What question did this study set out to answer?

The research aims to develop a diagnostic model for hypertrophic cardiomyopathy (HCM) using untargeted plasma metabolomics and machine learning techniques.

March 9, 2026Metabolomics0 citationsOpen Access

Application of untargeted plasma metabolomics and machine learning to construct a diagnostic model for hypertrophic cardiomyopathy: a case-control study

Q: What is the clinical evidence from this study?

Study design: Case-Control. Population: Hypertrophic cardiomyopathy (n=111). Intervention: Plasma metabolite diagnostic model (KAPA, γ-linolenoyl ethanolamid, nitrilotriacetic acid, D-quinovose, NAA) vs. Healthy controls. Primary outcome: Diagnostic accuracy (AUROC) for differentiating HCM patients from normal participants (AUROC 1.000).

RLRuoxuan Li BWBo Wang 博中博之中山

Key Result

A plasma metabolite diagnostic model including KAPA, γ-linolenoyl ethanolamid, nitrilotriacetic acid, D-quinovose, and NAA accurately differentiated hypertrophic cardiomyopathy patients from healthy controls with an AUROC of 1.000 using a random forest algorithm.

Key Points

The research aims to develop a diagnostic model for hypertrophic cardiomyopathy (HCM) using untargeted plasma metabolomics and machine learning techniques.
Applied untargeted plasma metabolomics to identify key metabolites
Utilized machine learning algorithms to analyze metabolite data
Conducted a case-control study comparing HCM patients and controls
Identified several significant plasma metabolites including KAPA and NAA
Showed effective screening capabilities for HCM patients
Proposed alanine and glutamate metabolism as a potential pathogenic pathway in HCM

Study Design

Type

Case-Control (n=111)

Multicenter

Structured PICO

Does a plasma metabolite diagnostic model using machine learning accurately identify patients with hypertrophic cardiomyopathy compared to healthy controls?

Population

111 adults, including 76 with hypertrophic cardiomyopathy and 35 healthy controls, evaluated using untargeted plasma metabolomics to construct a diagnostic model.

Exposure

Untargeted plasma metabolomics combined with machine learning algorithms (Support Vector Machine [SVM] and Random Forest [RF]) to construct a diagnostic model based on 5 selected features (KAPA, γ-linolenoyl ethanolamide, nitrilotriacetic acid, D-quinovose, and NAA).

Comparator

Healthy controls without cardiovascular or metabolic disease.

Outcome

Diagnostic accuracy (AUROC and accuracy) of the machine learning models to distinguish HCM patients from normal participants in discovery and validation sets.surrogate

A machine learning diagnostic model utilizing five specific plasma metabolites demonstrated high accuracy in distinguishing patients with hypertrophic cardiomyopathy from healthy controls.

Main Result

Effect estimate: AUROC 1.000

Limitations

Relatively small cohort from a single center, which may limit generalizability
Cross-sectional design cannot establish causal relationships between metabolic alterations and HCM pathogenesis
Identified metabolites were not verified through targeted quantitative analysis
Machine learning models were developed using internal data only, requiring external validation in independent and larger cohorts

Abstract

Plasma metabolite diagnostic model including KAPA, γ-linolenoyl ethanolamid, nitrilotriacetic acid, D-quinovose and NAA can effectively and accurately screen HCM patients. Metabolomics combined with ML algorithm showed that alanine, aspartate and glutamate metabolism may be the pathogenic pathway leading to the occurrence of HCM with NAA as the central target.

问 AI

Bookmark

View Full Paper

问 AI

Bookmark

View Full Paper

Cite This Study

Li et al. (Sat,) conducted a case-control in Hypertrophic cardiomyopathy (n=111). Plasma metabolite diagnostic model (KAPA, γ-linolenoyl ethanolamid, nitrilotriacetic acid, D-quinovose, NAA) vs. Healthy controls was evaluated on Diagnostic accuracy (AUROC) for differentiating HCM patients from normal participants (AUROC 1.000). A plasma metabolite diagnostic model including KAPA, γ-linolenoyl ethanolamid, nitrilotriacetic acid, D-quinovose, and NAA accurately differentiated hypertrophic cardiomyopathy patients from healthy controls with an AUROC of 1.000 using a random forest algorithm.

synapsesocial.com/papers/69af235f3eac3accde8a172c https://doi.org/https://doi.org/10.1007/s11306-026-02412-w

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: