Objective To explore an artificial intelligence (AI)-based method for automated hand hygiene monitoring and to compare the effectiveness of three algorithms (UniFormerV2, TDN, C3D) in recognizing hand hygiene steps in surgical settings, thereby aiding hospital infection control. Methods From April to October 2024, we non-invasively collected 641 video recordings of healthcare staff performing hand hygiene at four-bay scrub sinks in two tertiary hospitals using overhead HD cameras. The dataset was annotated by five trained experts for model training and validation. Results Following training on 385 samples, internal validation (n=119) showed the C3D model achieved 81% accuracy, 87% recall, and an 83% F1-score. The TDN model achieved 93%, 91%, and 92% for the same metrics. The UniFormerV2 model outperformed both, with an accuracy, recall, and F1-score of 93%—an improvement of over 10 percentage points compared to traditional CNNs (TDN, C3D). It also achieved an 84% accuracy in external validation, demonstrating strong generalization. Conclusion The UniFormerV2 model is more accurate than CNN-based models for hand hygiene step recognition and shows robust performance in external validation. It presents a viable tool for healthcare facilities to enhance hand hygiene management, ultimately improving medical quality and patient safety.

It is very limited that the benefit of perioperative chemotherapy in early non-small cell lung cancer (NSCLC), and the 5-year survival rate is only 5% higher than surgery. Antibodies that block programmed cell death protein 1/programmed death-ligand 1 significantly improve the survival of advanced NSCLC. The value of immunotherapy in early NSCLC is also being explored. This paper firstly summarized and analyzed the progress of immunotherapy in the perioperative period of NSCLC. Secondly, the safety and feasibility of surgical resection after neoadjuvant immunotherapy were discussed. Finally, the clinical value of different therapeutic efficacy prediction indicators was summarized, in order to clarify the current status of immunotherapy in the perioperative period, so as to improve the clinical benefits of early NSCLC patients.

The saphenous vein graft (SVG) remains the most commonly used conduit in coronary artery bypass grafting (CABG), yet its limited long-term patency adversely affects patient outcomes. SVG failure is a multistage pathological process, characterized by early thrombosis, intermediate intimal hyperplasia, and late atherosclerotic degeneration. These changes are driven by endothelial dysfunction induced by ischemia-reperfusion and mechanical injury, smooth muscle cell phenotypic modulation, inflammatory activation, and conventional cardiovascular risk factors. Preventive strategies for SVG failure have increasingly focused on both surgical and pharmacological optimization. Surgical approaches include appropriate target vessel and anastomotic site selection, refinement of SVG harvesting techniques (notably the no-touch technique and endoscopic vein harvesting), optimization of graft configurations, and routine intraoperative graft flow assessment. Postoperative secondary prevention is essential, as antithrombotic and lipid-lowering therapies have been shown to reduce SVG occlusion. In addition, emerging therapies, including gene-based interventions, antiproliferative agents, novel graft preservation solutions, and external vein graft supports, show promise in improving SVG durability. Integrated multimodal strategies may further reduce SVG failure and improve long-term outcomes after CABG. This article provides a review of researches related to SVG failure, including the mechanisms of failure, intraoperative preventive measures, pharmacological prevention, and recent advances in treatment, aiming to offer insights for clinical diagnosis, treatment and future studies.

Objective By combining biological detection and imaging evaluation, a clinical prediction model is constructed based on a large cohort to improve the accuracy of distinguishing between benign and malignant pulmonary nodules. Methods A retrospective analysis was conducted on the clinical data of the 32 627 patients with pulmonary nodules who underwent chest CT and testing for 7 types of lung cancer-related serum autoantibodies (7-AABs) at our hospital from January 2020 to April 2024. The univariate and multivariate logistic regression models were performed to screen independent risk factors for benign and malignant pulmonary nodules, based on which a nomogram model was established. The performance of the model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Results A total of 1 017 patients with pulmonary nodules were included in the study. The training set consisted of 712 patients, including 291 males and 421 females, with a mean age of (58±12) years. The validation set included 305 patients, comprising 129 males and 176 females, with a mean age of (58±13) years. Univariate ROC curve analysis indicated that the combination of CT and 7-AABs testing achieved the highest area under the curve (AUC) value (0.794), surpassing the diagnostic efficacy of CT alone (AUC=0.667) or 7-AABs alone (AUC=0.514). Multivariate logistic regression analysis showed that radiological nodule diameter, nodule nature, and CT combined with 7-AABs detection were independent predictors, which were used to construct a nomogram prediction model. The AUC values for this model were 0.826 and 0.862 in the training and validation sets, respectively, demonstrating excellent performance in DCA. Conclusion The combination of 7-AABs with CT significantly enhances the accuracy of distinguishing between benign and malignant pulmonary nodules. The developed predictive model provides strong support for clinical decision-making and contributes to achieving precise diagnosis and treatment of pulmonary nodules.

Objective To establish and internally validate a predictive model for poorly differentiated adenocarcinoma based on CT imaging and tumor marker results. Methods Patients with solid and partially solid lung nodules who underwent lung nodule surgery at the Department of Thoracic Surgery, the Affiliated Brain Hospital of Nanjing Medical University in 2023 were selected and randomly divided into a training set and a validation set at a ratio of 7:3. Patients' CT features, including average density value, maximum diameter, pleural indentation sign, and bronchial inflation sign, as well as patient tumor marker results, were collected. Based on postoperative pathological results, patients were divided into a poorly differentiated adenocarcinoma group and a non-poorly differentiated adenocarcinoma group. Univariate analysis and logistic regression analysis were performed on the training set to establish the predictive model. The receiver operating characteristic (ROC) curve was used to evaluate the model's discriminability, the calibration curve to assess the model's consistency, and the decision curve to evaluate the clinical value of the model, which was then validated in the validation set. Results A total of 299 patients were included, with 103 males and 196 females, with a median age of 57.00 (51.00, 67.25) years. There were 211 patients in the training set and 88 patients in the validation set. Multivariate analysis showed that carcinoembryonic antigen (CEA) value [OR=1.476, 95%CI (1.184, 1.983), P=0.002], cytokeratin 19 fragment antigen (CYFRA21-1) value [OR=1.388, 95%CI (1.084, 1.993), P=0.035], maximum tumor diameter [OR=6.233, 95%CI (1.069, 15.415), P=0.017], and average density [OR=1.083, 95%CI (1.020, 1.194), P=0.040] were independent risk factors for solid and partially solid lung nodules as poorly differentiated adenocarcinoma. Based on this, a predictive model was constructed with an area under the ROC curve of 0.896 [95%CI (0.810, 0.982)], a maximum Youden index corresponding cut-off value of 0.103, sensitivity of 0.750, and specificity of 0.936. Using the Bootstrap method for 1000 samplings, the calibration curve predicted probability was consistent with actual risk. Decision curve analysis indicated positive benefits across all prediction probabilities, demonstrating good clinical value. Conclusion For patients with solid and partially solid lung nodules, preoperative use of CT to measure tumor average density value and maximum diameter, combined with tumor markers CEA and CYFRA21-1 values, can effectively predict whether it is poorly differentiated adenocarcinoma, allowing for early intervention.

Objective To investigate the safety, economic benefits and psychological effects of day breast conserving surgery for breast cancer. Methods The demographic data and clinical data of breast cancer patients undergoing day (day surgery group) and ward (ward surgery group) breast conserving surgeries in West China Hospital of Sichuan University from March 2020 to June 2021 were retrospectively collected; the demographic data, clinical data, medical and related transportation costs, and preoperative and postoperative BREAST-Q scores of breast cancer patients undergoing day (day surgery group) and ward (ward surgery group) breast conserving surgery in West China Hospital of Sichuan University from June 2021 to June 2022 were prospectively collected. The safety, economic benefit, and psychological satisfaction of day surgery was analyzed. Results A total of 42 women with breast cancer were included in the retrospective study and 39 women with breast cancer were included in the prospective study. In both prospective and retrospective studies, the mean age of patients in both groups were <50 years. There were only statistical differences between the two groups in the aspects of hypertension (P=0.022), neoadjuvant chemotherapy (P=0.037) and postoperative pathological estrogen receptor (P=0.033) in the prospective study. In postoperative complications, there were no statistical differences in the surgical-related complications or anesthesia-related complications between the two groups in either the prospective study or the retrospective study (P>0.05). In terms of the overall cost, we found that the day surgery group was more economical than the ward surgery group in the prospective study (P=0.002). There were no statistical differences in postoperative psychosocical well-being, sexual well-being, satisfaction with breasts or chest condition between the two groups (P>0.05). Conclusion It is safe and reliable to carry out breast conserving surgery in day surgery center under strict management standards, which can save medical costs and will not cause great psychological burden to patients.

Objective To evaluate the safety and efficacy of basic anesthesia combined with local anesthesia in the preoperative localization of multiple pulmonary nodules. Methods The clinical data of patients who underwent preoperative localization for multiple pulmonary nodules resection under single-port thoracoscopy in Nanjing Brain Hospital from July 2023 to September 2023 were extracted. They were divided into a group A and a group B according to the localization method. The patients in the group A were localized under local anesthesia, and the patients in the group B were localized with basic anesthesia combined with local anesthesia. The basic clinical characteristics, localization success rate, incidence of localization complications, localization time, and pain score of the two groups were compared and analyzed. Results Finally, we included 200 patients with 100 patients in each group. There were 49 males and 51 females at age of 25-77 (50.94±14.29) years in the group A. There are 45 males and 55 females at age of 24-78 (48.25±14.04) years in the group B. The incidence of localization complications (4% vs. 13%, P=0.04), localization time [(19.90±8.66) min vs. (15.23±5.98) min, P<0.01], and pain score[ (2.01±2.09) vs. (3.29±2.54), P<0.01] in the group B were significantly lower than those in the group A, and the differences were statistically significant. The localization success rate of the group B was significantly higher than that of the group A (98% vs. 92%, P=0.04), and the difference was statistically significant.Conclusion Mobile CT combined with basic anesthesia for preoperative localization of multiple pulmonary nodules is highly safe, has a high success rate, and provides high patient comfort, making it a valuable approach for clinical promotion.

Objective To investigate the relationship between primary pulmonary mucinous adenocarcinoma (PPMA) mass type and pneumonia type and their difference in malignant degree, and to analyze the role of clinical manifestations and CT features in the diagnosis of this disease. Methods The clinical data of PPMA patients admitted in the First Affiliated Hospital of Xiamen University from May 2011 to March 2022 were retrospectively analyzed. According to CT features, they were divided into a mass type group and a pneumonia type group. The clinical manifestations, CT features and the degree of malignancy between the two groups were analyzed and compared. Results A total of 57 PPMA patients were enrolled. There were 17 males and 40 females, with an average age of (53.82±10.65) years, and 28 (49%) patients had reversed hato-like sign. There were 42 patients in the mass type group and 15 patients in the pneumonia type group. PPMA often occurs in both lower lungs, with clinical manifestations mainly of coughing and expectorating white mucoid sputum. There were statistical differences between the two groups in the maximum diameter of tumor (P<0.001), boundary condition (P<0.001) and pleural indentation sign (P=0.019). There was no statistical difference between the two groups in Ki-67 index (P>0.05). Conclusion There is no statistical difference in the degree of malignancy between the two types of PPMA. Considering their clinical manifestations and differences in imaging features, it is supported that the pneumonia type is just a progression of the mass type. CT can present various manifestations, among which the reversed hato-like sign is expected to become an important imaging feature. Combined with a high proportion of solid components, pleural indentation sign, and vacuole sign, reversed hato-like sign can play a significant role in the diagnosis of PPMA.

In recent years, with the improvement of people's awareness of physical examination and the more accurate detection equipment, the detection rate of pulmonary nodules is getting higher and higher. Surgical resection is the first choice for the treatment of malignant pulmonary nodules, but multiple pulmonary nodules, nodules in complex areas and those with surgical contraindications are not suitable for surgery. As an effective, less invasive and low-cost treatment, ablation has developed rapidly in the treatment of multiple pulmonary nodules. This article introduces the progress of several common ablation techniques (radiofrequency ablation, microwave ablation, cryoablation) in the treatment of multiple pulmonary nodules, the indications and contraindications of ablation techniques, the efficacy evaluation and complications after ablation therapy, and the prospects of ablation techniques in the treatment of multiple pulmonary nodules.

Objective To construct large medical model named by "Huaxi HongYi"and explore its application effectiveness in assisting medical record generation. Methods By the way of a full-chain medical large model construction paradigm of "data annotation - model training - scenario incubation", through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, "Huaxi HongYi" with 72 billion parameters was constructed. Combined with technologies such as speech recognition, knowledge graphs, and reinforcement learning, an application system for assisting in the generation of medical records was developed. Results Taking the assisted generation of discharge records as an example, in the pilot department, after using the application system, the average completion times of writing a medical records shortened (21 min vs. 5 min) with efficiency increased by 3.2 time, the accuracy rate of the model output reached 92.4%. Conclusion It is feasible for medical institutions to build independently controllable medical large models and incubate various applications based on these models, providing a reference pathway for artificial intelligence development in similar institutions.