Applying machine learning to screen for acute myocardial infarction‐related biomarkers and immune infiltration features and validate it clinically and experimentally

Author:

Zhan Zhenrun12ORCID,Han Pengyong2,Tang Xu12,Yang Jinpeng12,Bi Xiaodan12,Zhao Tingting12ORCID

Affiliation:

1. Department of Cardiology Heping Hospital Affiliated to Changzhi Medical College Changzhi Shanxi China

2. Changzhi Medical College Changzhi Shanxi China

Abstract

AbstractAcute myocardial infarction (AMI) has been responsible for 8.5 million deaths worldwide each year over the past decade and is the leading cause of death. It is a severe illness worldwide and can happen in multiple age categories. Despite the significant progress in fundamental and clinical studies of AMI, biomarkers for AMI development have not been adequately investigated. The present research aimed to characterize potential new biomarkers of AMI by comprehensive analysis and to explore the immune infiltration characteristics of this pathophysiological process. In this study, we identified 68 DEGs and performed gene set enrichment analysis, GO, disease oncology, and KEGG analysis, and the results suggested that several functional signaling pathways and essential genes were strongly related to the onset and progression of AMI. In addition, combining multiple algorithms, FCER1G, CLEC4D, SRGN, and SLC11A1 were determined to be prospective biomarkers of AMI and showed good diagnostic value. Immuno‐infiltration analysis suggested that neutrophils, CD8+ T cells, monocytes, and M0 macrophages might be involved in the onset and progress of AMI. In conclusion, a combined approach was employed to select biomarkers associated with AMI and to probe the critical function of immune cells in the progression of AMI. In addition, clinical studies were applied to analyze the correlation between the occurrence of AMI and lipid dysregulation.

Publisher

Wiley

Subject

Electrical and Electronic Engineering,Computer Vision and Pattern Recognition,Software,Electronic, Optical and Magnetic Materials

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3