Abstract
The metabolic derangement is common in heart failure with reduced ejection fraction (HFrEF). The aim of the study was to check feasibility of the combined approach of untargeted metabolomics and machine learning to create a simple and potentially clinically useful diagnostic panel for HFrEF. The study included 67 chronic HFrEF patients (left ventricular ejection fraction-LVEF 24.3 ± 5.9%) and 39 controls without the disease. Fasting serum samples were fingerprinted by liquid chromatography-mass spectrometry. Feature selection based on random-forest models fitted to resampled data and followed by linear modelling, resulted in selection of eight metabolites (uric acid, two isomers of LPC 18:2, LPC 20:1, deoxycholic acid, docosahexaenoic acid and one unknown metabolite), demonstrating their predictive value in HFrEF. The accuracy of a model based on metabolites panel was comparable to BNP (0.85 vs 0.82), as verified on the test set. Selected metabolites correlated with clinical, echocardiographic and functional parameters. The combination of two innovative tools (metabolomics and machine-learning methods), both unrestrained by the gaps in the current knowledge, enables identification of a novel diagnostic panel. Its diagnostic value seems to be comparable to BNP. Large scale, multi-center studies using validated targeted methods are crucial to confirm clinical utility of proposed markers.
Highlights
The metabolic derangement is common in heart failure with reduced ejection fraction (HFrEF)
67 patients with chronic heart failure with reduced ejection fraction (HFrEF) and 39 age, ischemic heart disease (IHD) occurrence- and body mass index (BMI)-matched controls were enrolled in the study
Among assessed laboratory parameters higher concentration of uric acid (6.8 mg/dL interquartile range (IQR) 6.0–7.9 mg/dL vs 5.99 mg/dL IQR 5.1–7.0 mg/dL, p = 0.029) and lower total cholesterol (167.5 ± 42 mmo/L vs 197.2 ± 35 mg/dL, p = 0.001), HDL (46.5 ± 14.1 mmol/L vs 53.3 ± 14.3 mmol/L, p = 0.029), LDL (101.9 ± 32.7 mmol/L vs 127.0 ± 39.2 mmol/L, p = 0.001) levels were observed in HFrEF patients
Summary
The metabolic derangement is common in heart failure with reduced ejection fraction (HFrEF). The aim of the study was to check feasibility of the combined approach of untargeted metabolomics and machine learning to create a simple and potentially clinically useful diagnostic panel for HFrEF. Untargeted metabolomics analysis enables comprehensive characterization of low molecular weight metabolites reflecting the complete metabolic phenotype of the disease. ML, by having different motivating philosophies (data-driven models) and by not being limited by current knowledge (no need for a pre-specification of a model structure), seems to be a powerful tool to improve diagnostic and prognostic processes in various diseases[4,5,6,7]. The aim of the study was to detect in peripheral blood possibly all low molecular weight metabolites which differentiate HFrEF patients from controls with further creation of the top performing diagnostic panel using ML algorithms
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
