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.

Recent advances in large models demonstrate significant prospects for transforming the field of medical imaging. These models, including large language models, large visual models, and multimodal large models, offer unprecedented capabilities in processing and interpreting complex medical data across various imaging modalities. By leveraging self-supervised pretraining on vast unlabeled datasets, cross-modal representation learning, and domain-specific medical knowledge adaptation through fine-tuning, large models can achieve higher diagnostic accuracy and more efficient workflows for key clinical tasks. This review summarizes the concepts, methods, and progress of large models in medical imaging, highlighting their potential in precision medicine. The article first outlines the integration of multimodal data under large model technologies, approaches for training large models with medical datasets, and the need for robust evaluation metrics. It then explores how large models can revolutionize applications in critical tasks such as image segmentation, disease diagnosis, personalized treatment strategies, and real-time interactive systems, thus pushing the boundaries of traditional imaging analysis. Despite their potential, the practical implementation of large models in medical imaging faces notable challenges, including the scarcity of high-quality medical data, the need for optimized perception of imaging phenotypes, safety considerations, and seamless integration with existing clinical workflows and equipment. As research progresses, the development of more efficient, interpretable, and generalizable models will be critical to ensuring their reliable deployment across diverse clinical environments. This review aims to provide insights into the current state of the field and provide directions for future research to facilitate the broader adoption of large models in clinical practice.
Humans ; Diagnostic Imaging/methods* ; Precision Medicine/methods* ; Image Processing, Computer-Assisted/methods*

BACKGROUND: The clinical impact of post-percutaneous coronary intervention (PCI) quantitative flow ratio (QFR) in patients treated with PCI for chronic total occlusion (CTO) was still undetermined. METHODS: All CTO vessels treated with successful anatomical PCI in patients from PANDA III trial were retrospectively measured for post-PCI QFR. The primary outcome was 2-year vessel-oriented composite endpoints (VOCEs, composite of target vessel-related cardiac death, target vessel-related myocardial infarction, and ischemia-driven target vessel revascularization). Receiver operator characteristic curve analysis was conducted to identify optimal cutoff value of post-PCI QFR for predicting the 2-year VOCEs, and all vessels were stratified by this optimal cutoff value. Cox proportional hazards models were employed to calculate the hazard ratio (HR) with 95% CI. RESULTS: Among 428 CTO vessels treated with PCI, 353 vessels (82.5%) were analyzable for post-PCI QFR. 31 VOCEs (8.7%) occurred at 2 years. Mean value of post-PCI QFR was 0.92 ± 0.13. Receiver operator characteristic curve analysis shown the optimal cutoff value of post-PCI QFR for predicting 2-year VOCEs was 0.91. The incidence of 2-year VOCEs in the vessel with post-PCI QFR < 0.91 (n = 91) was significantly higher compared with the vessels with post-PCI QFR ≥ 0.91 (n = 262) (22.0% vs. 4.2%, HR = 4.98, 95% CI: 2.32-10.70). CONCLUSIONS Higher post-PCI QFR values were associated with improved prognosis in the PCI practice for coronary CTO. Achieving functionally optimal PCI results (post-PCI QFR value ≥ 0.91) tends to get better prognosis for patients with CTO lesions.

Objective To explore the relationship between dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)and clinical pathological features of invasive breast cancer and lymphovascular invasion(LVI).Methods Imaging and clinical pathological data were retrospectively collected from 508 patients with invasive breast cancer who underwent breast DCE-MRI at the First Medical Center of Chinese PLA General Hospital from January 2019 to August 2021.Patients were divided into the LVI-positive(LVI+)group(n=79)and LVI-negative(LVI-)group(n=429)based on postoperative pathological results.Univariate and multivariate logistic regression analyses were used to identify risk factors for LVI.Results Compared with LVI-group,LVI+group had a higher proportion of patients aged<45 years(44.3%vs.27.0%,P=0.002),non-mass-like enhancement(NME)(31.7%vs.17.7%,P=0.004),Ki-67 expression rate(40.0%vs.30.0%,P<0.001),high Ki-67 expression(94.9%vs.78.1%,P=0.001),Luminal B subtype(76.0%vs.60.1%,P=0.008),and positive axillary lymph nodes rate(72.2%vs.31.5%,P<0.001),while the proportion of Luminal A subtype was lower(2.5%vs.21.5%,P<0.001).Univariate and multivariate logistic regression analyses showed that age≥45 years(OR=0.468,95%CI 0.280-0.783,P=0.004)was an independent protective factor for LVI,while NME(OR=1.987,95%CI 1.126-3.444,P=0.016)was an independent risk factor.Compared with Luminal A subtype,patients with Luminal B subtype(OR=10.482,95%CI 3.164-64.923,P=0.001),HER-2 overexpression subtype(OR=11.571,95%CI 2.755-79.341,P=0.003)and triple-negative subtypes(OR=8.433,95%CI 1.985-57.908,P=0.009)had a higher risk of LVI.Conclusions Age≥45 years is an independent protective factor for LVI,while NME is an independent risk factor.Among molecular subtypes,patients with Luminal B,HER-2 overexpression and triple-negative subtypes have a higher risk of LVI compared with the Luminal A subtype.

Outer membrane vesicles (OMVs) are nanoscale vesicles secreted by Gram-negative bacteria. As a unique bacterial secretion, OMV secretion can help bacteria maintain the outer membrane stability or remove harmful substances. Studies have shown that local separation of outer membrane and peptidoglycan layers led by abnormalities in outer membrane protein function, abnormal structure or excessive accumulation of LPS, and erroneous accumulation of phospholipids in the outer leaflet, which can all lead to bacterial outer membrane protrusion and eventually bud formation of OMVs. Since OMVs are mainly composed of bacterial outer membrane and periplasmic components, the pathogen associated molecular patterns (PAMPs) on their surface can trigger strong immune responses. For example, OMVs can recruit and activate neutrophils, polarize macrophages to secrete large amounts of inflammatory factors. More importantly, OMVs can act as adjuvants to induce dendritic cell (DC) maturation to enhance adaptive immune response in the body. At the same time, OMVs are derived from bacteria, which make it easy to modify. The methods by genetic engineering and others can improve their tumor targeting, give them new functions, or reduce their immunotoxicity, which is conducive to their application in tumor therapy. OMVs not only induce apoptosis or pyroptosis of tumor cells, but also regulate the host immune system, which makes OMVs themselves have a certain killing effect on tumors. In addition, the tendency of neutrophils to inflammatory tumor sites and the formation of neutrophil extracellular traps enable OMVs to target tumor sites, and the suitable size and the characteristic that they are easily taken up by DCs give OMVs a certain lymphatic targeting ability. Therefore, OMVs are often employed as excellent drug or vaccine carriers in tumor therapy. This review mainly discusses the biological mechanism of OMVs, the regulatory effects of OMVs on immune cells, the functional modification strategies of OMVs, and their research progress in tumor therapy.

ObjectiveTo investigate the structural and functional characteristics of gut microbiota in common traditional Chinese medicine （TCM） syndromes of irritable bowel syndrome with diarrhea （IBS-D）. MethodsIBS-D patients who visited the Hospital of Chengdu University of Traditional Chinese Medicine， and healthy participants from the Physical Examination Centre of the same hospital were recruited from 1st January 2020 to 31st March 2021.The IBS-D patients were classified into syndrome of liver constraint and spleen deficiency， and syndrome of spleen deficiency and dampness exuberance； together with the recruited healthy participants， there were liver-constraint group， dampness-exuberance group， and healthy group. General information， including age， gender and body mass index （BMI）， were collected， and Irritable Bowel Syndrome Symptom Severity Scale （IBS-SSS） as well as Irritable Bowel Syndrome Quality of Life Scale （IBS-QOL） scores were additionally collected from IBS-D patients. Fresh fecal samples were also collected and tested by macro-genome sequencing technology for abundance statistical display， PCoA， Anosim， LEfSe bioinformatic analysis of the annotated gut microbiota structure and function. ResultsThere was no statistically significant difference in the general information of the participants in the three groups （P＞0.05）； the difference in the IBS-SSS and IBS-QOL scores between liver-constraint group and dampness-exuberance group were not statistically significant （P＞0.05）. The study included 28 cases each in liver-constraint group， dampness-exuberance group， and healthy group. The number of specific genes to patients in liver-constraint group was 269 135， with 216 156 in dampness-exuberance group and 249 759 in healthy group， accounting of total 1 784 036 in the three groups. There were differences in the relative abundance distribution of the top ten species of gut microbiota among the three groups， with smaller differences at the phylum， class and order levels， and larger differences at the family， genus and species levels. There were differences in the relative abundance of structure and function of the gut microbiota among the three groups. Species PCoA and Anosim analyses at the species level showed significant differences in the composition of the microbiota among the three groups. Further LEfSe analyses showed that patients in liver-constraint group were screened for 14 dominant strains， of which Clostridium sp. CAG 217， Lachnospira pectinoschiza， Anaerotruncus sp. CAG 528， Paeniclostridium sordellii， Eubecterium sp. CAG 76， Bacillus cereus were affected to a greater extent in abundance differences； dampness-exuberance group screened 24 species of dominant bacteria， of which Roseburia inulinivorans， Eubacterium sp. CAG 251， Roseburia hominis， Unclassified Eubacterium rectale， Roseburia intestinalis， and Megamonas funiformis were affected to a greater extent in abundance differences； no dominant functional genes were screened for patients in liver-constraint group， and dampness-exuberance group was screened for flagellum assembly （ko02040）， porphyrin metabolism （ ko00860）， salmonella infection （ko05132）， and benzoic acid degradation （ko00362）. The differentially dominant functional genes in liver-constraint group and dampness-exuberance group may mainly focus on metabolism （including biodegradation and metabolism of exogenous substances， energy metabolism， lipid metabolism， etc.）. ConclusionIBS-D with syndrome of liver constraint and spleen deficiency is characterized by the enrichment of 14 gut microbiota， such as Clostridium sp. CAG 217， while IBS-D with syndrome of spleen deficiency and dampness exuberance is characterized by the enrichment of 24 gut microbiota， such as Roseburia inulinivorans， and 4 functional enrichments， such as flagellum assembly. Clostridium sp. CAG 217 and Roseburia inulinivorans are expected to be biomarkers for IBS-D patients in the two syndromes， respectively.

Background and aim:Hepatic ischemia-reperfusion injury(IRI)is a significant challenge in liver trans-plantation,trauma,hypovolemic shock,and hepatectomy,with limited effective interventions available.This study aimed to investigate the role of leukocyte cell-derived chemotaxin 2(LECT2)in hepatic IRI and assess the therapeutic potential of Lect2-short hairpin RNA(shRNA)delivered through adeno-associated virus(AAV)vectors. Materials and methods:This study analyzed human liver and serum samples from five patients under-going the Pringle maneuver.Lect2-knockout and C57BL/6J mice were used.Hepatic IRI was induced by clamping the hepatic pedicle.Treatments included recombinant human LECT2(rLECT2)and AAV-Lect2-shRNA.LECT2 expression levels and serum biomarkers including alanine aminotransferase(ALT),aspartate aminotransferase(AST),creatinine,and blood urea nitrogen(BUN)were measured.Histological analysis of liver necrosis and quantitative reverse-transcription polymerase chain reaction were performed. Results:Serum and liver LECT2 levels were elevated during hepatic IRI.Serum LECT2 protein and mRNA levels increased post reperfusion.Lect2-knockout mice had reduced weight loss;hepatic necrosis;and serum ALT,AST,creatinine,and BUN levels.rLECT2 treatment exacerbated weight loss,hepatic necrosis,and serum biomarkers(ALT,AST,creatinine,and BUN).AAV-Lect2-shRNA treatment significantly reduced weight loss,hepatic necrosis,and serum biomarkers(ALT,AST,creatinine,and BUN),indicating thera-peutic potential. Conclusions:Elevated LECT2 levels during hepatic IRI increased liver damage.Genetic knockout or shRNA-mediated knockdown of Lect2 reduced liver damage,indicating its therapeutic potential.AAV-mediated Lect2-shRNA delivery mitigated hepatic IRI,offering a potential new treatment strategy to enhance clinical outcomes for patients undergoing liver-related surgeries or trauma.

Humans ; Acute Disease ; Pancreatitis/diagnosis* ; Follow-Up Studies ; Patient Discharge ; Disease Progression

Objective To compare the differences in lower limb force line between degenerative medial meniscus injuries and lateral meniscus injuries and investigate their correlation.Methods A total of 90 patients who underwent arthroscopic treatment for meniscal injuries between March 2019 and March 2022 were enrolled in the study.They were 45 males and 45 females,at a median age of 52 years(ranging from 40 to 59 years).Of these patients,47 had medial meniscus injuries,while 43 had lateral meniscus injuries.The hip-knee-ankle(HKA)angle was measured on full-length films,and the differences were compared between the 2 groups.Results There were no significant differences in terms of gender,age,lower limb laterality,body mass index,site of injury,and type of injury between the medial meniscus injury group and the lateral meniscus injury group.Statistical difference was observed in the mean HKA angle,with a value of(177.20±2.46)° in the medial meniscus injury group and of(181.05±3.13)° in the lateral meniscus injury group(P＜0.01).Conclusion There is a significant difference in HKA angle between medial meniscus injury group and the lateral meniscus injury group.A correlation is found between lower limb alignment and degenerative meniscus injury.

Objective To investigate the incidence rate,clinical characteristics,and prognosis of neonatal stroke in Shenzhen,China.Methods Led by Shenzhen Children's Hospital,the Shenzhen Neonatal Data Collaboration Network organized 21 institutions to collect 36 cases of neonatal stroke from January 2020 to December 2022.The incidence,clinical characteristics,treatment,and prognosis of neonatal stroke in Shenzhen were analyzed.Results The incidence rate of neonatal stroke in 21 hospitals from 2020 to 2022 was 1/15 137,1/6 060,and 1/7 704,respectively.Ischemic stroke accounted for 75％(27/36);boys accounted for 64％(23/36).Among the 36 neonates,31(86％)had disease onset within 3 days after birth,and 19(53％)had convulsion as the initial presentation.Cerebral MRI showed that 22 neonates(61％)had left cerebral infarction and 13(36％)had basal ganglia infarction.Magnetic resonance angiography was performed for 12 neonates,among whom 9(75％)had involvement of the middle cerebral artery.Electroencephalography was performed for 29 neonates,with sharp waves in 21 neonates(72％)and seizures in 10 neonates(34％).Symptomatic/supportive treatment varied across different hospitals.Neonatal Behavioral Neurological Assessment was performed for 12 neonates(33％,12/36),with a mean score of(32±4)points.The prognosis of 27 neonates was followed up to around 12 months of age,with 44％(12/27)of the neonates having a good prognosis.Conclusions Ischemic stroke is the main type of neonatal stroke,often with convulsions as the initial presentation,involvement of the middle cerebral artery,sharp waves on electroencephalography,and a relatively low neurodevelopment score.Symptomatic/supportive treatment is the main treatment method,and some neonates tend to have a poor prognosis.