A novel preliminary metabolomic panel for IHD diagnostics and pathogenesis

Area of Science:

• Biochemistry
• Computational Biology
• Cardiology

Background:

• Cardiovascular disease (CVD) is a leading global cause of mortality, with ischemic heart disease (IHD) accounting for a significant portion.
• Accurate and early diagnostics for IHD are crucial for effective patient management and improved outcomes.

Purpose of the Study:

• To investigate the potential of targeted metabolomic profiling combined with machine learning for diagnosing IHD.
• To identify specific plasma metabolites and metabolic pathways associated with IHD.

Main Methods:

• Quantitative analysis of 87 endogenous plasma metabolites in 112 subjects (76 IHD patients, 36 controls).
• Development of a novel age-adjustment correction method for metabolomics data.
• Application of various machine learning algorithms (logistic regression, SVM, decision trees, random forest, gradient boosting) for IHD diagnostic model development.

Main Results:

• Identified 36 significantly altered metabolites in IHD patients, including changes in amino acids, acylcarnitines, and tryptophan catabolism pathways.
• The random forest model achieved the highest diagnostic accuracy with an Area Under the Curve (AUC) of 0.98.
• Key metabolites such as Norepinephrine, Xanthurenic acid, Serotonin, and Phenylalanine were identified as significant predictors of IHD.

Conclusions:

• Targeted metabolomic profiling coupled with machine learning offers a promising approach for IHD diagnostics.
• A panel of identified metabolites may serve as a novel preliminary biomarker for IHD detection.
• Further validation studies are warranted to confirm the clinical utility of these findings.