ImmunoTargets and Therapy最新文献

{"title":"Precision Medicine in Asthma: The Role of Biomarkers.","authors":"Eleanor Quek, Neve Horn, Salman Siddiqui","doi":"10.2147/ITT.S532291","DOIUrl":"10.2147/ITT.S532291","url":null,"abstract":"<p><p>Asthma represents a profoundly heterogeneous syndrome underpinned by multiple, distinct and overlapping immunopathological mechanisms. Nevertheless, prevailing management algorithms continue to adopt a largely uniform, stepwise approach in which pharmacotherapy is intensified only after clinical deterioration or recurrent exacerbations. Although the advent of targeted biologic agents has improved outcomes in severe asthma, the realisation of precision medicine - therapeutic selection directed by individual disease mechanisms - remains elusive. This is primarily attributable to the limited availability of validated biomarkers capable of defining endotypes and accurately predicting therapeutic responsiveness. Existing indicators of type-2 (T2) inflammation, including blood eosinophil counts, fractional exhaled nitric oxide, and serum Immunoglobulin E, provide only partial discrimination between T2 subtypes and are insufficient to guide the choice of specific T2-targeted biologics. Furthermore, robust non-T2 biomarkers are notably lacking. This review provides a critical appraisal of current biomarker paradigms and examines emerging molecular and cellular candidates with potential to enable precise endotyping. Integration of such biomarkers into early disease assessment offers the prospect of delivering truly individualised therapy, ensuring that appropriate treatment is instituted for the right patient at the optimal time.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1479-1513"},"PeriodicalIF":4.4,"publicationDate":"2025-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12756974/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145901175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inhibitors of KAT2A Alleviate the Progression of AKI by Alleviating Macrophage Ferritinophagy.","authors":"Zhenying Zuo, Shenglan Gao, Jinzheng Wang, Zhongyu Liu, Zhiliang Lu, Hongluan Wu, Xiaorong Huang, Chen Yang, Jiaxuan Chen, Huafeng Liu, Qingjun Pan, Lawei Yang","doi":"10.2147/ITT.S568586","DOIUrl":"10.2147/ITT.S568586","url":null,"abstract":"<p><strong>Background: </strong>Acute kidney injury (AKI) involves complex inflammatory responses in which macrophage dysfunction plays a central role. Although histone acetyltransferase KAT2A has been implicated in immune regulation, its role in macrophage ferritinophagy during AKI remains unclear.</p><p><strong>Methods: </strong>Single-cell RNA sequencing analysis of mouse kidney tissue identified abnormal activation of ferritinophagy and upregulation of KAT2A in renal macrophage during AKI progression. Colocalization of FTH1 and LAMP1 and the increased fluorescence intensity of FTH1 and NCOA4 proteins, and KAT2A proteins in macrophage of kidney in AKI samples were detected via immunofluorescence staining. Functional impacts of KAT2A on macrophage ferritinophagy were assessed using KAT2A knockdown and overexpression plasmids in RAW264.7 cell lines. Butyrolactone 3 (MB-3), a specific KAT2A inhibitor, was administered via intraperitoneal injection 24 hours post-IR to assess the influence of MB-3 on renal pathological changes and the activity of macrophage ferritinophagy.</p><p><strong>Results: </strong>In this study, using single-cell RNA sequencing and dual immunofluorescence, we observed aberrant ferritinophagy in renal macrophages, marked by increased colocalization of FTH1 with LAMP1 and NCOA4, alongside elevated CD68 expression. KAT2A was upregulated in macrophages from both human AKI biopsies and murine models. Genetic knockdown of KAT2A suppressed ferritinophagy, reduced NCOA4 and FTH1 expression, decreased FTH1-LAMP1 colocalization, and inhibited cGAS signaling. Conversely, KAT2A overexpression exacerbated these processes. Critically, NCOA4 silencing abolished KAT2A-driven ferritinophagy and cGAS-STING activation. Pharmacological inhibition of KAT2A with MB-3 significantly attenuated renal injury, macrophage infiltration, and ferritinophagy, and reduced colocalization of KAT2A or NCOA4 with F4/80.</p><p><strong>Conclusion: </strong>These findings demonstrate that KAT2A promotes AKI progression via NCOA4-mediated ferritinophagy and cGAS-STING inflammatory signaling in macrophages, highlighting KAT2A inhibition as a promising therapeutic strategy for AKI.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1515-1529"},"PeriodicalIF":4.4,"publicationDate":"2025-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12750145/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145879263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Immune-Related Adverse Events of Checkpoint Inhibitors and Human Leukocyte Antigen System: A Review.","authors":"Kamil Kośmider, Agata Kozakiewicz, Paweł Krawczyk, Robert Kieszko, Katarzyna Szklener, Magdalena Skórzewska, Kamila Wojas-Krawczyk, Ewa Kalinka, Janusz Milanowski","doi":"10.2147/ITT.S548443","DOIUrl":"10.2147/ITT.S548443","url":null,"abstract":"<p><p>The introduction of immune checkpoint inhibitors (ICIs) in the treatment of cancer has significantly improved patient outcomes. Whereas ICIs have a substantially more beneficial risk profile than chemotherapy, immune-related adverse events (irAEs) are currently among the most pressing challenges of clinical oncology. It has been well established that certain variants of <i>HLA</i> genes are associated with increased susceptibility or a decreased risk of certain autoimmune diseases. Considering that irAEs often resemble autoimmune disorders observed in the general population, we conducted the first review summarizing the current knowledge on the link between the HLA system and the development of irAEs during ICIs treatment. We performed a comprehensive search of the US National Library of Medicine (PubMed) database. Based on the research conducted so far, our analysis indicates that certain <i>HLA</i> variants have been described to increase or, conversely, decrease the risk of irAEs. Thus, <i>HLA</i> genotyping may be useful in stratifying the risk of irAEs, allowing for more thorough screening of patients with a higher likelihood of developing ICI-related toxicities and less frequent monitoring of those at lower risk, thereby significantly reducing costs and the overall burden of disease. <i>HLA</i> genotyping may ultimately contribute to the personalization of cancer therapy, significantly improving patient safety and clinical efficacy. Furthermore, identifying an association between certain <i>HLA</i> variants and irAEs may lead to a better understanding of the pathogenesis underlying these adverse effects. Nevertheless, the studies conducted so far have included limited cohorts of patients with a wide variety of malignancies and diverse treatment regimens. Hence, further research that addresses these limitations is needed.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1455-1478"},"PeriodicalIF":4.4,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12724206/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145828648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrative Spatial Transcriptomics and Experimental Validation Reveal UBC-Mediated EMT Associated with Immune Evasion in Hepatocellular Carcinoma.","authors":"Xiaosong Li, Xian Qin, Kezhi Shi, Guangrui Lu, Guodong Tian, Yue Chen, Rucheng Yao","doi":"10.2147/ITT.S567643","DOIUrl":"10.2147/ITT.S567643","url":null,"abstract":"<p><strong>Background: </strong>Hepatocellular carcinoma (HCC) exhibits pronounced spatial heterogeneity that limits therapeutic efficacy. The contribution of epithelial-mesenchymal transition (EMT) to regional tumor progression and immune evasion remains incompletely understood.</p><p><strong>Methods: </strong>We integrated bulk transcriptomic datasets (TCGA, GSE14520), 34 single-cell RNA-seq samples, and 15 spatial transcriptomic datasets to delineate EMT activity across distinct HCC regions. Immune infiltration profiling, pathway enrichment, and multi-model machine learning were used to identify candidate EMT regulators. Functional validation was performed in Hep3B cells through wound healing, Transwell migration/invasion, and immunofluorescence assays.</p><p><strong>Results: </strong>EMT activity was significantly elevated at tumor margins (fold change = 2.7, p < 0.001) and was associated with poorer overall survival (HR = 2.15, 95% CI: 1.41-3.27, p < 0.001). Regions with high EMT signatures showed reduced CD8⁺ T-cell infiltration and increased immunosuppressive cells, including MDSCs, M2 macrophages, and Tregs, along with elevated expression of immune checkpoints (PDCD1, CTLA4, LAG3). Among candidate regulators, UBC was consistently ranked as a top EMT-associated gene across all models. Functional assays confirmed that UBC overexpression enhanced migration, invasion, and vimentin expression, whereas UBC knockdown reversed these effects.</p><p><strong>Conclusion: </strong>Through integrative spatial multi-omics and experimental validation, we identify UBC as a key mediator of EMT and immune suppression at HCC margins. These findings provide mechanistic insight into spatial heterogeneity and suggest that targeting UBC could have translational potential for overcoming immune evasion in HCC.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1437-1454"},"PeriodicalIF":4.4,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12724235/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145828658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Novel Anti-Siglec-15 Antibody for Tumor Immunotherapy.","authors":"Qin Liu, Lin Li, Siji Nian, Xiaoke Sun, Xiyuan Guo, Chengwen Li, Zhihui Yang, Yingchun Ye, Qing Yuan","doi":"10.2147/ITT.S536009","DOIUrl":"10.2147/ITT.S536009","url":null,"abstract":"<p><strong>Purpose: </strong>As a novel candidate in cancer immunotherapy, siglec-15-targeting antibodies hold promise for providing alternative therapeutic strategies to tumors unresponsive to programmed death ligand 1 (PD-L1) antibody therapy. To date, pharmacological development targeting siglec-15 has not yet achieved significant breakthroughs or clinical approval. Therefore, this study aims to develop a novel anti-siglec-15 antibody designed to restore tumor immune normalization.</p><p><strong>Methods: </strong>In this study, we constructed a phage immune library derived from lymphoid tissues of lung cancer patients using phage display technology and screened the fully human antibodies against siglec-15 antigen from this library. The antibody affinity was detected by Bio-Layer Interferometry, the binding rate of antibody to positively expressing siglec-15 tumor cells was examined by flow cytometry, and the activity of antibody-mediated killer cells against tumor cells was reflected by Antibody-Dependent Cellular Cytotoxicity (ADCC) action. The blockage of proliferation inhibition caused by siglec-15 antigen by antibodies was investigated by t-lymphocyte proliferation assays, and CD8⁺ T cells were collected from malignant pleural effusion specimens derived from lung cancer patients to determinewhether antibodies could alleviate the immunosuppression present in the tumor microenvironment (TME). The anti-tumor efficacy of the antibody was investigated in vivo by constructing a zebrafish tumor model and a humanized mouse tumor model.</p><p><strong>Results: </strong>The antibody demonstrated nanomolar affinity and specificity, enhanced antibody-dependent cellular cytotoxicity (ADCC) against tumor cells, reversed T-cell suppression, and reduced CD8⁺ T-cell exhaustion in vitro analyses. In vivo models confirmed tumor growth inhibition via increased lymphocyte infiltration and activation.</p><p><strong>Conclusion: </strong>Antibody immune libraries from lymphoid tissues of lung cancer patients can screen specific antibodies against siglec-15 target antigens and exert certain biological functions in vitro and in vivo.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1419-1435"},"PeriodicalIF":4.4,"publicationDate":"2025-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12704181/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145768863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Durable Tumor Control with Multi-Organ Immune-Related Adverse Events Following Immune Checkpoint Inhibitor and Sequential Radiotherapy in Locally Advanced NSCLC: A Case Report.","authors":"Menglan Zhai, Xianwen Liu, Ying Li, Guoliang Pi, Jianping Bi, Guang Han","doi":"10.2147/ITT.S559801","DOIUrl":"10.2147/ITT.S559801","url":null,"abstract":"<p><p>Combining radiotherapy (RT) with immune checkpoint inhibitors (ICIs) improves survival in stage III non-small cell lung cancer (NSCLC), though immune-related adverse events (irAEs) require vigilant management. Emerging evidence suggests multi-organ irAEs may correlate with favorable outcomes. We report a case of unresectable stage IIIA NSCLC achieving sustained partial response (PR) with progression-free survival (PFS) exceeding 42 months after one cycle of pembrolizumab-chemotherapy followed by sequential thoracic RT (50 Gy/25 fractions). Severe multi-organ irAEs (muscular, cardiovascular, respiratory, hematologic) developed but were effectively managed with corticosteroid-based therapy. Remarkably, durable tumor control persisted despite suboptimal therapeutic dosing and early systemic treatment discontinuation. This case demonstrates that RT-ICI synergy can induce robust systemic antitumor immunity even with dose-reduced RT, while severe multi-system irAEs may signal favorable prognosis. These findings support optimizing RT parameters (eg, dose de-escalation, target volume refinement) as a viable approach in the immunotherapy era.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1411-1417"},"PeriodicalIF":4.4,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12703373/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145768946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Critical Role of DC-SIGN⁺ Tumor-Associated Macrophages in Colorectal Cancer Immune Evasion and Progression via BCL-3-Mediated PD-L1 Expression.","authors":"Jianfeng Zhang, Yifan Zhao, Xingchao Wang, Chuang Miao, Wangcheng Xu, Chunhua Wan, Baoying Hu, Fei Qian","doi":"10.2147/ITT.S562182","DOIUrl":"10.2147/ITT.S562182","url":null,"abstract":"<p><strong>Background: </strong>Tumor-associated macrophages (TAMs) play a pivotal role in facilitating tumor immune escape in colorectal cancer (CRC). C-type lectin Dendritic Cell-Specific ICAM-Grabbing Nonintegrin (DC-SIGN) is variably expressed in TAMs in tumor tissues. However, its role in CRC progression remains poorly defined.</p><p><strong>Methods: </strong>We analyzed The Cancer Genome Atlas (TCGA) data and an independent CRC cohort to evaluate the prognostic significance of DC-SIGN^high TAMs. Immunofluorescence and flow cytometry were used to characterize DC-SIGN expression in CRC tissues. RNA sequencing and bioinformatics analyses were performed on sorted DC-SIGN^high and DC-SIGN^low TAMs. Functional assays using THP-1-derived macrophages and primary TAMs were conducted to examine how DC-SIGN regulates PD-L1 expression via the transcription factor BCL-3.</p><p><strong>Results: </strong>DC-SIGN was specifically expressed in TAMs within CRC tissues and was associated with increased stromal and immune cell infiltration. DC-SIGN expression correlated with worsened prognosis in CD8^high, but not CD8^low, patients with CRC across two independent cohorts, and served as an independent predictor of unfavorable survival in CD8^high CRC. Transcriptomic profiling revealed that DC-SIGN^high TAMs exhibited distinct immune-related pathways, including marked upregulation of PD-L1 and PD-L1 immune checkpoint pathway. Mechanistically, Lewis^x-ligated DC-SIGN upregulated PD-L1 expression at both mRNA and protein levels through BCL-3, which directly bound to the PD-L1 promoter.</p><p><strong>Conclusion: </strong>The DC-SIGN/BCL-3 axis in TAMs drives PD-L1 expression and contributes to CRC immune evasion. Targeting DC-SIGN⁺ TAMs may represent a promising therapeutic strategy to reprogram the tumor microenvironment (TME) and improve the efficacy of immunotherapy in CRC.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1395-1410"},"PeriodicalIF":4.4,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12702786/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145769519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neutrophil Extracellular Traps in Sepsis and Sepsis-Related Organ Dysfunction.","authors":"Wenbo Yan, Xiyuan Xu, Xiaojuan Li, Yushu Ma, Lining Guo, Jingping Yang, Zhipeng Jin, Jie Zhang, Tiewei Li","doi":"10.2147/ITT.S569962","DOIUrl":"10.2147/ITT.S569962","url":null,"abstract":"<p><p>Sepsis is a systemic inflammatory response triggered by infection, which can result in multiple organ dysfunctions, including disseminated intravascular coagulation (DIC) and acute lung injury (ALI), ultimately leading to patient mortality. The pathophysiology of sepsis is intricate, involving excessive immune activation, cytokine storms, endothelial damage, and microcirculatory dysfunction. Dysregulated host responses frequently give rise to severe complications, markedly elevating mortality rates. Neutrophil extracellular traps (NETs) are web-like structures consisting of DNA, histones, and granular proteins, released by neutrophils upon activation. Ongoing research into NETs has uncovered their significant pathophysiological roles in clinical conditions, including sepsis. This review outlines the mechanisms of NET formation, release, classification, detection methods, and relevant biomarkers. Additionally, it delves into the signaling pathways involved in NET generation, their pathophysiological implications in sepsis and its complications, and evaluates their potential utility in clinical laboratory diagnostics.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1373-1393"},"PeriodicalIF":4.4,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12667721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145662192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Role of Intestinal Microbiota and Immune System Interactions in Autoimmune Diseases.","authors":"Batuhan Yurtseven, Esra Aydemir, Furkan Ayaz","doi":"10.2147/ITT.S569016","DOIUrl":"10.2147/ITT.S569016","url":null,"abstract":"<p><strong>Background: </strong>The intricate interplay between the intestinal microbiota and the immune system has emerged as a central theme in understanding autoimmune disease pathogenesis. This review comprehensively explores the role of gut microbiota in shaping immune development, establishing immune tolerance, and contributing to both local and systemic immune regulation.</p><p><strong>Methods: </strong>This review synthesizes the modulatory effects of microbial metabolites (eg, short-chain fatty acids and indole derivatives) on regulatory T cells (Tregs) and inflammatory pathways. The concept of \"dysbiosis\" is examined from functional and compositional perspectives, linking microbial imbalances to autoimmune disorders (IBD, MS, RA, and T1D). Microbiota-targeted therapeutic interventions (probiotics, prebiotics, FMT) are also evaluated.</p><p><strong>Key findings: </strong>The synthesis of the literature confirms that microbial metabolites have a direct impact on Treg differentiation and inflammatory pathways. Dysbiosis, through functional and compositional disruptions, is strongly associated with the pathogenesis of various autoimmune disorders, including Inflammatory Bowel Disease, Multiple Sclerosis, Rheumatoid Arthritis, and Type 1 Diabetes. Therapeutic interventions such as probiotics, prebiotics, and Fecal Microbiota Transplantation show promising potential in restoring microbial and immune homeostasis.</p><p><strong>Conclusion: </strong>This review highlights the role of the gut-immune axis in autoimmune diseases. Despite current challenges, such as individual variability and determining causality, future directions toward precision microbiota and immune modulation are promising. This study provides a robust foundation for researchers and clinicians seeking to understand and therapeutically target the gut-immune axis.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1347-1372"},"PeriodicalIF":4.4,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12666415/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145662131","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Classification of Rheumatoid Arthritis in Hand Radiographs Interpretability Insights and Web Application.","authors":"Kanglin Cai, Dengfeng Dou, Guibing Deng, Yunzhen Zhan, Huilian Huang, Zhitao Feng","doi":"10.2147/ITT.S547159","DOIUrl":"10.2147/ITT.S547159","url":null,"abstract":"<p><strong>Purpose: </strong>To establish an interpretable deep learning framework for automated classification of rheumatoid arthritis (RA) in hand radiographs, with emphasis on elucidating model decision-making patterns and enabling clinical translation through web-based deployment.</p><p><strong>Patients and methods: </strong>A retrospective multicenter study analyzed 1,655 hand radiographs (809 RA patients, including early RA cases, and 846 healthy controls). Enhanced data (random rotation, brightness/contrast adjustment) was applied to the collected X-ray images to improve the model's generalization ability and performance. Subsequently, A lightweight Visual Geometry Group (VGG)-8 convolutional neural network was trained and validated using processed hand X-ray images. This model has the ability to distinguish RA patients from healthy controls. The interpretability of the model was systematically evaluated using both Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP). Finally, a web application was developed using Streamlit that supports JPEG input, helps to address the clinical practicality of the model.</p><p><strong>Results: </strong>For distinguishing RA patients from healthy individuals, the classifier achieved excellent training performance (AUC=0.99, accuracy=0.94) and generalizable testing metrics (AUC=0.81, accuracy=0.74). Specifically, the model was successfully constructed and demonstrated good performance in external validation. Interpretability analysis revealed areas of pathological significance, with Grad CAM heatmaps highlighting structural abnormalities (joint space stenosis, bone erosion, trabecular structural changes), and SHAP values analysis identifying metacarpophalangeal and wrist joints as key predictive features. A web application developed using Python and Streamlit framework can assist in the diagnosis of RA hand X-ray images in clinical practice.</p><p><strong>Conclusion: </strong>This work advances clinical diagnosis, including early RA patients, by integrating deep learning with interpretable decision paths in hand radiographic analysis, while helping clinicians to use the model more proficiently. The framework provides both diagnostic assistance and educational insights into RA radiographic markers.</p>","PeriodicalId":30986,"journal":{"name":"ImmunoTargets and Therapy","volume":"14 ","pages":"1333-1345"},"PeriodicalIF":4.4,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12640576/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145597489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}