Key result
A 15-gene immune model achieves an AUC of 0.98 for diagnosing DCM.
Why the study?
The study was conducted to construct a diagnostic model of immune-related genes during the development of heart failure caused by idiopathic dilated cardiomyopathy.
Can machine learning models based on immune-related genes accurately diagnose heart failure caused by idiopathic dilated cardiomyopathy?
Observational (n=342)
Can machine learning models based on immune-related genes accurately diagnose heart failure caused by idiopathic dilated cardiomyopathy?
Machine learning models, particularly logistic regression, based on 15 immune-related hub genes can accurately distinguish idiopathic dilated cardiomyopathy from normal cardiac tissue.
May support immune-gene signatures for DCM diagnosis; leaves open clinical translation pending prospective validation.
OBJECTIVE: The purpose of the study was to construct the potential diagnostic model of immune-related genes during the development of heart failure caused by idiopathic dilated cardiomyopathy. METHOD: GSE5406 and GSE57338 were downloaded from the GEO website ( https://www.ncbi.nlm.nih.gov/geo/ ). CIBERSORT was used for the evaluation of immune infiltration in idiopathic dilated cardiomyopathy (DCM) of GSE5406. Differently expressed genes were calculated by the limma R package and visualized by the volcano plot. The immune-related genes were downloaded from Immport, TISIDB, and InnateDB. Then the immune-related differential genes (IRDGs) were acquired from the intersection. Protein-protein interaction network (PPI) and Cytoscape were used to visualize the hub genes. Three machine learning methods such as random forest, logical regression, and elastic network regression model were adopted to construct the prediction model. The diagnostic value was also validated in GSE57338. RESULTS: Our study demonstrated the obvious different ratio of T cell CD4 memory activated, T cell regulatory Tregs, and neutrophils between DCM and control donors. As many as 2139 differential genes and 274 immune-related different genes were identified. These genes were mainly enriched in lipid and atherosclerosis, human cytomegalovirus infection, and cytokine-cytokine receptor interaction. At the same time, as many as fifteen hub genes were identified as the IRDGs (IFITM3, IFITM2, IFITM1, IFIT3, IFIT1, HLA-A, HLA-B, HLA-C, ADAR, STAT1, SAMHD1, RSAD2, MX1, ISG20, IRF2). Moreover, we also discovered that the elastic network and logistic regression models had a higher diagnostic value than that of random forest models based on these hub genes. CONCLUSION: Our study demonstrated the pivotal role of immune function during the development of heart failure caused by DCM. This study may offer new opportunities for the detection and intervention of immune-related DCM.
No takes yet. Share an insight, caveat, or question.
Xu et al. (2024) conducted an observational in Heart failure caused by idiopathic dilated cardiomyopathy (n=342). Machine learning diagnostic models (Logistic Regression, Elastic Network, Random Forest) was evaluated on Diagnostic accuracy (AUC) of the logistic regression model. A logistic regression diagnostic model based on 15 immune-related hub genes achieved high diagnostic accuracy for dilated cardiomyopathy with an AUC of 0.98.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: