Summary: Background: SARS-CoV-2 is a novel human coronavirus, there is no specific antiviral drugs. It has been proved that host-cell-expressed CD147 could bind spike protein of SARS-CoV-2 and involve in host cell invasion. Antibody against CD147 could block the infection of SARS-CoV-2. We aimed to assess the efficacy and safety of meplazumab, a humanized anti-CD147 antibody, as add-on therapy in patients with COVID-19 pneumonia. Methods: All patients received recommended strategy from Chinese Clinical Guidance for COVID-19 Pneumonia Diagnosis and Treatments released by National Health Commission of China. Eligible patients were add-on administered 10 mg meplazumab intravenously at days 1, 2, and 5. Patients hospitalized in the same period were observed as concurrent control. The endpoints include virological clearance rate, case severity, chest radiographic, and laboratory test. This trial was approved by the Ethics Committee of Institution at the Tangdu hospital, and registered with ClinicalTrials.gov, NCT 04275245. Findings: 17 patients were enrolled and assigned to meplazumab group between Feb 3, 2020 and Feb 10, 2020. 11 hospitalized patients served as concurrent control. Baseline characteristics were generally balanced across two groups. Compared to control group, meplazumab treatment significantly improved the discharged (p=0.005) and case severity (p=0.021) in patients. The time to virus negative in meplazumab group was reduced than that in control group (median 3, 95%CI[1.5-4.5] vs. 13, [6.5-19.5]; p=0.045, HR=0.374, 95%CI[0.143-0.978]). The percentages of patients recovered to the normal lymphocyte count and CRP concentration were also increased remarkably and rapidly in meplazumab group. No adverse effect was found in meplazumab-treated patients. Interpretation: Meplazumab efficiently improved the recovery of patients with SARS-CoV-2 pneumonia with a favorable safety profile. Our results support to carry out a large-scale investigation of meplazumab as a treatment for COVID-19 pneumonia. Funding: National Science and Technology Major Project.

Epithelial cell adhesion molecule (EpCAM) is a type I transmembrane glycoprotein overexpressed in human epithelioma but with relatively low expression in normal epithelial tissues. To exploit this differential expression pattern for targeted cancer therapy, an EpCAM‐targeted immunotoxin was developed and its antitumor activity was investigated in vitro. An immunotoxin (scFv2A9‐PE or APE) was constructed by genetically fusing a truncated form (PE38KDEL) of Pseudomonas aeruginosa exotoxin with an anti‐EpCAM single‐chain variable fragment (scFv). ELISA and flow cytometry were performed to verify immunotoxin (scFv2A9‐PE or APE) antigen‐binding activity with EpCAM. Cytotoxicity was measured by MTT assay. Confocal microscopy was used to observe its cellular localization. The results of ELISA and flow cytometry revealed that the immunotoxin efficiently recognized recombinant and natural EpCAM. Its antigen‐binding activity was relatively lower than 2A9. MTT assay confirmed potent reduction in EpCAM‐positive HHCC (human hepatocellular carcinoma) cell viability (IC₅₀ 50 pM). Immunofluorescence revealed that the immunotoxin localized to endoplasmic reticulum 24 h later. In conclusion, we described the development of an EpCAM‐targeted immunotoxin with potent activity against tumor cells, which may lay the foundation for future development of therapeutic antibody for the treatment of EpCAM‐positive tumors.

Background: Machine learning (ML) has been investigated for its predictive value in knee osteoarthritis (KOA) progression. However, systematic evidence on the effectiveness of ML is still lacking, posing a challenge to precision prevention. Objective: This systematic review aimed to systematically assess the application status and accuracy of ML in predicting KOA progression and to compare the predictive performance of ML, traditional methods, and deep learning under different datasets, model types, modeling variables, and definitions of KOA progression. Methods: Following the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) statement, a systematic search was conducted in Embase, Web of Science, PubMed, and Cochrane Library up to October 10, 2025. Two investigators were independently responsible for study screening, data extraction, and risk-of-bias assessment in included studies using the Prediction Model Risk of Bias Assessment Tool. Meta-analyses were conducted on the concordance index (C-index) and diagnostic 4-fold table using a random effects model, with prediction intervals (PIs) reported. In addition, subgroup analyses were performed by model type, modeling variable, and definition of KOA progression. Results: A total of 32 studies were included. The overall risk of bias was considered low in 8 studies, high in 13 studies, and unclear in 11 studies. For predicting all progression, the pooled C-index was 0.773 (95% CI 0.727‐0.821; 95% PI 0.567‐1.000) for the clinical feature–based model, 0.798 (95% CI 0.755‐0.843; 95% PI 0.646‐0.984) for the magnetic resonance imaging (MRI)–based model, 0.712 (95% CI 0.657‐0.772; 95% PI 0.526‐0.965) for the X-ray–based model, 0.806 (95% CI 0.765‐0.849; 95% PI 0.639‐1.000) for the MRI+clinical feature–based model, 0.772 (95% CI 0.731‐0.815; 95% PI 0.610‐0.976) for the X-ray+clinical feature–based model, and 0.731 (95% CI 0.669‐0.798; 95% PI 0.518‐1.000) for the clinical feature+X-ray+MRI–based model. The clinical feature–based model was established mainly using logistic regression and exhibited accuracy comparable to other ML models. Among image-based models, traditional ML or deep learning possessed higher accuracy. Conclusions: This systematic review used CIs to estimate mean effects and PIs to estimate the potential range of effects in future scenarios. It systematically compared the performance of ML in predicting KOA progression under different model types, modeling variables, and definitions of KOA progression. ML models demonstrate certain discriminatory power in predicting KOA progression, but current evidence should be interpreted with caution due to various sources of significant heterogeneity, such as variations in the definition of KOA progression and validation strategies. Future research should standardize the definition of KOA progression, enhance methodological rigor, and conduct stringent external validation to improve model reliability and facilitate clinical translation.

Takayasu arteritis (TA) is a kind of large-vessel vasculitis that mainly affects the aorta and its branches, and the patients are usually women at a relatively young age. The chronic inflammation of arteries in TA patients leads to stenosis, occlusion, dilatation, or aneurysm formation. Patients with TA thereby have a high risk of cardiovascular disease (CVD) complications, which are the most common cause of mortality. This review summarizes the main cardiovascular complications and the risk factors of cardiovascular complications in patients with TA. Here, we discuss the benefits and potential risks of physical exercise in patients with TA and give recommendations about exercise prescription for TA patients to decrease the risks of CVD and facilitate rehabilitation of cardiovascular complications, which might maximally improve the outcomes.

Axial spondyloarthritis (axSpA) is an inflammatory disease marked by chronic low back pain, with a global average diagnostic delay of 6.7 years. Early diagnosis is crucial for improving prognosis and reducing disability rates, yet primary care physicians (PCPs) may find it challenging to ensure timely recognition and referrals. This study developed and validated Spondyloarthritis Agents (SpAgents), an early diagnostic system based on a multi-agent framework integrating large language models (LLMs) and imaging models. The SpAgents framework includes PlannerAgent, DataAgent, ToolAgent, and DoctorAgent, supported by long-term memory for dynamic knowledge updates. We enrolled 596 patients, dividing 545 from one hospital into a training dataset (n = 359) and a validation dataset (n = 186), along with an independent cohort of 51 patients from five additional hospitals for testing. SpAgents demonstrated strong diagnostic performance, achieving sensitivity of 0.8615 and specificity of 0.8000 during validation, and 0.9375 and 0.7368 during testing. SpAgents exhibited significantly higher sensitivity (0.9400) and accuracy (0.8600) than both PCPs and junior rheumatologists, with overall performance equivalent to that of senior rheumatologists. Under SpAgents-assisted diagnosis, both PCPs and junior rheumatologists showed marked improvements in sensitivity and accuracy. SpAgents effectively enhance early axSpA identification among PCPs, offering an innovative solution to reduce diagnostic delays.