Machine Learning Analysis of the Cerebrovascular Thrombi Lipidome in Acute Ischemic Stroke

Abstract

OBJECTIVE:The aim of this study was to identify a signature lipid profile from cerebral thrombi in acute ischemic stroke (AIS) patients at the time of ictus. METHODS: We performed untargeted lipidomics analysis using liquid chromatography-mass spectrometry on cerebral thrombi taken from a nonprobability, convenience sampling of adult subjects (≥18 years old, n = 5) who underwent thrombectomy for acute cerebrovascular occlusion. The data were classified using random forest, a machine learning algorithm. RESULTS: The top 10 metabolites identified from the random forest analysis were of the glycerophospholipid species and fatty acids. CONCLUSION: Preliminary analysis demonstrates feasibility of identification of lipid metabolomic profiling in cerebral thrombi retrieved from AIS patients. Recent advances in omic methodologies enable lipidomic profiling, which may provide insight into the cellular metabolic pathophysiology caused by AIS. Understanding of lipidomic changes in AIS may illuminate specific metabolite and lipid pathways involved and further the potential to develop personalized preventive strategies.

Advancing Stroke Research on Cerebral Thrombi with Omic Technologies

“…So far, one study performed metabolomic analysis only, and 2 others metabolomic coupled with proteomics (combined proteomic and metabolomic paragraph). Early results on 5 thrombi indicate that the 10 most represented lipids were part of the phosphoethanolamine, phosphocholine, and fatty acids groups [ 23 ]. Plasma lipoproteins may play a role in thrombi formation through the interaction between ruptured atherosclerotic plaques and platelets [ 23 ].…”

“…Early results on 5 thrombi indicate that the 10 most represented lipids were part of the phosphoethanolamine, phosphocholine, and fatty acids groups [ 23 ]. Plasma lipoproteins may play a role in thrombi formation through the interaction between ruptured atherosclerotic plaques and platelets [ 23 ]. In addition, patients with hypercholesterolemia present more frequently abnormal platelet function, such as alterations of lipoprotein-surface receptors interactions, increased platelet activation, and leukocyte recruitment [ 23 , 54 ].…”

“…Plasma lipoproteins may play a role in thrombi formation through the interaction between ruptured atherosclerotic plaques and platelets [ 23 ]. In addition, patients with hypercholesterolemia present more frequently abnormal platelet function, such as alterations of lipoprotein-surface receptors interactions, increased platelet activation, and leukocyte recruitment [ 23 , 54 ]. Thus, the characterization of lipid composition in clots from AIS patients could help to better understand the role of different lipids in thrombogenesis, investigate the mechanisms of atherosclerotic plaque disruption in LAA-associated stroke, develop more tailored lipid-lowering and antithrombotic secondary prevention strategies for AIS.…”

“…Recent studies [ 21 , 22 , 23 , 24 , 25 , 26 ] have evaluated omic techniques to assess thrombi composition. These refer to a variety of technologies enabling deep phenotyping of biological samples to define their molecular characteristics [ 27 ].…”

Letter to the Editor: Telestroke and Artificial Intelligence

“…Using AI to determine biomarker values associated with acute stroke to tailor patient education and promote medication adherence is promising. 3,4 However, using AI to screen neuroimaging before the neuroradiologist should be explored with caution. Implementing AI in healthcare is not a perfect science.…”