Lipidomic-Based Algorithms Can Enhance Prediction of Obstructive Coronary Artery Disease.

Lipidomics emerges as a promising research field with the potential to help in personalized risk stratification and improve our understanding on the functional role of individual lipid species in the metabolic perturbations occurring in coronary artery disease (CAD). This study aimed to utilize a machine learning approach to provide a lipid panel able to identify patients with obstructive CAD. In this posthoc analysis of the prospective CorLipid trial, we investigated the lipid profiles of 146 patients with suspected CAD, divided into two categories based on the existence of obstructive CAD. In total, 517 lipid species were identified, from which 288 lipid species were finally quantified, including glycerophospholipids, glycerolipids, and sphingolipids. Univariate and multivariate statistical analyses have shown significant discrimination between the serum lipidomes of patients with obstructive CAD. Finally, the XGBoost algorithm identified a panel of 17 serum biomarkers (5 sphingolipids, 7 glycerophospholipids, a triacylglycerol, galectin-3, glucose, LDL, and LDH) as totally sensitive (100% sensitivity, 62.1% specificity, 100% negative predictive value) for the prediction of obstructive CAD. Our findings shed light on dysregulated lipid metabolism's role in CAD, validating existing evidence and suggesting promise for novel therapies and improved risk stratification.

Predicting Non-Alcoholic Steatohepatitis: A Lipidomics-Driven Machine Learning Approach.

Nonalcoholic fatty liver disease (NAFLD), nowadays the most prevalent chronic liver disease in Western countries, is characterized by a variable phenotype ranging from steatosis to nonalcoholic steatohepatitis (NASH). Intracellular lipid accumulation is considered the hallmark of NAFLD and is associated with lipotoxicity and inflammation, as well as increased oxidative stress levels. In this study, a lipidomic approach was used to investigate the plasma lipidome of 12 NASH patients, 10 Nonalcoholic Fatty Liver (NAFL) patients, and 15 healthy controls, revealing significant alterations in lipid classes, such as glycerolipids and glycerophospholipids, as well as fatty acid compositions in the context of steatosis and steatohepatitis. A machine learning XGBoost algorithm identified a panel of 15 plasma biomarkers, including HOMA-IR, BMI, platelets count, LDL-c, ferritin, AST, FA 12:0, FA 18:3 ω3, FA 20:4 ω6/FA 20:5 ω3, CAR 4:0, LPC 20:4, LPC O-16:1, LPE 18:0, DG 18:1_18:2, and CE 20:4 for predicting steatohepatitis. This research offers insights into the connection between imbalanced lipid metabolism and the formation and progression of NAFL D, while also supporting previous research findings. Future studies on lipid metabolism could lead to new therapeutic approaches and enhanced risk assessment methods, as the shift from isolated steatosis to NASH is currently poorly understood.

Plasma Lipids Profile in the Prediction of Non-Alcoholic Steatohepatitis in Adults: A Case-Control Study.

Patients with non-alcoholic steatohepatitis (NASH) show significantly faster progress in the stages of fibrosis compared to those with non-alcoholic fatty liver (NAFL) disease. The non-invasive diagnosis of NASH remains an unmet clinical need. Preliminary data have shown that sphingolipids, especially ceramides, fatty acids, and other lipid classes may be related to the presence of NASH and the histological activity of the disease. The aim of our study was to assess the association of certain plasma lipid classes, such as fatty acids, acylcarnitines, and ceramides, with the histopathological findings in patients with NASH. The study included three groups: patients with NASH (N = 12), NAFL (N = 10), and healthy [non non-alcoholic fatty liver disease (NAFLD)] controls (N = 15). Plasma samples were collected after 12 h of fasting, and targeted analyses for fatty acids, acylcarnitines, and ceramides were performed. Baseline clinical and demographic characteristics were collected. There was no significant difference in baseline characteristics across the three groups or between NAFL and NASH patients. Patients with NASH had increased levels of several fatty acids, including, among others, fatty acid (FA) 14:0, FA 15:0, FA 18:0, FA 18:3n3, as well as Cer(d18:1/16:0), compared to NAFL patients and healthy controls. No significant difference was found between NAFL patients and healthy controls. In conclusion, patients with NASH exhibited a distinctive plasma lipid profile that can differentiate them from NAFL patients and non-NAFLD populations. More data from larger cohorts are needed to validate these findings and examine possible implications for diagnostic and management strategies of the disease.

Is Current Practice Adhering to Guidelines Proposed for Metabolite Identification in LC-MS Untargeted Metabolomics? A Meta-Analysis of the Literature.

Metabolite identification remains a bottleneck and a still unregulated area in untargeted LC-MS metabolomics. The metabolomics research community and, in particular, the metabolomics standards initiative (MSI) proposed minimum reporting standards for metabolomics including those for reporting metabolite identification as long ago as 2007. Initially, four levels were proposed ranging from level 1 (unambiguously identified analyte) to level 4 (unidentified analyte). This scheme was expanded in 2014, by independent research groups, to give five levels of confidence. Both schemes provided guidance to the researcher and described the logical steps that had to be made to reach a confident reporting level. These guidelines have been presented and discussed extensively, becoming well-known to authors, editors, and reviewers for academic publications. Despite continuous promotion within the metabolomics community, the application of such guidelines is questionable. The scope of this meta-analysis was to systematically review the current LC-MS-based literature and effectively determine the proportion of papers following the proposed guidelines. Also, within the scope of this meta-analysis was the measurement of the actual identification levels reported in the literature, that is to find how many of the published papers really reached full metabolite identification (level 1) and how many papers did not reach this level.

Liquid chromatography-mass spectrometry metabolite library for metabolomics: Evaluating column suitability using a scoring approach.

Untargeted metabolomic studies require an extensive set of analyte (metabolic) information to be obtained from each analyzed sample. Thus, highly selective, and efficient analytical methodologies together with reversed-phase (RP) or hydrophilic interaction liquid chromatography (HILIC) are usually applied in these approaches. Here, we present a performance comparison of five different chromatographic columns (C18, C8, RP Amide, zicHILIC, OH5 HILIC phases) to evaluate their sufficiency of analysis for a large analyte library, consisting of 817 authentic standards. By taking into account experimental chromatographic parameters (i.e. retention time, peak tailing and asymmetry, FWHM, signal-to-noise ratio and peak area and intensity), the proposed column scoring approach provides a simple criterion that may assist analysis in the select of a stationary phase for those metabolites of interest. RPLC methods offered better results regarding metabolic library coverage, while the zicHILIC stationary phase delivered a bigger number of properly eluted compounds. This study demonstrates the importance of choosing the most suitable configuration for the analysis of different metabolic classes.

Machine Learning Algorithm to Predict Obstructive Coronary Artery Disease: Insights from the CorLipid Trial.

Developing risk assessment tools for CAD prediction remains challenging nowadays. We developed an ML predictive algorithm based on metabolic and clinical data for determining the severity of CAD, as assessed via the SYNTAX score. Analytical methods were developed to determine serum blood levels of specific ceramides, acyl-carnitines, fatty acids, and proteins such as galectin-3, adiponectin, and APOB/APOA1 ratio. Patients were grouped into: obstructive CAD (SS > 0) and non-obstructive CAD (SS = 0). A risk prediction algorithm (boosted ensemble algorithm XGBoost) was developed by combining clinical characteristics with established and novel biomarkers to identify patients at high risk for complex CAD. The study population comprised 958 patients (CorLipid trial (NCT04580173)), with no prior CAD, who underwent coronary angiography. Of them, 533 (55.6%) suffered ACS, 170 (17.7%) presented with NSTEMI, 222 (23.2%) with STEMI, and 141 (14.7%) with unstable angina. Of the total sample, 681 (71%) had obstructive CAD. The algorithm dataset was 73 biochemical parameters and metabolic biomarkers as well as anthropometric and medical history variables. The performance of the XGBoost algorithm had an AUC value of 0.725 (95% CI: 0.691−0.759). Thus, a ML model incorporating clinical features in addition to certain metabolic features can estimate the pre-test likelihood of obstructive CAD.