ObjectiveThis study aims to develop and validate a novel multimodal predictive model， termed criss-cross network（CCNet）-directed graph neural network（DGNN）（CGN）， for accurate assessment of pulmonary nodule progression in high-risk individuals for lung cancer， by integrating longitudinal chest computed tomography（CT） imaging with both traditional Chinese and western clinical evaluation data. MethodsA cohort of 4 432 patients with pulmonary nodules was retrospectively analyzed. A twin CCNet was employed to extract spatiotemporal representations from paired sequential CT scans. Structured clinical assessment and imaging-derived features were encoded via a multilayer perceptron， and a similarity-based alignment strategy was adopted to harmonize multimodal imaging features across temporal dimensions. Subsequently， a DGNN was constructed to integrate heterogeneous features， where nodes represented modality-specific embeddings and edges denoted inter-modal information flow. Finally， model optimization was performed using a joint loss function combining cross-entropy and cosine similarity loss， facilitating robust classification of nodule progression status. ResultsThe proposed CGN model demonstrated superior predictive performance on the held-out test set， achieving an area under the receiver operating characteristic curve（AUC） of 0.830， accuracy of 0.843， sensitivity of 0.657， specificity of 0.712， Cohen's Kappa of 0.417， and F₁ score of 0.544. Compared with unimodal baselines， the CGN model yielded a 36%-48% relative improvement in AUC. Ablation studies revealed a 2%-22% increase in AUC when compared to simplified architectures lacking key components， substantiating the efficacy of the proposed multimodal fusion strategy and modular design. Incorporation of traditional Chinese medicine （TCM）-specific symptomatology led to an additional 5% improvement in AUC， underscoring the complementary value of integrating TCM and western clinical data. Through gradient-weighted activation mapping visualization analysis， it was found that the model's attention predominantly focused on nodule regions and effectively captured dynamic associations between clinical data and imaging-derived features. ConclusionThe CGN model， by synergistically combining cross-attention encoding with directed graph-based feature integration， enables effective alignment and fusion of heterogeneous multimodal data. The incorporation of both TCM and western clinical information facilitates complementary feature enrichment， thereby enhancing predictive accuracy for pulmonary nodule progression. This approach holds significant potential for supporting intelligent risk stratification and personalized surveillance strategies in lung cancer prevention.

Objective This study aimed to analyze the use of various virtual surgical planning and 3D printing templates in mandibular angle ostectomy.Methods Twelve patients with mandibular angle prominence were selected from the Affiliated Stomatological Hospital of Guizhou Medical University between January 2022 and January 2023.Preoperative craniofacial CT scans were used to create three-dimensional models.Two types of virtual surgical planning and templates were designed:ascend-ing branch-fixed templates on the ramus(Group Ⅰ)and inferior border-fixed templates on the excised mandibular angle(GroupⅡ).Patients were divided into two groups based on the template used during surgery.The changes in the mandibular angle be-fore and two weeks after surgery were compared between the groups,and deviations between the surgical plans and postopera-tive results were measured.Results All patients healed successfully with satisfactory cosmetic outcomes.Lateral mandibular angles were observed in all patients of Group Ⅰ.In Group Ⅱ,one patient presented with a lateral angle,while the others showed medial angles.An increase in the mandibular angle(P＜0.01)was noted with no significant difference between the bilateral an-gles(P＞0.05).The deviation from the surgical planning was also not significantly different between the groups(P＞0.05).Conclusion Virtual surgical planning and 3D printed templates in mandibular angle ostectomy result in high accuracy and favor-able cosmetic outcomes.Ramus-fixed template is suitable for lateral mandibular angle type,while lower edge-fixed template is better for medial mandibular angle type.

Background::Pulmonary arterial hypertension (PAH) is characterized by excessive proliferation of small pulmonary arterial vascular smooth muscle cells (PASMCs), endothelial dysfunction, and extracellular matrix remodeling. G protein-coupled receptor kinase 2 (GRK2) plays an important role in the maintenance of vascular tone and blood flow. However, the role of GRK2 in the pathogenesis of PAH is unknown.Methods::GRK2 levels were detected in lung tissues from healthy people and PAH patients. C57BL/6 mice, vascular smooth muscle cell-specific Grk2-knockout mice ( Grk2?SM22), and littermate controls ( Grk2flox/flox) were grouped into control and hypoxia mice ( n = 8). Pulmonary hypertension (PH) was induced by exposure to chronic hypoxia (10%) combined with injection of the SU5416 (cHx/SU). The expression levels of GRK2 and Yes-associated protein (YAP) in pulmonary arteries and PASMCs were detected by Western blotting and immunofluorescence staining. The mRNA expression levels of Grk2 and Yes-associated protein ( YAP) in PASMCs were quantified with real-time polymerase chain reaction (RT-PCR). Wound-healing assay, 3-(4,5)-dimethylthiahiazo (-z-y1)-3,5-di-phenytetrazoliumromide (MTT) assay, and 5-Ethynyl-2′-deoxyuridine (EdU) staining were performed to evaluate the proliferation and migration of PASMCs. Meanwhile, the interaction among proteins was detected by immunoprecipitation assays. Results::The expression levels of GRK2 were upregulated in the pulmonary arteries of patients with PAH and the lungs of PH mice. Moreover, cHx/SU-induced PH was attenuated in Grk2?SM22 mice compared with littermate controls. The amelioration of PH in Grk2?SM22 mice was accompanied by reduced pulmonary vascular remodeling. In vitro study further confirmed that GRK2 knock-down significantly altered hypoxia-induced PASMCs proliferation and migration, whereas this effect was severely intensified by overexpression of GRK2. We also identified that GRK2 promoted YAP expression and nuclear translocation in PASMCs, resulting in excessive PASMCs proliferation and migration. Furthermore, GRK2 is stabilized by inhibiting phosphorylating GRK2 on Tyr86 and subsequently activating ubiquitylation under hypoxic conditions. Conclusion::Our findings suggest that GRK2 plays a critical role in the pathogenesis of PAH, via regulating YAP expression and nuclear translocation. Therefore, GRK2 serves as a novel therapeutic target for PAH treatment.

Objective:In this study, the application value of a specific information platform in heart failure was explored.Methods:We constructed five modules of information platform based on clinical needs, including user interface, patient management interface, follow-up platform, data processing interface and system management. By making good use of the platform, a database of heart failure was established and quality-controlled to realize the management of chronic heart failure, and prepare database for possible clinical research.Results:More than 3 000 patients with heart failure had been registered in the heart failure special disease platform. Long-term out-of-hospital management of cerfain patients with heart failure was conducted through intelligent information means. High-quality heart failure data were obtained and translated into clinical results.Conclusions:Long-term out-of-hospital management of patients with chronic heart failure can be realized through the special disease information platform, and high-quality evidence-based medical data can be obtained. Besides, the platform provides theoretical basis and data support for evaluation system of prognosis of heart failure, provides theoretical basis and data support for improving medication and surgical treatment plans and comprehensive management system of patients with heart failure.

Objective:This article takes the practical experience of the construction of the cardiovascular disease clinical medicine research center in Nanjing First Hospital as an example to provide reference for institutions preparing to build a clinical research center.Methods:The center conducts top-level design based on clinical needs, and this study systematically elaborates the construction of the center from management mechanisms, research platforms, collaborative networks, team building and international cooperation.Results:The center has made remarkable progress in clinical research, scientific and technological innovation, transformation and promotion, standard formulation, and technology leading. On the basis of an international perspective, the level of regional diagnosis and treatment has been improved by optimizing the structure of subject talents, and focusing on the clinical needs of cardiovascular subspecialty.Conclusions:Taking the construction of the clinical medicine center as an opportunity, integrating superior resources, improving the level of disease diagnosis, treatment and service and enhancing international academic influence are effective measures to accelerate the development of health services and deepen medical reforms.

Animal models of pulmonary artery hypertension (PAH),aiming to simulate human characteristics of the disease,have contributed extensively to understanding the pathophysiology of PAH and the investigation of experimental treatments.The classical models include monocrotaline models,chronic hypoxia model and so on,more new models were investigated in recent years.These animal models were not able to perfectly mimic human pathological characteristics of PAH because of the defect in different aspects.In this review,both typical and novel methods of PAH modeling were summarized and evaluated to provide a suitable guidance for the settlement of animal models which can meet human characteristics comprehensively.