Development and Validation of a New Diagnostic Prediction Model of ENHO and NOX4 for early diagnosis of Systemic sclerosis

Leting Zheng¹ Qiulin Wu² Shuyuan Chen¹ Jing Wen¹ Fei Dong¹ Ningqin Meng¹ Wen Zeng¹ Cheng Zheng^1* Xiaoning Zhong^3*

• ¹Department of Rheumatology and Immunology, First Affiliated Hospital, Guangxi Medical University, China
• ²Department of General Surgery, The Second Affiliated Hospital of Guangxi Medical University, China
• ³Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Guangxi Medical University, China

Systemic sclerosis (SSc) is a chronic autoimmune disease characterized by fibrosis. The challenge of early diagnosis, along with the lack of effective treatments for fibrosis, contribute to poor therapeutic outcomes and high mortality of SSc. Therefore, there is an urgent need to identify suitable biomarkers for early diagnosis of SSc. In this study, we employ machine learning techniques to identify novel diagnostic biomarkers and investigate their association with immune infiltration. We conducted an analysis of the GSE130955 dataset (48 early diffuse cutaneous SSc and 33 controls) and identified 200 differentially expressed genes (DEGs) between SSc and normal skin specimens. Functional enrichment analysis revealed that these 200 DEGs may play crucial roles in the pathogenesis of SSc involving immune dysregulation, extracellular matrix remodeling, cell-cell interactions, and metabolism. Subsequently, we employed two machine-learning algorithms and identified two critical genes (ENHO and NOX4), which are implicated in the pathogenesis of SSc. The down-regulation of ENHO and the up-regulation of NOX4 were further validated in the GSE130955, GSE58095 (61 SSc and 36 controls) and GSE181549 datasets (113 SSc and 44 controls). Notably, these differential expressions were more pronounced in patients with diffuse cutaneous SSc than in those with limited cutaneous SSc. Next, the expression of ENHO and NOX4 were validated in our own SSc cohort using RT-qPCR.  More importantly, we developed a novel diagnostic model for SSc using ENHO and NOX4, which demonstrated strong predictive power in above three cohorts and in our own cohort. Furthermore, a negative correlation was observed between the levels of ENHO and Macrophages M1 and M2, while a positive correlation was observed between the levels of NOX4 and Macrophages M1 and M2. Collectively, this study employed LASSO and SVM analysis to identify ENHO and NOX4 as novel biomarkers, serving as a diagnostic prediction model for early detection of SSc. Additionally, these findings suggest that ENHO and NOX4 may contribute to the progression of SSc by regulating macrophage polarization. Overall, this study provides valuable insights into the role of ENHO and NOX4 in the early diagnosis and risk prediction of SSc, and their potential role in the pathogenesis of SSc.