ObjectiveCleft palate (CP) is a common congenital deformity often associated with velopharyngeal insufficiency (VPI), which disrupts the physiological coupling between respiration and speech. Conventional clinical assessments, such as nasometry and spirometry, provide limited static data and fail to visualize the dynamic spatiotemporal distribution of lung ventilation during phonation. This study introduces spatiotemporal electrical impedance tomography (ST-EIT) to evaluate speech-respiratory functional features in CP patients compared to normal controls (NC). The aim is to characterize multi-domain respiratory patterns and to validate an interpretable machine learning framework for providing objective, quantitative evidence for clinical assessment. MethodsSeventy-five participants were enrolled in this study, comprising 37 patients with surgically repaired CP and 38 healthy volunteers matched for age, gender, and body mass index (BMI). All subjects performed standardized sustained phonation tasks while undergoing synchronous monitoring with a 16-electrode EIT system and a pneumotachograph. A comprehensive feature engineering pipeline was developed to extract physiological parameters across 3 complementary domains. (1) Temporal domain: including inspiratory/expiratory phase duration (tPhase), time constants (Tau), and inspiratory-to-expiratory time ratios (TI/TE); (2) airflow domain: comprising mean flow, peak flow, and instantaneous flow at 25%, 50%, and 75% of tidal volume; and (3) spatial domain: quantifying global and regional tidal impedance variation (TIV), global inhomogeneity (GI), and center of ventilation (CoV). Extreme Gradient Boosting (XGBoost) classifiers were trained using 5 distinct data sources (Spirometry, Nasometry, Inspiratory-EIT, Expiratory-EIT, and fused ST-EIT). Model performance was rigorously evaluated via stratified 5-fold cross-validation, and Shapley additive explanations (SHAP) were employed to quantify global and local feature contributions. ResultsThe CP group exhibited a distinct respiratory phenotype compared to controls. In the temporal domain, CP patients showed significantly shorter inspiratory (1.60 s vs.1.85 s, P<0.001) and expiratory phase durations (2.45 s vs. 3.95 s, P<0.001), indicating a rapid, shallow breathing rhythm. In the airflow domain, while inspiratory flows were comparable, the CP group demonstrated significantly elevated mean and peak flows during the expiratory phase (P<0.001), reflecting compensatory respiratory effort. Spatially, CP patients presented significant ventilation redistribution, characterized by higher regional TIV in the right-anterior (ROI1) and left-posterior (ROI4) quadrants, but lower TIV in the left-anterior (ROI2) quadrant. In terms of diagnostic accuracy, the multi-modal ST-EIT model achieved the highest performance (AUC: 0.915±0.012, Accuracy: 0.843±0.019, F1-score: 0.872±0.017), substantially outperforming models based on spirometry (AUC: 0.721) or nasometry (AUC: 0.625) alone. Interpretability analysis revealed that spatial domain features were the most critical, contributing 53.4% to the model’s decision-making, followed by temporal (25.0%) and airflow (21.6%) features. ConclusionST-EIT successfully captures the temporal, airflow, and spatial deviations in CP speech respiration that are undetectable by conventional methods—specifically, rapid phase transitions, hyperdynamic expiratory airflow, and regional ventilation heterogeneity. This study validates ST-EIT as a robust, non-invasive, and radiation-free tool for characterizing speech-respiratory dysfunction, offering high clinical value for bedside screening, rehabilitation planning, and longitudinal monitoring of patients with cleft palate.

ObjectiveCleft palate (CP) is a common congenital deformity often associated with velopharyngeal insufficiency (VPI), which disrupts the physiological coupling between respiration and speech. Conventional clinical assessments, such as nasometry and spirometry, provide limited static data and fail to visualize the dynamic spatiotemporal distribution of lung ventilation during phonation. This study introduces spatiotemporal electrical impedance tomography (ST-EIT) to evaluate speech-respiratory functional features in CP patients compared to normal controls (NC). The aim is to characterize multi-domain respiratory patterns and to validate an interpretable machine learning framework for providing objective, quantitative evidence for clinical assessment. MethodsSeventy-five participants were enrolled in this study, comprising 37 patients with surgically repaired CP and 38 healthy volunteers matched for age, gender, and body mass index (BMI). All subjects performed standardized sustained phonation tasks while undergoing synchronous monitoring with a 16-electrode EIT system and a pneumotachograph. A comprehensive feature engineering pipeline was developed to extract physiological parameters across 3 complementary domains. (1) Temporal domain: including inspiratory/expiratory phase duration (tPhase), time constants (Tau), and inspiratory-to-expiratory time ratios (TI/TE); (2) airflow domain: comprising mean flow, peak flow, and instantaneous flow at 25%, 50%, and 75% of tidal volume; and (3) spatial domain: quantifying global and regional tidal impedance variation (TIV), global inhomogeneity (GI), and center of ventilation (CoV). Extreme Gradient Boosting (XGBoost) classifiers were trained using 5 distinct data sources (Spirometry, Nasometry, Inspiratory-EIT, Expiratory-EIT, and fused ST-EIT). Model performance was rigorously evaluated via stratified 5-fold cross-validation, and Shapley additive explanations (SHAP) were employed to quantify global and local feature contributions. ResultsThe CP group exhibited a distinct respiratory phenotype compared to controls. In the temporal domain, CP patients showed significantly shorter inspiratory (1.60 s vs.1.85 s, P<0.001) and expiratory phase durations (2.45 s vs. 3.95 s, P<0.001), indicating a rapid, shallow breathing rhythm. In the airflow domain, while inspiratory flows were comparable, the CP group demonstrated significantly elevated mean and peak flows during the expiratory phase (P<0.001), reflecting compensatory respiratory effort. Spatially, CP patients presented significant ventilation redistribution, characterized by higher regional TIV in the right-anterior (ROI1) and left-posterior (ROI4) quadrants, but lower TIV in the left-anterior (ROI2) quadrant. In terms of diagnostic accuracy, the multi-modal ST-EIT model achieved the highest performance (AUC: 0.915±0.012, Accuracy: 0.843±0.019, F1-score: 0.872±0.017), substantially outperforming models based on spirometry (AUC: 0.721) or nasometry (AUC: 0.625) alone. Interpretability analysis revealed that spatial domain features were the most critical, contributing 53.4% to the model’s decision-making, followed by temporal (25.0%) and airflow (21.6%) features. ConclusionST-EIT successfully captures the temporal, airflow, and spatial deviations in CP speech respiration that are undetectable by conventional methods—specifically, rapid phase transitions, hyperdynamic expiratory airflow, and regional ventilation heterogeneity. This study validates ST-EIT as a robust, non-invasive, and radiation-free tool for characterizing speech-respiratory dysfunction, offering high clinical value for bedside screening, rehabilitation planning, and longitudinal monitoring of patients with cleft palate.

Objective: To characterize perioperative dynamic changes in immune-cell phenotypes and inflammatory cytokines in patients undergoing CPB (cardiopulmonary bypass) cardiac surgery, and to explore their associations with postoperative outcomes. Methods: In this prospective cohort study, 120 adult patients who underwent elective cardiac surgery under CPB at West China Hospital from May 2022 to March 2023 were enrolled. Perioperative immune-cell phenotypes and concentrations of 40 inflammation-related cytokines were measured. The primary outcomes were the sequential organ failure assessment (SOFA) score at 24 h after surgery and ΔSOFA (the peak SOFA score within 48 h after surgery minus the preoperative SOFA score). Secondary outcomes included major adverse cardiovascular events (MACE), acute kidney injury (AKI), respiratory failure, severe liver injury, and infection. Results: The mean age of enrolled patients was 57±10 years. Of these, 52% (62/120) were male and 90% (108/120) underwent valve surgery. During the rewarming to the end of CPB, neutrophil counts rapidly increased (7.39×10 /L vs preoperative 3.07×10 /L, P<0.001), with significant upregulation of CD11b (7.30×10 /L vs preoperative 3.05×10 /L, P<0.001) and CD54 (7.15×10 /L vs preoperative 2.99×10 /L, P<0.001). Lymphocyte counts increased at the end of CPB (1.75×10 /L vs preoperative 1.12×10 /L, P<0.001) but decreased significantly at 24 h after surgery (0.59×10 /L vs preoperative 1.12×10 /L, P<0.001). Plasma analysis showed that multiple pro-inflammatory cytokines increased during CPB and remained elevated up to 24 h after surgery; five chemokines and the anti-inflammatory cytokine IL-10 peaked at the end of CPB. The SOFA score increased from 1 (1, 2) preoperatively to 7 (5, 10) at 24 h after surgery, with a ΔSOFA of 6 (4, 8). Within 30 days after surgery, 48 patients (40.0%) developed AKI, 17 (14.2%) developed infection, 4 (3.3%) developed severe liver injury, 3 (2.5%) developed respiratory failure, and 3 (2.5%) experienced MACE. During the 2-year follow-up, 8 patients (6.7%) experienced MACE and 5 (4.2%) died. Conclusion: Multi-organ dysfunction is common after cardiac surgery under CPB (median ΔSOFA, 6), accompanied by perioperative activation of multiple immune-cell subsets and upregulation of pro-inflammatory, anti-inflammatory, and chemotactic mediators. This study provides data-driven evidence and research clues for further investigation of the associations between CPB-related immune perturbations and postoperative organ dysfunction and clinical outcomes.

With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

BACKGROUND: Based on the China-VHD database, this study sought to develop and validate a Valvular Heart Disease- specific Age-adjusted Comorbidity Index (VHD-ACI) for predicting mortality risk in patients with VHD. METHODS & RESULTS: The China-VHD study was a nationwide, multi-centre multi-centre cohort study enrolling 13,917 patients with moderate or severe VHD across 46 medical centres in China between April-June 2018. After excluding cases with missing key variables, 11,459 patients were retained for final analysis. The primary endpoint was 2-year all-cause mortality, with 941 deaths (10.0%) observed during follow-up. The VHD-ACI was derived after identifying 13 independent mortality predictors: cardiomyopathy, myocardial infarction, chronic obstructive pulmonary disease, pulmonary artery hypertension, low body weight, anaemia, hypoalbuminaemia, renal insufficiency, moderate/severe hepatic dysfunction, heart failure, cancer, NYHA functional class and age. The index exhibited good discrimination (AUC, 0.79) and calibration (Brier score, 0.062) in the total cohort, outperforming both EuroSCORE II and ACCI (P < 0.001 for comparison). Internal validation through 100 bootstrap iterations yielded a C statistic of 0.694 (95% CI: 0.665-0.723) for 2-year mortality prediction. VHD-ACI scores, as a continuous variable (VHD-ACI score: adjusted HR (95% CI): 1.263 (1.245-1.282), P < 0.001) or categorized using thresholds determined by the Yoden index (VHD-ACI ≥ 9 vs. < 9, adjusted HR (95% CI): 6.216 (5.378-7.184), P < 0.001), were independently associated with mortality. The prognostic performance remained consistent across all VHD subtypes (aortic stenosis, aortic regurgitation, mitral stenosis, mitral regurgitation, tricuspid valve disease, mixed aortic/mitral valve disease and multiple VHD), and clinical subgroups stratified by therapeutic strategy, LVEF status (preserved vs. reduced), disease severity and etiology. CONCLUSION The VHD-ACI is a simple 13-comorbidity algorithm for the prediction of mortality in VHD patients and providing a simple and rapid tool for risk stratification.

Nitrogen narcosis is a neurological syndrome that manifests when humans or animals encounter hyperbaric nitrogen, resulting in a range of motor, emotional, and cognitive abnormalities. The anterior cingulate cortex (ACC) is known for its significant involvement in regulating motivation, cognition, and action. However, its specific contribution to nitrogen narcosis-induced hyperlocomotion and the underlying mechanisms remain poorly understood. Here we report that exposure to hyperbaric nitrogen notably increased the locomotor activity of mice in a pressure-dependent manner. Concurrently, this exposure induced heightened activation among neurons in both the ACC and dorsal medial striatum (DMS). Notably, chemogenetic inhibition of ACC neurons effectively suppressed hyperlocomotion. Conversely, chemogenetic excitation lowered the hyperbaric pressure threshold required to induce hyperlocomotion. Moreover, both chemogenetic inhibition and genetic ablation of activity-dependent neurons within the ACC reduced the hyperlocomotion. Further investigation revealed that ACC neurons project to the DMS, and chemogenetic inhibition of ACC-DMS projections resulted in a reduction in hyperlocomotion. Finally, nitrogen narcosis led to an increase in local field potentials in the theta frequency band and a decrease in the alpha frequency band in both the ACC and DMS. These results collectively suggest that excitatory neurons within the ACC, along with their projections to the DMS, play a pivotal role in regulating the hyperlocomotion induced by exposure to hyperbaric nitrogen.
Animals ; Gyrus Cinguli/drug effects* ; Male ; Mice, Inbred C57BL ; Locomotion/drug effects* ; Neurons/drug effects* ; Mice ; Nitrogen/toxicity* ; Inert Gas Narcosis/physiopathology* ; Corpus Striatum/physiopathology*

Neuropathic pain, a debilitating condition caused by dysfunction of the somatosensory nervous system, remains difficult to treat due to limited understanding of its molecular mechanisms. Bioinformatics analysis identified cerebellin 2 (CBLN2) as highly enriched in human and murine proprioceptive and nociceptive neurons. We found that CBLN2 expression is persistently upregulated in dorsal root ganglia (DRG) following spinal nerve ligation (SNL) in mice. In addition, transcription factor SOX11 binds to 12 cis-regulatory elements within the Cbln2 promoter to enhance its transcription. SNL also induced SOX11 upregulation, with SOX11 and CBLN2 co-localized in nociceptive neurons. The siRNA-mediated knockdown of Sox11 or Cbln2 attenuated SNL-induced mechanical allodynia and thermal hyperalgesia. High-throughput sequencing of DRG following intrathecal injection of CBLN2 revealed widespread gene expression changes, including upregulation of numerous NF-κB downstream targets. Consistently, CBLN2 activated NF-κB signaling, and inhibition with pyrrolidine dithiocarbamate reduced CBLN2-induced pain hypersensitivity, proinflammatory cytokines and chemokines production, and neuronal hyperexcitability. Together, these findings identified the SOX11/CBLN2/NF-κB axis as a critical mediator of neuropathic pain and a promising target for therapeutic intervention.
Animals ; Neuralgia/metabolism* ; Ganglia, Spinal/metabolism* ; Up-Regulation ; Mice ; NF-kappa B/metabolism* ; SOXC Transcription Factors/genetics* ; Male ; Neuroinflammatory Diseases/metabolism* ; Mice, Inbred C57BL ; Nerve Tissue Proteins/genetics* ; Hyperalgesia/metabolism* ; Signal Transduction ; Spinal Nerves

The rapid development of artificial intelligence (AI), especially generative AI (GenAI), has already brought, and will continue to bring, revolutionary changes to our daily production and life, as well as create new opportunities and challenges for diagnostic and therapeutic practices in the medical field. Haihe Hospital of Tianjin University collaborates with the National Supercomputer Center in Tianjin, Tianjin University, and other institutions to carry out research in areas such as smart healthcare, smart services, and smart management. We have conducted research and development of a full-process disease diagnosis and treatment assistance system based on GenAI in the field of smart healthcare. The development of this project is of great significance. The first goal is to upgrade and transform the hospital's information center, organically integrate it with existing information systems, and provide the necessary computing power storage support for intelligent services within the hospital. We have implemented the localized deployment of three models: Tianhe "Tianyuan", WiNGPT, and DeepSeek. The second is to create a digital avatar of the chief physician/chief physician's voice and image by integrating multimodal intelligent interaction technology. With generative intelligence as the core, this solution provides patients with a visual medical interaction solution. The third is to achieve deep adaptation between generative intelligence and the entire process of patient medical treatment. In this project, we have developed assistant tools such as intelligent inquiry, intelligent diagnosis and recognition, intelligent treatment plan generation, and intelligent assisted medical record generation to improve the safety, quality, and efficiency of the diagnosis and treatment process. This study introduces the content of a full-process disease diagnosis and treatment assistance system, aiming to provide references and insights for the digital transformation of the healthcare industry.
Artificial Intelligence ; Humans ; Delivery of Health Care ; Generative Artificial Intelligence

OBJECTIVE: To observe the clinical efficacy of 3D printing spinal external fixator combined with McKenzie therapy for patients with lumbar dics herniation (LDH). METHODS: Sixty patients with LDH between January 2022 and January 2023 were enrolled. Among them, 30 patients were given McKinsey training. According to different treatment methods, all patients were divided into McKenzie group and McKenzie + 3D printing group, 30 patients in each group. The McKenzie group provided McKenzie therapy. The McKenzie + 3D printing group were treated with 3D printing spinal external fixation brace on the basis of McKenzie therapy. Patients in both groups were between 25 and 60 years of age and had their first illness. In the McKenzie group, there were 19 males and 11 females, with an average age of (48.57±5.86) years old, and the disease duration was (7.03 ±2.39) months. The McKenzie + 3D printing group, there were 21 males and 9 females, with an average age of (48.80±5.92) years old, and the disease duration was(7.30±2.56) months. Pain was evaluated using the visual analogue scale (VAS), and lumbar spine function was assessed using the Oswestry disability index (ODI) and the Japanese Orthopaedic Association (JOA) score. VAS, ODI and JOA scores were compared between two groups before treatment and at 1, 3, 6, 9 and 12 months after treatment. RESULTS: All patients were followed up for 12 months. The VAS for the McKenzie combined with 3D printing group before treatment and at 1, 3, 6, 9, and 12 months post-treatment were(6.533±0.860), (5.133±1.008), (3.933±0.868), (2.900±0.759), (2.067±0.640), (1.433±0.504), respectively. In the McKenzie group, the corresponding scores were (6.467±0.860), (5.067±1.048), (4.600±0.968), (3.533±1.008), (2.567±0.728), (1.967±0.809), respectively. The ODI of the McKenzie group before treatment and at 1, 3, 6, 9, and 12 months post-treatment were (41.033±6.810)%, (37.933±6.209)%, (35.467±6.962)%, (27.567±10.081)%, (20.800±7.531)%, (13.533±5.158)%, respectively. For the McKenzie combined with 3D printing group, the corresponding ODI were(38.033±5.605)%, (33.000±6.192)%, (28.767±7.045)%, (22.200±5.517)%, (17.700±4.836)%, (11.900±2.771)%, respectively. The JOA scores of the McKenzie combined with 3D printing group before treatment and at 1, 3, 6, 9, and 12 months post-treatment were(8.900±2.074), (13.133±2.330), (15.700±3.583), (20.400±3.480), (22.267±3.084), (24.833±2.640), respectively. In the McKenzie group, the corresponding scores were(9.200±2.091), (12.267±2.406), (15.333±3.198), (18.467±2.240), (20.133±2.751), (22.467±2.849), respectively. Before the initiation of treatment, no statistically significant differences were observed in the VAS, ODI, and JOA scores between two groups (P>0.05). At 3, 6, 9, and 12 months post-treatment, the VAS in the McKenzie combined with 3D printing group was significantly lower than that in the McKenzie group, and the difference was statistically significant (P<0.05). The comparison of ODI between two groups at 1, 3, 6, 9, and 12 months post-treatment revealed statistically significant differences (P<0.05). At 6, 9, and 12 months post-treatment, the JOA score in the McKenzie combined with 3D printing group was significantly higher than that in the McKenzie-only group, and the difference was statistically significant (P<0.05). CONCLUSION The combination of 3D printed functional spinal external fixation brace with McKenzie therapy can significantly improve and maintain lumbar function in patients with LDH.
Humans ; Male ; Female ; Middle Aged ; Printing, Three-Dimensional ; Intervertebral Disc Displacement/surgery* ; External Fixators ; Lumbar Vertebrae/surgery* ; Adult ; Braces ; Treatment Outcome

OBJECTIVES: To investigate the role of active glucose monitoring in preventing hypoglycemia during the perioperative period of gastrointestinal endoscopy in children with glycogen storage disease type Ⅰb (GSD-Ⅰb). METHODS: A retrospective analysis was performed for the clinical data of children with GSD-Ⅰb who were diagnosed and treated in Guangdong Provincial People's Hospital from June 2021 to August 2024. The effect of active glucose monitoring on hypoglycemic episodes during the perioperative period of gastrointestinal endoscopy was analyzed. RESULTS: A total of 14 children with GSD-Ⅰb were included, among whom there were 7 boys and 7 girls, with a mean age of 10.0 years. Among 34 hospitalizations, there were 15 cases of hypoglycemic episodes (44%), among which 6 symptomatic cases (1 case with blood glucose level of 1.6 mmol/L and 5 cases with blood glucose level of <1.1 mmol/L) occurred without active monitoring, while 9 asymptomatic cases (with blood glucose level of 1.2-3.9 mmol/L) were detected by active monitoring. The predisposing factors for hypoglycemic episodes included preoperative fasting (5 cases, 33%), delayed feeding (7 cases, 47%), vomiting (2 cases, 13%), and parental omission (1 case, 7%). Two children experienced two hypoglycemic episodes during the same period of hospitalization, and no child experienced subjective symptoms prior to hypoglycemic episodes. Treatment methods included nasogastric glucose administration (1 case, 7%), intravenous injection of glucose (14 cases, 93%), and continuous glucose infusion (4 cases, 27%). Blood glucose returned to 3.5-6.9 mmol/L within 10 minutes after intervention and remained normal after dietary resumption. CONCLUSIONS Active glucose monitoring during the perioperative period of gastrointestinal endoscopy can help to achieve early detection of hypoglycemic states in children with GSD-Ⅰb, prevent hypoglycemic episodes, and enhance precise diagnosis and treatment.
Humans ; Female ; Male ; Child ; Retrospective Studies ; Blood Glucose/analysis* ; Hypoglycemia/etiology* ; Glycogen Storage Disease Type I/blood* ; Endoscopy, Gastrointestinal ; Perioperative Period ; Child, Preschool ; Adolescent