Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Enhanced co-expression of TIGIT and PD-1 on γδ T cells correlates with clinical features and laboratory parameters in patients with primary Sjögren's syndrome

OBJECTIVES

The research aimed to assess the proportions of Gamma delta (γδ) T cells and the expression levels of CD226, ICOS, CD40L, OX40, TIGIT, LAG-3, Tim-3, and PD-1 on γδ T cells in the peripheral blood of patients diagnosed with primary Sjögren's syndrome (pSS), and to evaluate the clinical significance of these findings.

METHODS

Utilizing flow cytometry, we investigated the proportion of γδ T cells and the expression of CD226, ICOS, CD40L, OX40, TIGIT, LAG-3, PD-1, and Tim-3 on γδ T cells in 37 patients diagnosed with pSS and 28 healthy controls (HC). Moreover, we explored the potential associations between the proportion of γδ T cells, TIGIT + γδ T cells, PD-1 + γδ T cells, and TIGIT + PD-1 + γδ T cells with clinical symptoms and laboratory parameters.

RESULTS

Compared to HC, patients with pSS showed a decreased proportion of γδ T cells, alongside an increased proportion of TIGIT + γδ T cells, PD-1 + γδ T cells, and TIGIT + PD-1 + γδ T cells (p < 0.01). Nevertheless, there were no statistically significant variations noted in the expression levels of CD226, ICOS, CD40L, Tim-3, LAG-3, and OX40 on γδ T cells between two groups (p > 0.05). Furthermore, γδ T cells demonstrated a declining trend in patients with clinical symptoms such as xerostomia, xerophthalmia, decayed teeth, and fatigue, as well as in those with high IgG levels and positivity for anti-SSB/La, anti-SSA/Ro60, and anti-SSA/Ro52. Conversely, TIGIT + γδ T cells, PD-1 + γδ T cells, and TIGIT + PD-1 + γδ T cells exhibited an increasing trend in these patient groups. In correlation analyses with IgG, ESR, CRP, C3, C4, IgA, RF, IgM, and ESSDAI, γδ T cells were observed to have a negative correlation with ESR, IgG and ESSDAI. TIGIT + γδ T cells demonstrated significant positive correlations with IgG, IgA, and ESSDAI. PD-1 + γδ T cells showed positive correlations with ESR, CRP, IgA, and ESSDAI. Furthermore, TIGIT + PD-1 + γδ T cells showed significant positive correlations with ESR, IgG, RF, IgA, and ESSDAI.

CONCLUSION

Our results indicated that patients with pSS exhibited a reduction in γδ T cells alongside elevated expression of TIGIT, PD-1, and their co-expression on γδ T cells. These changes were found to correlate with clinical symptoms and laboratory parameters, suggesting that γδ T cells, TIGIT + γδ T cells, PD-1 + γδ T cells, and especially TIGIT + PD-1 + γδ T cells could potentially serve as diagnostic biomarkers for pSS.

JAK1, SKI, ZBTB16 as potential biomarkers mediate the inflammatory response in keratoconjunctivitis sicca

Keratoconjunctivitis sicca (KCS) is an ocular condition characterized by insufficient tear production and inflammatory irritation, with Sjögren's syndrome (SS) being a major causative factor. This study aimed to extract patient transcriptomic data from the GEO database to identify signature genes associated with the diagnosis and treatment of KCS and the expression of three key genes were experimentally verified. We performed a difference analysis on the SS patient dataset and performed a Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis on the resulting genes. Additionally, a Weighted Gene Co-expression Network Analysis (WGCNA) was constructed. Machine learning techniques were employed to analyze the most strongly correlated gene modules with SS traits. These findings were further validated using KCS immune-correlation microarrays as a validation set. The correlation of the three identified genes with 22 immune cells was assessed through immune infiltration analysis. Subsequently, a rat model of desiccated keratoconjunctivitis was established, and the modeling situation and expression of characteristic genes were analyzed at the morphological, tissue, and molecular levels. Bioinformatic prediction revealed that the expression of JAK1, SKI, ZBTB16 not only differed in the machine learning validation set, but also correlated with some immune cells in the immune infiltration analysis. The results of animal experiments showed that the transcription and expression levels of these three genes were significantly different in rat KCS tissues and normal tissues, and there were also differences in the expression of JAK1 and SKI in rat peripheral blood, as well as significant up-regulation of the expression of related inflammatory factors in KCS tissues. Through bioinformatics prediction and animal experimental validation, this study identified three differentially expressed genes in SS mediated KCS patients, which provide new potential biological targets for the diagnosis and treatment of KCS.

Unveiling Artificial Intelligence's Power: Precision, Personalization, and Progress in Rheumatology

This review examines the increasing use of artificial intelligence (AI) in rheumatology, focusing on its potential impact in key areas. AI, including machine learning (ML) and deep learning (DL), is revolutionizing diagnosis, treatment personalization, and prognosis prediction in rheumatologic diseases. Specifically, AI models based on convolutional neural networks (CNNs) demonstrate significant efficacy in analyzing medical images for disease classification and severity assessment. Predictive AI models also have the ability to forecast disease trajectories and treatment responses, enabling more informed clinical decisions. The role of wearable devices and mobile applications in continuous disease monitoring is discussed, although their effectiveness varies across studies. Despite existing challenges, such as data privacy concerns and issues of model generalizability, the compelling results highlight the transformative potential of AI in rheumatologic disease management. As AI technologies continue to evolve, further research will be essential to address these challenges and fully harness the potential of AI to improve patient outcomes in rheumatology.

Novel multiclass classification machine learning approach for the early-stage classification of systemic autoimmune rheumatic diseases

OBJECTIVE

Systemic autoimmune rheumatic diseases (SARDs) encompass a diverse group of complex conditions with overlapping clinical features, making accurate diagnosis challenging. This study aims to develop a multiclass machine learning (ML) model for early-stage SARDs classification using accessible laboratory indicators.

METHODS

A total of 925 SARDs patients were included, categorised into SLE, Sjögren's syndrome (SS) and inflammatory myositis (IM). Clinical characteristics and laboratory markers were collected and nine key indicators, including anti-dsDNA, anti-SS-A60, anti-Sm/nRNP, antichromatin, anti-dsDNA (indirect immunofluorescence assay), haemoglobin (Hb), platelet, neutrophil percentage and cytoplasmic patterns (AC-19, AC-20), were selected for model building. Various ML algorithms were used to construct a tripartite classification ML model.

RESULTS

Patients were divided into two cohorts, cohort 1 was used to construct a tripartite classification model. Among models assessed, the random forest (RF) model demonstrated superior performance in distinguishing SLE, IM and SS (with area under curve=0.953, 0.903 and 0.836; accuracy= 0.892, 0.869 and 0.857; sensitivity= 0.890, 0.868 and 0.795; specificity= 0.910, 0.836 and 0.748; positive predictive value=0.922, 0.727 and 0.663; and negative predictive value= 0.854, 0.915 and 0.879). The RF model excelled in classifying SLE (precision=0.930, recall=0.985, F1 score=0.957). For IM and SS, RF model outcomes were (precision=0.793, 0.950; recall=0.920, 0.679; F1 score=0.852, 0.792). Cohort 2 served as an external validation set, achieving an overall accuracy of 87.3%. Individual classification performances for SLE, SS and IM were excellent, with precision, recall and F1 scores specified. SHAP analysis highlighted significant contributions from antibody profiles.

CONCLUSION

This pioneering multiclass ML model, using basic laboratory indicators, enhances clinical feasibility and demonstrates promising potential for SARDs classification. The collaboration of clinical expertise and ML offers a nuanced approach to SARDs classification, with potential for enhanced patient care.