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.

Objective To systematically evaluate the risk prediction models for acute kidney injury in patients with acute coronary syndrome (ACS) based on machine learning, providing a reference for clinical selection of appropriate risk assessment tools. Methods Clinical studies using machine learning methods for predicting the risk of acute kidney injury in ACS patients were retrieved from PubMed, Cochrane Library, Embase, Web of Science core database, CNKI, Wanfang Database, CBM, and VIP. The retrieval time was from the establishment of the database to May 24, 2025. The quality of the models were evaluated using the prediction model risk of bias assessment tool. Results Nine articles were included, and a total of 58 prediction models were constructed using 20 machine learning methods. The area under the receiver operating characteristic curve ranged from 0.733 to 0.894. The most commonly used predictors were age and creatinine. The overall bias risk of the included studies was relatively high, but the applicability was good.Conclusion Machine learning models can identify the risk of acute kidney injury in ACS patients. All models have good predictive potential, but they are still in the development stage. It is recommended that future studies adopt prospective design with external validation to improve the stability and predictive accuracy of the models.

ObjectiveTo elucidate the effects of autonomic neuromodulators [calcium chloride (CaCl₂)-acetylcholine (ACh)] on atrial electrical remodeling and histopathological changes in rats, thereby providing evidence for further investigation into the pathological mechanisms by which autonomic imbalance induces atrial fibrillation (AF). MethodsTen 8-week-old male Sprague-Dawley (SD) rats were randomly divided into experimental and control groups, with 5 rats in each group. The experimental group received daily tail vein injections of a CaCl₂-ACh mixed solution for 28 days, while the control group received an equal volume of saline. Surface electrocardiograms were recorded before and after daily administration. On day 28 of administration, under isoflurane inhalation anesthesia, echocardiography was performed, and then the rats were euthanized by exsanguination under isoflurane anesthesia for tissue collection. Body weight and heart weight of rats were measured, and electrophysiological parameters including AF inducibility, conduction velocity, and conduction dispersion in isolated rat hearts were monitored using the MappingLab multichannel electrophysiological mapping system. HE staining was performed to evaluate atrial tissue architecture and inflammatory cell infiltration. The expression levels of matrix metalloproteinase 9 (MMP-9) and interleukin-1 beta (IL-1β) were analyzed by Western blotting. Masson staining was used to quantitatively analyze the proportional distribution of collagen fibers and myocardial fibers, and to calculate the area of collagen deposition, thereby evaluating the degree of myocardial fibrosis. Wheat germ agglutinin (WGA) staining was used to evaluate morphological changes of cardiomyocytes. Dihydroethidium (DHE) staining was used to detect the level of oxidative stress in atrial myocytes. Terminal deoxynucleotidyl transferase-mediated dUTP nick-end labeling (TUNEL) staining was used to detect atrial cell apoptosis. ResultsCompared with the control group, the experimental group showed obvious arrhythmias on electrocardiograms. Echocardiography after 28 days of administration revealed significant structural remodeling in the experimental group, with a marked increase in left atrial anteroposterior diameter (P < 0.05), and also showed cardiac dysfunction, with significant decreases in left ventricular ejection fraction and left ventricular fractional shortening (P < 0.01). Compared with the control group, the experimental group showed a significantly increased heart weight-to-body weight ratio (P < 0.05), a markedly higher AF inducibility (P < 0.001), a significantly slowed atrial conduction velocity (P < 0.05), an uneven isochronal map with irregular directions, and a significantly increased conduction dispersion (P < 0.01). HE staining showed that atrial myocytes in the experimental group were disorganized, with slight inflammatory cell infiltration. Western blotting showed that the expression levels of MMP-9 and IL-1β in the atrial tissue of the experimental group were significantly upregulated (P < 0.05). Masson staining showed a significant increase in collagen deposition and a significant increase in fibrosis area in the atrial tissue of the experimental group (P < 0.001). WGA staining showed that cardiomyocytes in the experimental group were significantly hypertrophied compared with the control group (P < 0.05). DHE staining and TUNEL staining revealed that the level of oxidative stress in atrial myocytes (P < 0.001) and the apoptotic rate (P < 0.01) were both significantly increased. Conclusion Daily tail vein injections of the autonomic neuromodulator CaCl₂-ACh mixed solution for 28 days can successfully induce AF in rats, accompanied by significant atrial structural remodeling, electrical remodeling, and oxidative stress.

Short-chain fatty acids （SCFA） are the main metabolic products generated by the fermentation of dietary fiber by gut microbiota. Studies have shown that SCFA not only play a role in energy metabolism， but also act as important signaling molecules， exhibiting a significant potential in alleviating liver and pancreatic fibrosis. The core mechanism of SCFA mainly involves the regulation of various key signaling pathways by activating G protein-coupled receptors and inhibiting the activity of histone deacetylase， thereby suppressing the activation and proliferation of hepatic stellate cell （HSC） and pancreatic stellate cell （PSC）， which is a key link in fibrosis formation. In addition， SCFA can effectively alleviate tissue inflammation response， improve intestinal barrier function， and regulate gut microbiota balance， thus indirectly preventing the process of fibrosis mediated by the “gut-liver/pancreas axis”. Compared with the research on SCFA in liver fibrosis， studies on their role in pancreatic fibrosis are limited. Given that HSC and PSC are highly homologous， the transcription factors and proteins that have been confirmed in liver fibrosis-related studies are also similarly expressed in PSC， suggesting that they may also influence the activation of PSC. This article systematically summarizes the recent advances in the research on SCFA in alleviating liver and pancreatic fibrosis， in order to provide new perspectives for exploring the mechanism of pancreatic fibrosis and developing related interventional strategies.

ObjectiveTo evaluate the effect of neuromuscular electrical stimulation (NMES) on pain, quadriceps strength and motor function of patients after total knee arthroplasty (TKA). MethodsThe databases of CNKI, Wanfang data, VIP, PubMed, Embase, Cochrane, Web of Science and Scopus were retrieved from inception to April, 2025. Randomized controlled trials (RCT) related to the intervention of NMES after TKA were collected. The quality of the included literature was evaluated using the Cochrane Risk of Bias Assessment Tool and the Physical Therapy Evidence Database (PEDro) scale. Meta-analysis was performed with RevMan 5.4. ResultsA total of twelve RCT were included, involving 772 subjects. The PEDro scale score ranged from four to seven. NMES improved postoperative quadriceps muscle strength (SMD = 0.61, 95%CI 0.34 to 0.88, P < 0.001) and knee flexion range of motion (SMD = 1.35, 95%CI 0.30 to 2.41, P = 0.010), and reduced the Timed Up and Go Test (TUGT) time (SMD = -0.86, 95%CI -1.45 to -0.26, P = 0.005). Compared with the control group, the intervention group achieved better outcomes in the 2-Minute Walk Test (2MWT) (SMD = 19.44, 95%CI 10.44 to 30.43, P < 0.001), 3-Minute Walk Test (SMD = 23.57, 95%CI 14.77 to 32.36, P < 0.001), 6-Minute Walk Test (SMD = 42.29, 95%CI 9.71 to 74.86, P = 0.010), Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) (SMD = -0.52, 95%CI -1.00 to -0.04, P = 0.040), as well as the Physical Component Summary (PCS) (SMD = 2.90, 95%CI 0.73 to 5.06, P = 0.009) and Mental Component Summary (MCS) (SMD = 2.84, 95%CI 1.40 to 4.28, P = 0.040) of the 36-Item Short Form Health Survey (SF-36). Subgroup analysis demonstrated that two to four weeks after surgery, NMES enhanced patients' quadriceps muscle strength (SMD = 0.90, 95%CI 0.58 to 1.21, P < 0.001), shortened TUGT time (SMD = -1.28, 95%CI -2.57 to -0.02, P < 0.05) and increased walking distance in 2MWT (SMD = 20.43, 95%CI 10.44 to 30.43, P < 0.001). For patients followed up for two to three months, NMES yielded improvements in WOMAC scores (SMD = -0.44, 95%CI -0.79 to -0.09, P = 0.010) and SF-36 MCS scores (SMD = 4.17, 95%CI 2.43 to 5.91, P < 0.001). ConclusionNMES can significantly improve the quadriceps strength and walking ability of the TKA patients two to four weeks after surgery, and enhance the quality of life of patients two to three months after surgery.

Objective To explore the impact of wearable devices in assisting disease monitoring on heart-focused anxiety in patients with tachyarrhythmias. Methods A cross-sectional study design was conducted. 305 patients with tachyarrhythmias who attended the department of cardiology of Zhongshan Hospital, Fudan University in Shanghai from July 2025 to December 2025 were enrolled as the research subjects, and clinical data of patients were collected. Univariate analysis and multiple stepwise regression analysis were used to analyze the impact of wearable devices in assisting disease monitoring on patients’ heart-focused anxiety. Results The mean score of heart-focused anxiety in the 305 patients with tachyarrhythmias was 33.16±9.70. Among them, 104(34.10%) patients used wearable devices in assisting disease monitoring. The results of univariate analysis and multiple stepwise regression showed that the use of wearable devices in assisting disease monitoring was an influencing factor for heart-focused anxiety (P＜0.05), and the patients who used wearable devices in assisting disease monitoring had a significantly lower level of heart-focused anxiety (P＜0.05). Conclusions The use of wearable devices in assisting disease monitoring is associated with a lower level of heart-focused anxiety in patients with tachyarrhythmias. Medical staff can guide patients to rationally use wearable devices in assisting disease monitoring on the basis of evaluating their needs and device operation capabilities.

Hyperthyroidism （HT） is frequently complicated by atrial fibrillation （AF） in clinical practice. Based on traditional Chinese medicine （TCM） zang-xiang （藏象） theory and clinical experience， both HT and AF are closely associated with dysfunction of the liver. The pathogenesis is initiated by the liver failing to govern the free flow of qi， and liver constraint and qi stagnation， with the key turning points being liver constraint transforming into fire and the internal stirring of liver wind， ultimately leading to liver blood depletion and insufficient nourishment of the heart spirit. Thus， it is proposed to treat the disease from the liver， with stage-specific therapeutic approaches according to the evolution of the disease. In the early stage， the treatment should focus on soothing the liver and relieving constraint to reduce goiter and calm the heart， while in the progressive stage， the method of clearing liver and draining fire is suggested to subdue yang and stabilize palpitations. In the acute stage， the strategy is calming the liver and nourishing yin to subdue yang and extinguish wind. In the later stage， it is suggested to soften the liver and benefit qi， so as to nourish yin and restore pulse. These methods are sequentially applied to synergistically reduce goiter and stabilize palpitations， providing a therapeutic approach for HT complicated by AF.

ObjectiveTo investigate the role of interleukin （IL）-17A in acute inhalational pneumonia induced by the highly drug-resistant and hypervirulent Staphylococcus aureus strain USA300-R in mice. MethodsAn acute inhalational pneumonia model was established in mice using an aerosolized pulmonary delivery technique. RNA sequencing （RNA-seq） and enzyme-linked immunosorbent assay （ELISA） were employed to examine the expression dynamics of Il17a mRNA and IL-17A protein， respectively， in the lungs of infected mice. Il17a knockout （Il17a^-/-） mice were generated using CRISPR/Cas9 gene editing technology. The survival rate， body weight， bacterial load in lung tissue， and histopathological changes were compared between Il17a^-/- and wild-type （WT） mice following inhalational infection with USA300-R. Results12 hours after USA300-R infection， compared to pre-infection， the expression level of Il17a mRNA in lung tissue and the level of IL-17A protein in bronchoalveolar lavage fluid （BALF） increased by approximately 50-fold （P<0.01） and 6-fold （P<0.001）， respectively. Compared to WT mice， Il17a^-/- mice exhibited approximately 10-fold higher bacterial loads in lung tissue at both 12 and 24 hours post-infection （P<0.001， P<0.05）. However， they showed significantly attenuated lung histopathological injury， reduced alveolar wall thickening， markedly decreased neutrophil infiltration， and an approximately 50% improvement in survival rate （P<0.05）. ConclusionIn acute Staphylococcus aureus USA300-R inhalational pneumonia， IL-17A contributes to bacterial clearance by recruiting neutrophils； however， excessive neutrophil infiltration exacerbates pulmonary inflammation and injury， reduces survival rates， and represents a potential therapeutic target.

ObjectiveTo investigate the value of predictive models established based on machine learning methods in predicting the risk of metabolic associated fatty liver disease （MAFLD）， and to analyze its key risk factors. MethodsA retrospective analysis was performed for the 50 variables of 2 168 healthy individuals who underwent physical examination in Department of Health Assessment， Xiyuan Hospital， China Academy of Chinese Medical Sciences， from January 2021 to December 2024， including body composition， past history， and laboratory tests， and according to whether they were diagnosed with MAFLD or not， they were divided into MAFLD group with 265 individuals and non-MAFLD group with 1 903 individuals. The Mann-Whitney U test was used for comparison of continuous data between two groups， and the chi-square test was used for comparison of categorical data between two groups. Randomly split the research data into a training set and a validation set in a 70% to 30% ratio. Predictive factors were screened from the training set data using univariate analysis， LASSO regression， and multivariate Logistic regression analysis. Predictive models were then constructed using seven machine learning methods： Logistic regression， decision tree， random forest （RF）， eXtreme gradient boosting， light gradient boosting machine， support vector machine， and artificial neural network. Model performance was evaluated by plotting receiver operating characteristic curve for the validation set and calculating the area under the curve （AUC）， sensitivity， specificity， and Youden index for each model. Furthermore， the SHapley Additive exPlanation （SHAP） method was used to analyze the contribution of variables in the optimal model. ResultsThe prevalence rate of MAFLD among the 2 168 subjects was 12.22% （265/2 168）. Smoking， diastolic blood pressure， phase angle， visceral fat area， muscle fat ratio， waist-to-hip ratio， aspartate aminotransferase， non-HDL-C/HDL-C ratio， triglyceride-glucose index， and gallstones were independent risk factors for MAFLD （all P<0.05）. The seven predictive models of support vector machine， eXtreme gradient boosting， decision tree， light gradient boosting machine， artificial neural network， RF， and Logistic regression had an AUC of 0.738， 0.754， 0.757， 0.786， 0.795， 0.796， and 0.815， respectively， in the validation set， among which the RF model had the best discriminatory ability （AUC=0.796， 95% confidence interval： 0.754 — 0.839）， with a sensitivity of 81.01%， a specificity of 63.16%， and a Youden index of 44.17%. The SHAP analysis showed that visceral fat area， waist-to-hip ratio， and diastolic blood pressure were the top three predictive factors in terms of importance. ConclusionThe RF model， constructed based on body composition and clinical indicators， has a good performance in predicting the risk of MAFLD， and its interpretability can help to identify high-risk individuals in the early stage in clinical practice.

Objective:To explore the clinical characteristics, diagnosis and treatment strategies, and prognosis of pulmonary embolism (PE) complicating childhood rheumatic diseases.Methods:A retrospective case series study was performed on the demographic data, laboratory indicators, imaging features, treatment regimens, and follow-up data of 8 children with rheumatic diseases complicated by PE who were admitted to the Department of Rheumatology and Immunology, Capital Center for Children′s Health, Capital Medical University from January 2014 to October 2023.Results:Among the 8 children, there were 4 boys and 4 girls, with an age of 12.0 (7.5, 13.0) years. Among the primary diseases, there were 3 cases of systemic lupus erythematosus, 2 cases of Beh?et′s disease, 2 cases of Takayasu arteritis, and 1 case of antiphospholipid syndrome. All children developed PE during the active phase of the primary disease. PE was detected at the onset of the primary disease in 3 cases, and the median time from the diagnosis of the primary disease to the development of PE was 10.0 (6.0, 25.0) months in the remaining 5 cases. Fever was present in all 8 children, 4 cases were accompanied by chest tightness, dyspnea, etc., and 2 cases only presented with fever. Laboratory examinations revealed the following results: erythrocyte sedimentation rate was 42.0 (17.0, 78.0) mm/1 h, high-sensitivity C-reactive protein was 12.7 (2.6, 78.7) mg/L, white blood cell count was 9.6 (7.2, 18.7)×10 9/L; D-dimer was 2.3 (0.9, 6.2) mg/L; and hemoglobin was (109±16) g/L.Imaging examinations revealed that 5 cases had involvement of the bilateral lower pulmonary arteries, 5 cases had peripheral embolism, and 3 cases had central PE. Complications included 3 cases of deep vein thrombosis, 2 cases of intracranial venous sinus thrombosis, and 1 case of mild pulmonary hypertension.In terms of treatment, 7 cases received anticoagulation with heparin followed by warfarin. Immunomodulation was mainly based on glucocorticoids combined with immunosuppressants, and 4 cases were combined with biological agents. The follow-up time of 4.17 (1.75, 7.17) years, the time for complete absorption of PE was 10.5 (6.0, 18.0) months; all 8 children had no target events, with no recurrence or chronic thromboembolic pulmonary hypertension, and the pulmonary artery remodeling was good. Conclusions:PE complicating childhood rheumatic diseases is closely related to the activity of the primary disease. The clinical manifestations are insidious, with fever as the main symptom. Imaging examination is the key to diagnosis.Early adoption of heparin followed by warfarin anticoagulation and glucocorticoids combined with immunosuppressants and (or) biological agents to control the primary disease can achieve a favorable prognosis.