Key result
Plasma lipid profiling combined with machine learning classifiers accurately distinguished patients with cardiovascular disease, ischemic stroke, and systemic lupus erythematosus from healthy controls, achieving sensitivities of 0.90-1.0 and specificities of 0.88-1.0.
Why the study?
Deep plasma lipid profiles of major chronic inflammatory diseases had not been compared to determine whether they reflect disease-specific inflammation.
Does shotgun mass spectrometry-based plasma lipid profiling accurately distinguish between chronic inflammatory diseases (CVD, IS, SLE) and healthy controls?
Case-Control (n=427)
No
Does shotgun mass spectrometry-based plasma lipid profiling accurately distinguish between chronic inflammatory diseases (CVD, IS, SLE) and healthy controls?
Plasma lipidomics profiling using shotgun mass spectrometry can accurately distinguish between chronic inflammatory diseases (CVD, ischemic stroke, SLE) and healthy controls, highlighting its potential as a diagnostic biomarker tool.
Lipidomic ML classifiers may aid inflammatory disease diagnosis; leaves open clinical utility pending prospective validation.
Background Inflammation impacts several acute and chronic diseases causing localized stress and cell death, releasing tissue-specific lipids into the circulation from inflamed cells and tissues. The plasma lipidome may be expected to reflect the type of inflammation and the specific cells and tissues involved. However, deep lipid profiles of major chronic inflammatory diseases have not been compared. Methods We compare the plasma lipidomes of patients suffering from two etiologically distinct chronic inflammatory diseases, atherosclerosis-related cardiovascular disease (CVD) including ischemic stroke (IS), and systemic lupus erythematosus (SLE), to each other and to age-matched controls. The controls had never suffered from any of these diseases. Blood plasma lipidomes were screened by a top-down shotgun MS-based analysis without liquid chromatographic separation. Lipid profiling based on MS was performed on a cohort of 427 individuals. The cohort constitutes 85 controls (control), 217 with cardiovascular disease (further classified into CVD 1-5), 21 ischemic stroke patients (IS), and 104 patients suffering from systemic lupus erythematosis (SLE). 596 lipids were profiled which were quality filtered for further evaluation and determination of potential biomarkers. Lipidomes were compared by linear regression and evaluated by machine learning classifiers. Results Machine learning classifiers based on the plasma lipidomes of patients suffering from CVD and SLE allowed clear distinction of these two chronic inflammatory diseases from each other and from healthy age-matched controls and body mass index (BMI). We demonstrate convincing evidence for the capability of lipidomics to separate the studied chronic and inflammatory diseases from controls based on independent validation test set classification performance (CVD vs control - Sensitivity: 0.90, Specificity: 0.98; IS vs control - Sensitivity: 1.0, Specificity: 1.0; SLE vs control – Sensitivity: 1, Specificity: 0.88) and from each other (SLE vs CVD □ Sensitivity: 0.91, Specificity: 1). Preliminary linear discriminant analysis plots using all data clearly separated the clinical groups from each other and from the controls. In addition, CVD severities, as classified into five clinical groups, were partially separable by linear discriminant analysis. Notably, significantly dysregulated lipids between pathological groups versus control displayed a reverse lipid regulation pattern compared to statin treated controls versus non treated controls. Conclusion Dysregulation of the plasma lipidome is characteristic of chronic inflammatory diseases. Lipid profiling accurately identifies the diseases and in the case of CVD also identifies sub-classes. Dysregulated lipids are partially but not fully counterbalanced by statin treatment.
No takes yet. Share an insight, caveat, or question.
Matthiesen et al. (2021) conducted a case-control in Chronic inflammatory diseases (Cardiovascular disease, Ischemic stroke, Systemic lupus erythematosus) (n=427). Chronic inflammatory diseases (CVD, IS, SLE) vs. Healthy age-matched controls was evaluated on Classification performance (sensitivity and specificity) of plasma lipidome-based machine learning classifiers. Plasma lipid profiling combined with machine learning classifiers accurately distinguished patients with cardiovascular disease, ischemic stroke, and systemic lupus erythematosus from healthy controls, achieving sensitivities of 0.90-1.0 and specificities of 0.88-1.0.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: