Tetracyclines enhance antitumor T-cell immunity via the Zap70 signaling pathway.

BACKGROUND: Cancer immunotherapy including immune checkpoint inhibitors is only effective for a limited population of patients with cancer. Therefore, the development of novel cancer immunotherapy is anticipated. In preliminary studies, we demonstrated that tetracyclines enhanced T-cell responses. Therefore, we herein investigated the efficacy of tetracyclines on antitumor T-cell responses by human peripheral T cells, murine models, and the lung tumor tissues of patients with non-small cell lung cancer (NSCLC), with a focus on signaling pathways in T cells. METHODS: The cytotoxicity of peripheral and lung tumor-infiltrated human T cells against tumor cells was assessed by using bispecific T-cell engager (BiTE) technology (BiTE-assay system). The effects of tetracyclines on T cells in the peripheral blood of healthy donors and the tumor tissues of patients with NSCLC were examined using the BiTE-assay system in comparison with anti-programmed cell death-1 (PD-1) antibody, nivolumab. T-cell signaling molecules were analyzed by flow cytometry, ELISA, and qRT-PCR. To investigate the in vivo antitumor effects of tetracyclines, tetracyclines were administered orally to BALB/c mice engrafted with murine tumor cell lines, either in the presence or absence of anti-mouse CD8 inhibitors. RESULTS: The results obtained revealed that tetracyclines enhanced antitumor T-cell cytotoxicity with the upregulation of granzyme B and increased secretion of interferon-γ in human peripheral T cells and the lung tumor tissues of patients with NSCLC. The analysis of T-cell signaling showed that CD69 in both CD4+ and CD8+ T cells was upregulated by minocycline. Downstream of T-cell receptor signaling, Zap70 phosphorylation and Nur77 were also upregulated by minocycline in the early phase after T-cell activation. These changes were not observed in T cells treated with anti-PD-1 antibodies under the same conditions. The administration of tetracyclines exhibited antitumor efficacy with the upregulation of CD69 and increases in tumor antigen-specific T cells in murine tumor models. These changes were canceled by the administration of anti-mouse CD8 inhibitors. CONCLUSIONS: In conclusion, tetracyclines enhanced antitumor T-cell immunity via Zap70 signaling. These results will contribute to the development of novel cancer immunotherapy.

5,6-dimethylxanthenone-4-acetic acid (DMXAA), a partial STING agonist, competes for human STING activation.

5,6-dimethylxanthenone-4-acetic acid (DMXAA) is a mouse-selective stimulator of interferon gene (STING) agonist exerting STING-dependent anti-tumor activity. Although DMXAA cannot fully activate human STING, DMXAA reached phase III in lung cancer clinical trials. How DMXAA is effective against human lung cancer is completely unknown. Here, we show that DMXAA is a partial STING agonist interfering with agonistic STING activation, which may explain its partial anti-tumor effect observed in humans, as STING was reported to be pro-tumorigenic for lung cancer cells with low antigenicity. Furthermore, we developed a DMXAA derivative-3-hydroxy-5-(4-hydroxybenzyl)-4-methyl-9H-xanthen-9-one (HHMX)-that can potently antagonize STING-mediated immune responses both in humans and mice. Notably, HHMX suppressed aberrant responses induced by STING gain-of-function mutations causing STING-associated vasculopathy with onset in infancy (SAVI) in in vitro experiments. Furthermore, HHMX treatment suppressed aberrant STING pathway activity in peripheral blood mononuclear cells from SAVI patients. Lastly, HHMX showed a potent therapeutic effect in SAVI mouse model by mitigating disease progression. Thus, HHMX offers therapeutic potential for STING-associated autoinflammatory diseases.

Galectin-10 in serum extracellular vesicles reflects asthma pathophysiology.

BACKGROUND: Novel biomarkers (BMs) are urgently needed for bronchial asthma (BA) with various phenotypes and endotypes. OBJECTIVE: We sought to identify novel BMs reflecting tissue pathology from serum extracellular vesicles (EVs). METHODS: We performed data-independent acquisition of serum EVs from 4 healthy controls, 4 noneosinophilic asthma (NEA) patients, and 4 eosinophilic asthma (EA) patients to identify novel BMs for BA. We confirmed EA-specific BMs via data-independent acquisition validation in 61 BA patients and 23 controls. To further validate these findings, we performed data-independent acquisition for 6 patients with chronic rhinosinusitis without nasal polyps and 7 patients with chronic rhinosinusitis with nasal polyps. RESULTS: We identified 3032 proteins, 23 of which exhibited differential expression in EA. Ingenuity pathway analysis revealed that protein signatures from each phenotype reflected disease characteristics. Validation revealed 5 EA-specific BMs, including galectin-10 (Gal10), eosinophil peroxidase, major basic protein, eosinophil-derived neurotoxin, and arachidonate 15-lipoxygenase. The potential of Gal10 in EVs was superior to that of eosinophils in terms of diagnostic capability and detection of airway obstruction. In rhinosinusitis patients, 1752 and 8413 proteins were identified from EVs and tissues, respectively. Among 11 BMs identified in EVs and tissues from patients with chronic rhinosinusitis with nasal polyps, 5 (including Gal10 and eosinophil peroxidase) showed significant correlations between EVs and tissues. Gal10 release from EVs was implicated in eosinophil extracellular trapped cell death in vitro and in vivo. CONCLUSION: Novel BMs such as Gal10 from serum EVs reflect disease pathophysiology in BA and may represent a new target for liquid biopsy approaches.

Pneumocephalus and Cerebral Abscess in Granulomatosis With Polyangiitis.

Granulomatosis with polyangiitis (GPA) is a systemic autoimmune disease that causes necrotizing vasculitis of small- to medium-sized blood vessels and necrotizing granulomatous inflammation, primarily of the upper and lower respiratory system. A 33-year-old woman presented with a 16-month history of headaches, nasal obstruction, and anosmia.

Balloon Dilatation for Bronchoscope Delivery in a Swine Model: A Novel Technique for Ultra-Peripheral Lung Field Access and Accurate Biopsy.

INTRODUCTION: In transbronchial biopsy of peripheral pulmonary lesions, the bronchoscope can reach only a limited depth due to the progressive narrowing of bronchi, which may reduce the diagnostic rate. This study examined the balloon dilatation for bronchoscope delivery (BDBD) technique, employing a novel balloon device to enhance bronchoscopy into the peripheral lung areas. METHODS: Anaesthetised swine served as our primary model. Using computed tomography (CT) scans, we positioned virtual targets characterised by a positive bronchus sign and a diameter of 20 mm beneath the pleura. The bronchoscope was navigated along the pathways determined from the CT images. We performed balloon dilatation when bronchial narrowing obstructed progress to assess whether balloon dilatation would enable the bronchoscope to enter further into the periphery. RESULTS: We established 21 virtual targets on the CT scans. An average of 12.1 branches were identified along the pathways on the CT scans; however, bronchoscopy without BDBD only allowed access to an average of 6.7 branches. Based on 72 balloon dilatations with 3.0-mm or 4.0-mm ultra-thin bronchoscopes, there was an average increased access of 3.43 and 5.14 branches per route, respectively, with no significant BDBD complications. The bronchoscope was able to reach the planned location along all pathways, and the mean final bronchoscopic endpoints were at an average distance of 14.7 mm from the pleura. Post-procedure CT confirmed biopsy accuracy. CONCLUSION: The BDBD technique can enhance access of a flexible bronchoscope into the peripheral lung fields, which could potentially allow more accurate transbronchial interventions for peripheral targets.

Sema6D forward signaling impairs T cell activation and proliferation in head and neck cancer.

Immune checkpoint inhibitors (ICIs) are indicated for a diverse range of cancer types, and characterizing the tumor immune microenvironment is critical for optimizing therapeutic strategies, including ICIs. T cell infiltration and activation status in the tumor microenvironment greatly affects the efficacy of ICIs. Here, we show that semaphorin 6D (Sema6D) forward signaling, which is reportedly involved in coordinating the orientation of cell development and migration as a guidance factor, impaired the infiltration and activation of tumor-specific CD8+ T cells in murine oral tumors. Sema6D expressed by nonhematopoietic cells was responsible for this phenotype. Plexin-A4, a receptor for Sema6D, inhibited T cell infiltration and partially suppressed CD8+ T cell activation and proliferation induced by Sema6D stimulation. Moreover, mouse oral tumors, which are resistant to PD-1-blocking treatment in wild-type mice, showed a response to the treatment in Sema6d-KO mice. Finally, analyses of public data sets of human head and neck squamous cell carcinoma, pan-cancer cohorts, and a retrospective cohort study showed that SEMA6D was mainly expressed by nonhematopoietic cells such as cancer cells, and SEMA6D expression was significantly negatively correlated with CD8A, PDCD1, IFNG, and GZMB expression. Thus, targeting Sema6D forward signaling is a promising option for increasing ICI efficacy.

Single-cell transcriptome landscape of circulating CD4+ T cell populations in autoimmune diseases.

CD4+ T cells are key mediators of various autoimmune diseases; however, their role in disease progression remains unclear due to cellular heterogeneity. Here, we evaluated CD4+ T cell subpopulations using decomposition-based transcriptome characterization and canonical clustering strategies. This approach identified 12 independent gene programs governing whole CD4+ T cell heterogeneity, which can explain the ambiguity of canonical clustering. In addition, we performed a meta-analysis using public single-cell datasets of over 1.8 million peripheral CD4+ T cells from 953 individuals by projecting cells onto the reference and cataloging cell frequency and qualitative alterations of the populations in 20 diseases. The analyses revealed that the 12 transcriptional programs were useful in characterizing each autoimmune disease and predicting its clinical status. Moreover, genetic variants associated with autoimmune diseases showed disease-specific enrichment within the 12 gene programs. The results collectively provide a landscape of single-cell transcriptomes of CD4+ T cell subpopulations involved in autoimmune disease.

Cancer-associated SNRPD3 mutation confers resistance to hypoxia, which is attenuated by DRP1 inhibition.

RNA splicing is a fundamental cellular mechanism performed by spliceosomes that synthesise multiple mature RNA isoforms from a single gene. The association between spliceosome abnormality and solid cancers remains largely unknown. Here, we demonstrated that Sm proteins, which are common components of the spliceosomes and constitute the Sm ring, were overexpressed in multiple cancers and their expression levels were correlated with clinical prognosis. In a pan-cancer mutational hotspot in the Sm ring at SNRPD3 G96V, we found that the G96V substitution confers resistance to hypoxia. RNA-seq detected numerous differentially spliced events between the wild-type and mutation-carrying cells cultured under hypoxia, wherein skipping exons and mutually exclusive exons were frequently observed. This was observed in DNM1L mRNA, which encodes the DRP1 protein that regulates mitochondrial fission. The mitochondria of cells carrying this mutation were excessively fragmented compared with those of wild-type cells. Furthermore, treatment with a DRP1 inhibitor (Mdivi-1) recovered the over-fragmented mitochondria, leading to the attenuation of hypoxia resistance in the mutant cells. These results propose a novel correlation between the cancer-related spliceosome abnormality and mitochondrial fission. Thus, targeting SNRPD3 G96V with a DRP1 inhibitor is a potential treatment strategy for cancers with spliceosome abnormalities.

GWAS for systemic sclerosis identifies six novel susceptibility loci including one in the Fcγ receptor region.

Here we report the largest Asian genome-wide association study (GWAS) for systemic sclerosis performed to date, based on data from Japanese subjects and comprising of 1428 cases and 112,599 controls. The lead SNP is in the FCGR/FCRL region, which shows a penetrating association in the Asian population, while a complete linkage disequilibrium SNP, rs10917688, is found in a cis-regulatory element for IRF8. IRF8 is also a significant locus in European GWAS for systemic sclerosis, but rs10917688 only shows an association in the presence of the risk allele of IRF8 in the Japanese population. Further analysis shows that rs10917688 is marked with H3K4me1 in primary B cells. A meta-analysis with a European GWAS detects 30 additional significant loci. Polygenic risk scores constructed with the effect sizes of the meta-analysis suggest the potential portability of genetic associations beyond populations. Prioritizing the top 5% of SNPs of IRF8 binding sites in B cells improves the fitting of the polygenic risk scores, underscoring the roles of B cells and IRF8 in the development of systemic sclerosis. The results also suggest that systemic sclerosis shares a common genetic architecture across populations.

Real-world outcomes of nivolumab plus ipilimumab and pembrolizumab with platinum-based chemotherapy in advanced non-small cell lung cancer: a multicenter retrospective comparative study.

INTRODUCTION: Nivolumab plus ipilimumab with chemotherapy (NICT) and pembrolizumab with chemotherapy (PCT) are commonly used in patients with advanced non-small cell lung cancer (NSCLC). Compared with immune checkpoint inhibitor (ICI) monotherapy, ICI combination therapy can increase immune-related toxicity instead of prolonging survival. This study aimed to compare the efficacy and safety of NICT and PCT to decide on the favorable treatment. METHODS: We conducted a multi-center retrospective cohort study on patients who underwent NICT or PCT between December 2018 and May 2022. Propensity score matching (PSM) was performed with the variables age, sex, smoking status, performance status, stage, histology, and programmed cell death ligand-1 (PD-L1). The Kaplan-Meier method was used to compare survival for the matched patients. RESULTS: Six hundred consecutive patients were included. After PSM, 81 and 162 patients were enrolled in the NICT and PCT groups, respectively. The baseline characteristics were well-balanced. The median progression-free survival was equivalent (11.6 vs. 7.4 months; P = 0.582); however, the median overall survival (OS) was significantly longer in the NICT group than in the PCT group (26.0 vs. 16.8 months; P = 0.005). Furthermore, OS was better in PD-L1-negative patients who underwent NICT than in those who underwent PCT (26.0 vs. 16.8 months; P = 0.045). Safety profiles did not differ significantly in terms of severe adverse event and treatment-related death rates (P = 0.560, and 0.722, respectively). CONCLUSIONS: Real-world data suggests that NICT could be a favorable treatment option compared with PCT for patients with advanced NSCLC. Further follow-up is needed to determine the long-term prognostic benefit.

Idiopathic pulmonary fibrosis-specific Bayesian network integrating extracellular vesicle proteome and clinical information.

Idiopathic pulmonary fibrosis (IPF) is a progressive disease characterized by severe lung fibrosis and a poor prognosis. Although the biomolecules related to IPF have been extensively studied, molecular mechanisms of the pathogenesis and their association with serum biomarkers and clinical findings have not been fully elucidated. We constructed a Bayesian network using multimodal data consisting of a proteome dataset from serum extracellular vesicles, laboratory examinations, and clinical findings from 206 patients with IPF and 36 controls. Differential protein expression analysis was also performed by edgeR and incorporated into the constructed network. We have successfully visualized the relationship between biomolecules and clinical findings with this approach. The IPF-specific network included modules associated with TGF-ß signaling (TGFB1 and LRC32), fibrosis-related (A2MG and PZP), myofibroblast and inflammation (LRP1 and ITIH4), complement-related (SAA1 and SAA2), as well as serum markers, and clinical symptoms (KL-6, SP-D and fine crackles). Notably, it identified SAA2 associated with lymphocyte counts and PSPB connected with the serum markers KL-6 and SP-D, along with fine crackles as clinical manifestations. These results contribute to the elucidation of the pathogenesis of IPF and potential therapeutic targets.

Efficacy against Lung Cancer Is Augmented by Combining Aberrantly N-Glycosylated T Cells with a Chimeric Antigen Receptor Targeting Fragile X Mental Retardation 1 Neighbor.

The adaptive transfer of T cells redirected to cancer cells via chimeric Ag receptors (CARs) has produced clinical benefits for the treatment of hematologic diseases. To extend this approach to solid cancer, we screened CARs targeting surface Ags on human lung cancer cells using (to our knowledge) novel expression cloning based on the Ag receptor-induced transcriptional activation of IL-2. Isolated CARs were directed against fragile X mental retardation 1 neighbor (FMR1NB), a cancer-testis Ag that is expressed by malignant cells and adult testicular germ cells. Anti-FMR1NB CAR human T cells demonstrated target-specific cytotoxicity and successfully controlled tumor growth in mouse xenograft models of lung cancer. Furthermore, to protect CAR T cells from immune-inhibitory molecules, which are present in the tumor microenvironment, we introduced anti-FMR1NB CARs into 2-deoxy-glucose (2DG)-treated human T cells. These cells exhibited reduced binding affinity to immune-inhibitory molecules, and the suppressive effects of these molecules were resisted through blockade of the N-glycosylation of their receptors. Anti-FMR1NB CARs in 2DG-treated human T cells augmented target-specific cytotoxicity in vitro and in vivo. Thus, our findings demonstrated the feasibility of eradicating lung cancer cells using 2DG-treated human T cells, which are able to direct tumor-specific FMR1NB via CARs and survive in the suppressive tumor microenvironment.

The role of semaphorins in allergic diseases.

Semaphorins were originally identified as guidance molecules in neural development. However, accumulating evidence indicates that 'immune semaphorins' are critically involved in regulating immune cell activation, differentiation, mobility and migration. Semaphorins are also intimately associated with the pathogenesis of allergic diseases including asthma, allergic rhinitis, atopic dermatitis, allergic conjunctivitis, and eosinophilic chronic rhinosinusitis. Interestingly, reflecting their function in positive or negative regulation of immune cells, levels of some semaphorins are increased while others are decreased in patients with allergic diseases. This review presents the pathogenic functions of immune semaphorins in allergic inflammation and discusses the potential use of these molecules as therapeutic targets for allergic diseases.

Pneumonitis During Durvalumab Consolidation Therapy Affects Survival in Stage III NSCLC.

Introduction: Durvalumab consolidation therapy is the standard of care after concurrent chemoradiotherapy (CRT) for stage III NSCLC. Immune-related pneumonitis during durvalumab treatment is potentially fatal; however, information is lacking regarding the impact of pneumonitis on patient survival. This study investigates the effect of pulmonary and nonpulmonary immune-related adverse events (irAEs) on the efficacy of durvalumab treatment in patients with stage III NSCLC. Methods: We retrospectively assessed 158 patients who received durvalumab after CRT at nine Japanese institutions between July 2018 and March 2020. Survival outcomes were compared between patients who developed pneumonitis with those who developed irAEs other than pneumonitis. Patients who survived for less than 3 months were excluded to reduce immortal time bias. Results: Among 158 evaluated patients, 76 (48%) experienced grade less than or equal to one irAEs, whereas 82 (52%) experienced grade greater than or equal to two irAEs. Among the patients with grade greater than or equal to two irAEs, those with grade greater than or equal to two pneumonitis (n = 55) were compared with those with grade greater than or equal to two irAEs other than pneumonitis (n = 27). Patients with grade greater than or equal to two pneumonitis exhibited a significantly worse overall survival than those with grade greater than or equal to two irAEs that excluded pneumonitis. Multivariate analysis revealed that grade greater than or equal to two pneumonitis (hazard ratio = 3.71; 95% confidence interval, 1.85-7.45; p < 0.001) and squamous histology (hazard ratio = 2.64; 95% confidence interval, 1.29-5.42; p = 0.008) were independently associated with worse overall survival. Conclusions: After minimizing immortal time bias, pneumonitis grade two or greater and squamous histology were poor prognostic factors in patients who received consolidation durvalumab after CRT.

Estimating gene-level false discovery probability improves eQTL statistical fine-mapping precision.

Statistical fine-mapping prioritizes putative causal variants from a large number of candidate variants, and is widely used in expression quantitative loci (eQTLs) studies. In eQTL fine-mapping, the existence of causal variants for gene expression is not guaranteed, since the genetic heritability of gene expression explained by nearby (cis-) variants is limited. Here we introduce a refined fine-mapping algorithm, named Knockoff-Finemap combination (KFc). KFc estimates the probability that the causal variant(s) exist in the cis-window of a gene through construction of knockoff genotypes (i.e. a set of synthetic genotypes that resembles the original genotypes), and uses it to adjust the posterior inclusion probabilities (PIPs). Utilizing simulated gene expression data, we show that KFc results in calibrated PIP distribution with improved precision. When applied to gene expression data of 465 genotyped samples from the Japan COVID-19 Task Force (JCTF), KFc resulted in significant enrichment of a functional score as well as reporter assay hits in the top PIP bins. When combined with functional priors derived from an external fine-mapping study (GTEx), KFc resulted in a significantly higher proportion of hematopoietic trait putative causal variants in the top PIP bins. Our work presents improvements in the precision of a major fine-mapping algorithm.

Analysis of gut microbiome, host genetics, and plasma metabolites reveals gut microbiome-host interactions in the Japanese population.

Interaction between the gut microbiome and host plays a key role in human health. Here, we perform a metagenome shotgun-sequencing-based analysis of Japanese participants to reveal associations between the gut microbiome, host genetics, and plasma metabolome. A genome-wide association study (GWAS) for microbial species (n = 524) identifies associations between the PDE1C gene locus and Bacteroides intestinalis and between TGIF2 and TGIF2-RAB5IF gene loci and Bacteroides acidifiaciens. In a microbial gene ortholog GWAS, agaE and agaS, which are related to the metabolism of carbohydrates forming the blood group A antigen, are associated with blood group A in a manner depending on the secretor status determined by the East Asian-specific FUT2 variant. A microbiome-metabolome association analysis (n = 261) identifies associations between bile acids and microbial features such as bile acid metabolism gene orthologs including bai and 7ß-hydroxysteroid dehydrogenase. Our publicly available data will be a useful resource for understanding gut microbiome-host interactions in an underrepresented population.

Single-cell multi-omics analysis identifies two distinct phenotypes of newly-onset microscopic polyangiitis.

The immunological basis of the clinical heterogeneity in autoimmune vasculitis remains poorly understood. In this study, we conduct single-cell transcriptome analyses on peripheral blood mononuclear cells (PBMCs) from newly-onset patients with microscopic polyangiitis (MPA). Increased proportions of activated CD14+ monocytes and CD14+ monocytes expressing interferon signature genes (ISGs) are distinctive features of MPA. Patient-specific analysis further classifies MPA into two groups. The MPA-MONO group is characterized by a high proportion of activated CD14+ monocytes, which persist before and after immunosuppressive therapy. These patients are clinically defined by increased monocyte ratio in the total PBMC count and have a high relapse rate. The MPA-IFN group is characterized by a high proportion of ISG+ CD14+ monocytes. These patients are clinically defined by high serum interferon-alpha concentrations and show good response to immunosuppressive therapy. Our findings identify the immunological phenotypes of MPA and provide clinical insights for personalized treatment and accurate prognostic prediction.

Secretion of mitochondrial DNA via exosomes promotes inflammation in Behçet's syndrome.

Mitochondrial DNA (mtDNA) leakage into the cytoplasm can occur when cells are exposed to noxious stimuli. Specific sensors recognize cytoplasmic mtDNA to promote cytokine production. Cytoplasmic mtDNA can also be secreted extracellularly, leading to sterile inflammation. However, the mode of secretion of mtDNA out of cells upon noxious stimuli and its relevance to human disease remain unclear. Here, we show that pyroptotic cells secrete mtDNA encapsulated within exosomes. Activation of caspase-1 leads to mtDNA leakage from the mitochondria into the cytoplasm via gasdermin-D. Caspase-1 also induces intraluminal membrane vesicle formation, allowing for cellular mtDNA to be taken up and secreted as exosomes. Encapsulation of mtDNA within exosomes promotes a strong inflammatory response that is ameliorated upon exosome biosynthesis inhibition in vivo. We further show that monocytes derived from patients with Behçet's syndrome (BS), a chronic systemic inflammatory disorder, show enhanced caspase-1 activation, leading to exosome-mediated mtDNA secretion and similar inflammation pathology as seen in BS patients. Collectively, our findings support that mtDNA-containing exosomes promote inflammation, providing new insights into the propagation and exacerbation of inflammation in human inflammatory diseases.

Automatic evaluation of atlantoaxial subluxation in rheumatoid arthritis by a deep learning model.

BACKGROUND: This work aims to develop a deep learning model, assessing atlantoaxial subluxation (AAS) in rheumatoid arthritis (RA), which can often be ambiguous in clinical practice. METHODS: We collected 4691 X-ray images of the cervical spine of the 906 patients with RA. Among these images, 3480 were used for training the deep learning model, 803 were used for validating the model during the training process, and the remaining 408 were used for testing the performance of the trained model. The two-dimensional key points' detection model of Deep High-Resolution Representation Learning for Human Pose Estimation was adopted as the base convolutional neural network model. The model inferred four coordinates to calculate the atlantodental interval (ADI) and space available for the spinal cord (SAC). Finally, these values were compared with those by clinicians to evaluate the performance of the model. RESULTS: Among the 408 cervical images for testing the performance, the trained model correctly identified the four coordinates in 99.5% of the dataset. The values of ADI and SAC were positively correlated among the model and two clinicians. The sensitivity of AAS diagnosis with ADI or SAC by the model was 0.86 and 0.97 respectively. The specificity of that was 0.57 and 0.5 respectively. CONCLUSIONS: We present the development of a deep learning model for the evaluation of cervical lesions of patients with RA. The model was demonstrably shown to be useful for quantitative evaluation.