January 14, 2026Molecular Biomedicine0 citationsOpen Access

Early diagnostic biomarkers for acute myocardial infarction unveiled by metabolomics, Mendelian randomization, and machine learning

HFHao FanHenan University XFXiaoya FuHenan University JLJie LiXihua University

Key Result

The study identified 10 gene biomarkers associated with acute myocardial infarction, with the Enet[alpha = 0.1] model showing optimal diagnostic performance.

Key Points

The aim is to uncover early diagnostic biomarkers for acute myocardial infarction using multi-omics techniques.
Combined metabolomics, Mendelian randomization, and transcriptomics data analysis
Profiling of plasma metabolites to identify differentially abundant ones
Use of machine learning models to evaluate diagnostic performance
Logistic regression for validating the 10 candidate gene biomarkers
Immune cell infiltration analysis with CIBERSORT algorithm
Identified 174 differentially abundant metabolites linked to AMI
Pinpointed L-arachidoyl carnitine as a key causal metabolite
Validated 10 candidate gene biomarkers associated with AMI
Optimal diagnostic performance achieved with a specific machine learning model (Enet[alpha = 0.1])
Found potential associations between candidate genes and immune cell subpopulations

Structured PICO

Does a machine learning diagnostic model based on 10 gene biomarkers improve the early diagnosis of acute myocardial infarction compared to healthy controls?

Population

Patients with acute myocardial infarction and healthy controls. The metabolomics cohort included 30 AMI patients and 30 healthy controls. Transcriptomics data was sourced from GEO datasets (GSE66360, GSE60993, GSE61144).

Intervention

Diagnostic model using 10 gene biomarkers (ACSL1, PYGL, DYSF, MGAM, SLC7A7, SULF2, KCNJ2, CYP1B1, NCF2, and SLC22A4) identified via metabolomics, Mendelian randomization, and machine learning

Comparator

Healthy controls

Outcome

Diagnostic performance (Area Under the Curve) of the machine learning model for acute myocardial infarctionsurrogate

A multi-omics approach identified 10 gene biomarkers and a key metabolite (Carnitine C20:0) that demonstrate high diagnostic accuracy for early acute myocardial infarction using machine learning models.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Acute myocardial infarction (AMI) remains a leading cause of global cardiovascular morbidity and mortality. Limitations in current diagnostic methods hinder early detection and intervention, creating an urgent need for novel early diagnostic biomarkers. This study employed an integrated multi-omics approach, combining metabolomics, Mendelian randomization (MR), and transcriptomics data to identify potential AMI biomarkers. Plasma metabolomic profiling revealed 174 differentially abundant metabolites. Subsequent MR analysis pinpointed a key causal metabolite, L-arachidoyl carnitine (carnitine C20:0). Genes associated with this metabolite were retrieved from the GeneCards database and cross-referenced with differentially expressed genes from the GEO database, leading to the identification of 10 candidate biomarker genes: ACSL1 , PYGL , DYSF , MGAM , SLC7A7 , SULF2 , KCNJ2 , CYP1B1 , NCF2 , and SLC22A4 . By constructing and evaluating 80 machine learning models, the Enetalpha = 0.1 model was determined to have the optimal diagnostic performance. The diagnostic potential of these ten genes was further corroborated by logistic regression with tenfold cross-validation. Additionally, immune cell infiltration analysis using the CIBERSORT algorithm uncovered potential associations between the candidate genes and specific immune cell subpopulations. In conclusion, this sequential multi-omics investigation successfully identifies and validates 10 gene biomarkers related to AMI, offering new perspectives for early precision diagnosis and insights into the disease’s pathogenesis, alongside potential therapeutic targets.

问 AI

Bookmark

View Full Paper