transferring knowledge across tasks. To address these challenges, this study developed a multi-resolution feature encoding network based on residual networks, which effectively extracted local morphological features and global rhythm features of ECG signals, thereby enhancing feature representation. Furthermore, a model compression-based continual learning method was proposed, enabling the structured transfer of knowledge from simpler tasks to more complex ones, resulting in improved performance in downstream tasks. The multi-resolution learning model demonstrated superior or comparable performance to state-of-the-art algorithms across five datasets, including tasks such as ECG QRS complex detection, arrhythmia classification, and emotion classification. The continual learning method achieved significant improvements over conventional training approaches in cross-domain, cross-task, and incremental data scenarios. These results highlight the potential of the proposed method for effective cross-task knowledge transfer in ECG analysis and offer a new perspective for multi-task learning using ECG signals.
Humans ; Electrocardiography/methods* ; Mental Health ; Algorithms ; Signal Processing, Computer-Assisted ; Machine Learning ; Arrhythmias, Cardiac/diagnosis* ; Cardiovascular Diseases ; Neural Networks, Computer ; Mental Disorders

Synthetic CT (sCT) generated from CBCT has proven effective in artifact reduction and CT number correction, facilitating precise radiation dose calculation. However, the quality of different regions in sCT images is severely imbalanced, with soft tissue region exhibiting notably inferior quality compared to others. To address this imbalance, we proposed a Multi-Task Attention Network (MuTA-Net) based on VGG-16, specifically focusing the enhancement of image quality in soft tissue region of sCT. First, we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks: global image generation, soft tissue region generation and bone region segmentation. This approach ensured the quality of overall sCT image while enhancing the network's focus on feature extraction and generation for soft tissues region. The result of bone region segmentation task guided the fusion of sub-tasks results. Then, we designed an attention module to further optimize feature extraction capabilities of the network. Finally, by employing a results fusion module, the results of three sub-tasks were integrated, generating a high-quality sCT image. Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52% reduction in mean absolute error in soft tissue region, compared to the best performance among the three comparative methods, including ResNet, U-Net, and U-Net++. It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.
Cone-Beam Computed Tomography/methods* ; Humans ; Image Processing, Computer-Assisted/methods* ; Artifacts ; Algorithms ; Bone and Bones/diagnostic imaging* ; Neural Networks, Computer