Identification of signature genes and subtypes for heart failure diagnosis based on machine learning

Yanlong Zhang Yanming Fan Fei Cheng Dan Chen Hualong Zhang ^*

• Xingtai City People's Hospital, Xingtai, China

Background: Heart failure (HF) is a multifaceted clinical condition, and our comprehension of its genetic pathogenesis continues to be significantly restricted.Consequently, identifying specific genes for HF at the transcriptomic level may enhance early detection and allow for more targeted therapies for these individuals.Methods: HF datasets were acquired from the GEO database (GSE57338), and through the application of bioinformatics and machine learning algorithms. we identified four candidate genes (FCN3, MNS1, SMOC2, and FREM1) that may serve as potential diagnostics for HF. Futher validated the diagnostic value of these genes on additional GEO datasets (GSE21610 and GSE76701). Additionally, we assessed the different subtypes of heart failure through unsupervised clustering, and investigations were conducted on the differences in the immunological microenvironment, improved functions, and pathways among these subtypes. Finally, a comprehensive analysis of the expression profile, prognostic value, and genetic and epigenetic alterations of four potential diagnostic candidate genes was performed based on the TCGA database in pan-cancer.Results: A total of 295 differential genes were identified in the HF dataset, and intersected with the blue module gene with the highest correlation to HF identified by WGCNA analysis (r= 0.72, p=1.3e-43), resulting in a total of 114 key HF genes.Further based on RF, LASSO and SVM algorithms, we have finally identified four Hub genes (FCN3, FREM1, MNS1 and SMOC2) and had good potential for diagnosis in HF (AUC > 0.7). Meanwhile, three subgroups for HF patients were identified, compared with C1 and C2 groups, we eventually identified C3 as an immune subtype. Moreover, the pan-cancer study revealed that these four genes are closely associated with tumor development.Conclusions: Our research identified four unique genes (FCN3, FREM1, MNS1, SMOC2), enhancing our comprehension of the causes of HF. This provides new diagnostic insights and potentially establishes a tailored approach for individualized HF treatment.