Aim: Data from 124 rheumatoid arthritis (RA) patients and 69 healthy controls were collected. Materials & methods: ELISA was performed to detect serum FABP4 levels. Results: FABP4 level was elevate...

Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. Here, we have recruited a 144 COVID-19 patient cohort consisting of training, validation, and internal test sets, longitudinally recorded 124 routine clinical and laboratory parameters, and built a machine learning model to predict the disease progression based on measurements from the first 12 days since the disease onset when no patient became severe. A panel of 11 routine clinical factors, including oxygenation index, basophil counts, aspartate aminotransferase, gender, magnesium, gamma glutamyl transpeptidase, platelet counts, activated partial thromboplastin time, oxygen saturation, body temperature and days after symptom onset, constructed a classifier for COVID-19 severity prediction, achieving accuracy of over 94%. Validation of the model in an independent cohort containing 25 patients achieved accuracy of 80%. The overall sensitivity, specificity, PPV and NPV were 0.70, 0.99, 0.93 and 0.93, respectively. Our model captured predictive dynamics of LDH and CK while their levels were in the normal range. This study presents a practical model for timely severity prediction and surveillance for COVID-19, which is freely available at webserver https://guomics.shinyapps.io/covidAI/ .

Recombination signal-binding protein for immunoglobulin kappa J region (RBPJ) is a transcriptional regulator that plays an important role in maintaining immune homeostasis. This study aimed to estimate the expression of RBPJ in rheumatoid arthritis (RA) patients and investigate its relationship with RA. A total of 83 newly diagnosed RA patients and 70 healthy controls were included. mRNA was extracted from peripheral blood mononuclear cells (PBMCs), and the expression of RBPJ was detected using quantitative real-time PCR (qRT‒PCR). An RA dataset (GSE89408) was obtained from the Gene Expression Omnibus (GEO) database, and RA synovial tissues were divided into two groups. The differentially expressed genes (DEGs) were selected with the “DESeq2” R package. RBPJ expression was lower in RA patients than in health controls and was negatively correlated with the DAS28 score, C-reactive protein (CRP) level and erythrocyte sedimentation rate (ESR). RA synovial tissues from GSE89408 were classified into RBPJ-low (≤ 25%) and RBPJ-high (≥ 75%) groups according to RBPJ expression, and 562 DEGs were identified. Gene Ontology (GO) enrichment analyses revealed that the DEGs significantly affected the regulation of T cell activation and lymphocyte/mononuclear cell differentiation. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis revealed that the most enriched pathways of DEGs were the T cell receptor signaling pathway, Th1/2 and Th17 cell differentiation, the PI3K − Akt signaling pathway and cytokine‒cytokine receptor interaction. CytoHubba Plugin revealed that most of the top 10 genes were involved in osteoclast differentiation, the T cell receptor signaling pathway and cytokine‒cytokine receptor interaction. RBPJ expression was significantly lower in RA patients and negatively correlated with disease activity. GEO dataset analysis demonstrated that RBPJ may be involved in osteoclast differentiation, T cell activation and differentiation, and the T cell receptor signaling pathway. Our research may contribute to understanding the potential mechanisms by which RBPJ regulates T cell differentiation and cytokine‒cytokine receptor interaction in RA patients.