Objective To explore the application value of three mainstream large language models in the diagnosis, differential diagnosis, and treatment decision support of the primary diseases related to pediatric liver transplantation. Methods Seventy-nine cases of pediatric liver transplantation-related diseases diagnosed through pathological or clinical follow-up data were collected from Renji Hospital, Shanghai Jiao Tong University School of Medicine or published high-quality case reports. These cases covered 25 types of primary diseases such as cholestatic liver disease, metabolic diseases, and tumors. Standardized prompts were used to input the case information into the DeepSeek-R1, ChatGPT-4o and Grok-3 models, and the accuracy of their preliminary diagnosis and differential diagnosis based on basic clinical data was evaluated. The final diagnosis accuracy and the response time after supplementary examination were also assessed, as well as the completeness and rationality of their analysis of disease treatment principles. Results In the initial diagnosis and differential diagnosis stage, the comprehensive accuracy of DeepSeek-R1 was the highest [72.1%, 95% confidence interval (CI) 61.4% - 80.8%], and there was a statistically significant difference in the comprehensive accuracy of the three models for initial diagnosis (P = 0.008). After adding further examination information, the final diagnosis accuracy of the three models increased, with DeepSeek-R1 at 88.6% (95% CI 79.7% - 93.9%), ChatGPT-4o at 87.3% (95% CI 78.2% - 93.0%), and Grok-3 at 78.5% (95% CI 68.2% - 86.1%). There was no statistically significant difference among the three models (P = 0.05). The scores given by experts for the treatment principles showed good consistency (Kappa = 0.769). In addition, the response time of ChatGPT-4o is shorter than that of the other two models [(24 ± 7) s]. Conclusions Large language models demonstrate good efficacy in the diagnosis and treatment decision-making process of various pediatric liver diseases, have a good application prospect for auxiliary diagnosis and decision support, and are expected to help improve the accuracy and efficiency of clinical diagnosis and treatment of pediatric liver transplantation-related primary diseases.

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:Osteoporotic vertebral fractures are the most common complication in patients with osteoporosis.As a new imaging technique,spine magnetic resonance imaging(MRI)is much more sensitive than X-ray film in the diagnosis of osteoporotic vertebral fractures.However,total spine MRI is costly and takes a long time to scan.Therefore,there is no consensus on whether all patients with osteoporotic vertebral fractures need to undergo total spine MRI scan and which patients need to undergo total spine MRI. OBJECTIVE:To analyze the distribution characteristics of vertebral fractures and explore their clinical significance by observing the whole spine MRI data of osteoporotic vertebral fractures patients. METHODS:Data of cases and MRI images of all patients diagnosed with fresh osteoporotic vertebral fractures who visited the Department of Orthopedics,Affiliated Hospital of Southwest Medical University from August 2018 to September 2022 were retrospectively analyzed.903 patients were included in the study based on inclusion and exclusion criteria.General information(age,gender,and body mass index),medical history characteristics(duration of illness,history of trauma surgery,percussion pain area,and pain score)were collected.The characteristics of vertebral fractures were analyzed through whole spine magnetic resonance imaging.Firstly,based on the number of vertebral fractures in patients,they were divided into the single vertebral fracture group(484 cases)and the multi-vertebral fracture group(419 cases),and the differences were analyzed between the two groups.Then,based on whether the farthest interval between the fractured vertebrae was greater than or equal to 5,the multi vertebral fracture group was further divided into two subgroups.Among them,Group A(the farthest interval between the fractured vertebrae was less than 5)contained 306 cases;Group B(with the farthest interval between fractured vertebral bodies greater than 5)included 113 cases.The differences were analyzed between two subgroups. RESULTS AND CONCLUSION:(1)Among 903 patients,419 patients(46.4%)had more than two fractured vertebrae.There were 654 patients(72.4%)with thoracolumbar fractures,and 54 patients(6%)with fractures in the thoracic plus lumbar region and the entire thoracic to lumbar region.In group B,96.5%of patients had multiregional percussion pain.(2)Compared with the patients in the single vertebral fracture group and the multi-vertebral fracture group,there were significant differences in bone mineral density,whether the medical history was greater than or equal to 1 month,the history of low energy injury,and the distribution and number of axial percussion pain areas in the spine during physical examination between the two groups(P<0.05).Age,gender,body mass index,whether there was underlying disease,pain visual analog scale score,whether there was a history of elderly thoracolumbar fracture,and whether there was a history of thoracolumbar surgery,and the number of fractured vertebrae had no statistical significance(P>0.05).(3)There were statistically significant differences between the Groups A and B in bone mineral density,the distribution and quantity of percussion pain area,and the history of low energy injury(P<0.05).There were no significant differences in age,gender,history of old fractures,visual analog scale score,body mass index,whether the medical history was longer than or equal to 1 month,history of underlying diseases,and history of thoracolumbar surgery between the two groups(P>0.05).(4)Patients with multiple low-energy trauma history,history of more than 1 month,multiple percussion pain,and the lower bone mineral density should be alert to the occurrence of multiple vertebral fracture and jump fracture.We recommend the whole spinal MRI for these patients.

With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.

Objective: Based on spinopelvic parameters and biomechanical principles, the pedicle-facet joint (PFJ) morphological characteristics of isthmic and degenerative spondylolisthesis were analyzed, and the mechanism of their onset and progression was discussed. Methods: This retrospective cross-sectional study included 194 patients with L5 spondylolysis or L5–S1 low-grade isthmic spondylolisthesis (IS group), 172 patients with L4–5 degenerative spondylolisthesis (DS group), and 366 patients with nonlumbar spondylolysis (NL group). The spinopelvic parameters and PFJ morphological parameters of the patients were measured, the differences in these parameters among and within the 3 groups were compared, and the correlations were analyzed. Results: Sacral slope (SS) and lumbar lordosis (LL) were the highest in the IS group, the second highest in the DS group, and the lowest in the NL group. Among the 3 groups, the L4 facet joint angle (FJA) was the largest in the IS group, the second largest in the NL group, and the smallest in the DS group. The L4 pedicle-facet joint angle (PFA) was the largest in the DS group, the second largest in the IS group, and the smallest in the NL group. Pearson correlation analysis showed that within each group, SS and LL were negatively correlated with FJA and positively correlated with PFA. Conclusion This study found a correlation between the PFJ morphological characteristics of patients with lumbar spondylolisthesis and spinopelvic parameters, suggesting that the morphological characteristics of PFJs may be caused by varying stresses under different spinopelvic morphologies.

Objective:To investigate the risk factors for adverse outcomes in elderly patients with nonvalvular atrial fibrilla-tion(AF)after percutaneous left atrial appendage closure(LAAC)combined with radiofrequency ablation(RFA).Meth-ods:A total of 199 elderly AF patients who admitted in Department of Cardiology,Yuhuangding Hospital between Jan 1st,2019 and Aug 17th,2023 and underwent LAAC combined RFA were enrolled.The patients were divided into case group(n=78)and control group(n=121)according to presence of atrial arrhythmia and/or cerebral infarction(CI)within one year after operation.Baseline clinical data,laboratory indexes and color Doppler ultrasound indexes were compared be-tween the two groups,and multivariate Logistic regression was used to analyze the risk factors for postoperative atrial ar-rhythmia and/or CI.Receiver operating characteristic(ROC)curve was constructed to analyze the predictive efficacy of risk factors for atrial arrhythmia and/or CI after operation.Results:Univariate analysis indicated that compared with pa-tients in control group,those in case group had significant higher proportions of preoperative persistent atrial fibrillation(52.60％ vs.37.20％),old myocardial infarction(OMI)(11.50％vs.1.70％)and left atrial diameter(LAD)[(45.47±6.90)mm vs.(43.34±6.64)mm](P＜0.05 or＜0.01).Multivariate Logistic regression analysis indicated history of OMI(OR=8.736,95％CI 1.772～43.069,P=0.008)and LAD(OR=1.053,95％CI 1.006～1.102,P=0.027)were independent risk factors of adverse outcomes in elderly AF patients after LAAC+RFA.ROC analysis indicated that predic-tive efficacy of combined detection of OMI and LAD(AUC=0.663,95％CI 0.593～0.728)for adverse outcomes within 1 year in elderly AF patients after LAAC+RFA was significantly better than those of OMI(AUC=0.549,95％CI 0.477～0.620)and LAD(AUC=0.602,95％CI 0.531～0.671)alone(Z=3.045,2.312,P=0.002,0.021).Conclusion:His-tory of old myocardial infarction and left atrial diameter are independent risk factors for atrial arrhythmia and/or cerebral infarction within 1 year after percutaneous left atrial appendage closure combined with radiofrequency ablation in elderly patients with atrial fibrillation,and the combination has good predictive performance.

Objective:To investigate the risk factors for adverse outcomes in elderly patients with nonvalvular atrial fibrilla-tion(AF)after percutaneous left atrial appendage closure(LAAC)combined with radiofrequency ablation(RFA).Meth-ods:A total of 199 elderly AF patients who admitted in Department of Cardiology,Yuhuangding Hospital between Jan 1st,2019 and Aug 17th,2023 and underwent LAAC combined RFA were enrolled.The patients were divided into case group(n=78)and control group(n=121)according to presence of atrial arrhythmia and/or cerebral infarction(CI)within one year after operation.Baseline clinical data,laboratory indexes and color Doppler ultrasound indexes were compared be-tween the two groups,and multivariate Logistic regression was used to analyze the risk factors for postoperative atrial ar-rhythmia and/or CI.Receiver operating characteristic(ROC)curve was constructed to analyze the predictive efficacy of risk factors for atrial arrhythmia and/or CI after operation.Results:Univariate analysis indicated that compared with pa-tients in control group,those in case group had significant higher proportions of preoperative persistent atrial fibrillation(52.60％ vs.37.20％),old myocardial infarction(OMI)(11.50％vs.1.70％)and left atrial diameter(LAD)[(45.47±6.90)mm vs.(43.34±6.64)mm](P＜0.05 or＜0.01).Multivariate Logistic regression analysis indicated history of OMI(OR=8.736,95％CI 1.772～43.069,P=0.008)and LAD(OR=1.053,95％CI 1.006～1.102,P=0.027)were independent risk factors of adverse outcomes in elderly AF patients after LAAC+RFA.ROC analysis indicated that predic-tive efficacy of combined detection of OMI and LAD(AUC=0.663,95％CI 0.593～0.728)for adverse outcomes within 1 year in elderly AF patients after LAAC+RFA was significantly better than those of OMI(AUC=0.549,95％CI 0.477～0.620)and LAD(AUC=0.602,95％CI 0.531～0.671)alone(Z=3.045,2.312,P=0.002,0.021).Conclusion:His-tory of old myocardial infarction and left atrial diameter are independent risk factors for atrial arrhythmia and/or cerebral infarction within 1 year after percutaneous left atrial appendage closure combined with radiofrequency ablation in elderly patients with atrial fibrillation,and the combination has good predictive performance.

This study aims to investigate the changes in blood biochemical indicators of tongue roll-ing(TR)behavior in cattle and their correlation with changes in oral microbiota,laying a founda-tion for further exploring the relationship between animal oral microbiota,biochemical indicators,and behavioral changes.It also provides theoretical basis for preventing and treating TR behavior through regulating oral microbiota.This study intends to analyze and compare the blood biochemi-cal indicators and changes in oral microbiota of cattle with TR behavior and healthy cattle without TR behavior(healthy control,H),in order to explore the blood biochemical indicators of TR cattle and their correlation with changes in oral microbiota.Blood samples from the caudal vein of cattle in each group were collected for the detection of blood biochemical indicators and stress-related hormone indicators.Oral swabs from cattle in each group were collected for 16S rRNA gene se-quencing to analyze the composition,structure,and functional changes of their oral microbiota.The results of blood biochemical indicators in H and TR groups showed that the concentrations of al-bumin(ALB),aspartate aminotransferase(AST),calcium ion(Ca2+),and cortisol in TR group were significantly higher than those in H group(P＜0.05).There were significant differences in beta diversity of oral microbiota between TR and H groups(P＜0.05).At the genus level,the rela-tive abundances of Pseudomonas,Enterobacter,Xanthomonas,and other genera in the oral micro-biota of TR group were significantly higher than those in H group(P＜0.05).However,the rela-tive abundances of Tessaracoccus,Turicibacter,Monoglobus,Dietzia,Bifidobacterium,and other genera in the oral microbiota of TR group were significantly lower than those in H group(P＜0.05).In the KEGG metabolic pathway at the third level,the relative abundances of thiamine me-tabolism,lipoate metabolism,cysteine and methionine metabolism in the oral microbiota of TR group were significantly lower than those in H group(P＜0.05).Spearman correlation analysis showed that ALB and AST were significantly positively correlated with the relative abundances of Pseudomonas and Stenotrophomonas.Therelative abundances of Pseudomonas,Stenotrophomonas,and Sphingomonas were significantly positively correlated with fatty acid metabolism,phosphate and phosphonate metabolism,and lipoate metabolism.ALB was significantly positively correlated with inositol phosphate metabolism and phosphate and phosphonate metabolism.The study found that there were significant differences in blood biochemical indicators and oral microbiota between TR and H groups.In addition,there is a certain correlation between the composition,structure,and function of oral microbiota and the biochemical function of the host.This indicates that TR behav-ior may be associated with changes in the biochemical indicators of the host and the composition,structure,and function of oral microbiota.

Metabolic-bariatric surgery(MBS)has become an important treatment for pathological obesity and metabolic diseases.However,common postoperative nutritional complications—such as protein-energy malnutrition,iron deficiency anemia,and vitamin B12 deficiency—significantly affect patients' long-term prognosis.Traditional nutritional management models rely on static monitoring and standardized supplementation,which are insufficient to address individual variability and dynamic postoperative changes.Artificial intelligence(AI),through integrating multimodal data(such as biochemical indicators,imaging information,and wearable device monitoring)and intelligent modeling,offers new approaches for dynamic monitoring,risk prediction,and personalized intervention.Based on literature from 2017 to 2025,this article systematically evaluates the application of AI in perioperative nutritional management for MBS,covering key technologies including machine learning,deep learning,and natural language processing.It also analyzes current challenges in clinical translation,such as data fragmentation,lack of model interpretability,and limited long-term validation.In the future,enhanced multi-center collaboration,the development of standardized databases,and explainable models will be essential to advancing nutritional management in MBS from empirical practice to precision medicine.

Objective To investigate the impact of arthroscopic assisted locking hollow screw fixation on knee joint function and pain factors in patients with tibial plateau fractures.Method 113 patients with tibial plateau fractures from June 2021 to June 2023 were selected.According to different surgical methods,the patients were divided into arthroscopic group(57 cases)and traditional group(56 cases).The arthroscopic group was treated with arthroscopic assisted locking hollow screw fixation,while the traditional group was treated with open reduction and internal fixation.Compare the surgical status,postoperative recovery,and incidence of complications between two groups of patients,as well as the changes in pain factor levels before and after 24 hours of surgery,knee joint function before and 6 months after surgery,and changes in knee joint range of motion 6 months after surgery.Results The results showed that the arthroscopic group had significantly shorter surgical time and less intraoperative bleeding compared to the traditional group,with statistically significant differences(P<0.05);The serum levels of 5-hydroxytryptamine(5-HT),substance P(SP),and prostaglandin E2(PGE2)were significantly higher in both groups of patients 24 hours after surgery than those before surgery,but the arthroscopic group was significantly lower than that in traditional group,and the differences were statistically significant(P<0.05);The arthroscopic group had significantly shorter postoperative mobilization time,hospitalization time,weight-bearing time,and fracture healing time compared to the traditional group,and the differences were statistically significant(P<0.05);There was no statistically significant difference in Knee Society score(KSS)clinical score,KSS functional score,and hospital for special surgery knee score(HSS)between the two groups of patients 6 months after surgery(P>0.05);The knee joint extension and flexion in the arthroscopic group were significantly greater than those in the traditional group 6 months after surgery,and the differences were statistically significant(P<0.05);The postoperative incision infection in the arthroscopic group was significantly less than that in the traditional group,and the difference was statistically significant(P<0.05).Conclusion Arthroscopic assisted locking hollow screw fixation is effective in treating tibial plateau fractures,significantly improving knee joint function and inhibiting pain factor release.It is worthy of clinical promotion and application.