Metabolome of Cerebral Thrombi Reveals an Association between High Glycemia at Stroke Onset and Good Clinical Outcome

Abstract

Despite the fact that glucose is the main fuel of the brain, hyperglycemia at hospital admission is generally associated with a poor functional outcome in stroke patients. This paradox may be explained by the lack of information about the blood glucose level at stroke onset. Here, we analyzed the metabolome of blood cells entrapped in cerebral thrombi to gain insight into their metabolism at stroke onset. Fourty-one consecutive stroke patients completely recanalized by mechanical thrombectomy within 6 h were included. The metabolome of retrieved thrombi was analyzed by liquid chromatography tandem with mass spectrometry. Discriminant Analysis (sparse Partial Least Squares Discriminant Analysis (sPLS-DA)) was performed to identify classification models and significant associated features of favorable clinical outcome at 3 months (modified Rankin Scale (mRS) < 2). sPLS-DA of the metabolomes of cerebral thrombi discriminated between stroke patients with a favorable or poor clinical outcome (Area Under the Curve (AUC) = 0.992 (0.931-1)). In addition, our results revealed that high sorbitol and glucose levels in the thrombi positively correlated with favorable clinical outcomes. Sorbitol, a short-term glycemic index reflecting a high blood glucose level at stroke onset, was found to be an independent predictor of good outcome (AUC = 0.908 (0.807-0.995)). This study demonstrates that a high blood glucose level at stroke onset is beneficial to the clinical outcome of the patient.

Keywords: glucose; metabolomics; sorbitol; stroke; thrombectomy; thrombosis.

Figure 1

Metabolomic analysis of cerebral thrombi according to the clinical prognosis. sPLS-DA analysis based on untargeted metabolomic data of cerebral thrombi discriminated stroke patients according to their clinical outcomes (red and green dots represent respectively, patients with mRS (0–1) and mRS (2–6) at 3 months). The score plot is represented with a confidence ellipse of 95% (a). Loading plot of top 20 features selected on the first component of the sPLS-DA model. Identified features are shown as chemical names or at default by their mz/retention time (min)/ionization mode (p: positive and n: negative). Sorbitol was found in different adduct forms: * [M+H]⁺, † [M+H]⁺(¹³C₂), ‡ [M+H-H₂O]⁺ and § [M+H-H₂O]⁺(¹³C) (b).

Figure 2

LC-MS/MS identification of sorbitol (C₆H₁₄O₆; Metlin ID 147; [M]: 182.0790). Firstly, the following adducts of sorbitol were found at the same retention time (RT: 1.75 min) in positive ionization mode: [M+H]⁺ at m/z 183.0865, [M+H-H₂O]⁺ at m/z 165.0759, [M+Na]⁺ at m/z 205.0684 and [M+K]⁺ at m/z 221.0422) (a). Secondly, a MS/MS fragmentation of [M+H]⁺ at m/z 183.0865 with a (+) 30V collision energy was performed (b).

Figure 3

Metabolomic and proteomic analyses of the polyol (sorbitol) and glycolytic pathways of cerebral thrombi. A bar chart is shown for each identified metabolite and protein. White and black bars indicate the level of abundance in cerebral thrombi from patients respectively, with favorable and unfavorable outcomes. * p ≤ 0.05. † non-identified metabolite. G6P: glucose-6-phosphate; F6P: fructose-6-phosphate; FBP: fructose-1,6-biphosphate; G3P: glyceraldehyde-3-phosphate; BPG: biphosphoglycerate; PG: phosphoglycerate; PEP: phosphoenolpyruvate; AR: aldolase reductase, SDH: sorbitol dehydrogenase; GAPDH: glyceraldehyde-3-phosphate dehydrogenase.

Figure 4

Sorbitol in cerebral thrombi and admission glycemia in the prediction of the clinical prognosis (mRS) for stroke patients. ROC curve of sorbitol in cerebral thrombi for predicting favorable outcome (a). Scatter plot showing correlation between the level of sorbitol [M+H]⁺ in cerebral thrombi and admission glycemia according to the clinical outcome. Red lines represent the best thresholds (Youden plots) of each predictor of favorable outcome (sorbitol in cerebral thrombi ≥ 5.9 × 10⁸ and admission glycemia < 1.27 g/L) (b).

Figure 5

Correlations between glycated hemoglobin (HbA1c), sorbitol in cerebral thrombi and admission glycemia. HbA1c was positively correlated with admission glycemia (a) but not with sorbitol in cerebral thrombi (b).