A new method for predicting the prognosis of ischemic stroke based vascular structure features and lesion location features.

OBJECTIVE: Determining the changes in the prognosis of the cerebral infarction area has an important guiding role in the selection of the treatment plan. The goal of this study is to propose a machine learning-based method that can predict the prognosis of stroke effectively and efficiently. METHODS: 97 cases of stroke were analyzed retrospectively. Firstly, we extracted vascular structural features from computed tomography angiography (CTA) images and stroke location features from diffusion-weighted imaging (DWI) images to comprehensively characterize the lesions, respectively. Then, we performed sparse representation-based feature selection and classification to predict the prognosis of stroke based on the extracted features. Finally, we randomly divided the 97 cases into cross-validation set, independent testing set 1 and independent testing set 2 to validate the proposed model. RESULTS: 464 vascular structure features and 116 positional features were extracted. After feature selection, 52 features were finally applied to build the classification model. The proposed model achieved promising prediction performance on the two independent testing sets, with the classification accuracies of 85.19% and 81.25%, respectively. CONCLUSION: The proposed machine learning approach can effectively mine and accurately quantify the features related to the prognosis, which include the vascular structural features and the stroke location features. In addition, the established prognostic prediction model based on these features has achieved interesting performances, which may provide valuable guidance for the clinical treatment of stroke.

Longitudinal white matter hyperintensity changes and cognitive decline in patients with minor stroke.

BACKGROUND AND OBJECTIVE: As reported, both minor stroke and white matter hyperintensities (WMHs) are associated with an increased risk of cognitive impairment and dementia. The underlying factors for dynamic changes in WMH volume and cognitive performances in patients with minor stroke remain poorly understood. A 2-year longitudinal study was designed to investigate the factors associated with the changes in white matter hyperintensity (WMH) volume on brain MRI and cognitive decline in patients with minor stroke. METHODS: A group of eligible patients with minor ischemic stroke was recruited in a row. At the initial and 2-year follow-up visits, all the participants underwent routine examinations, multimodal MRI, and cognitive assessment. Using a lesion prediction algorithm tool, we were able to automate the measurement of the change in WMH volume. During the 2-year follow-up, cognitive function was evaluated using Telephone Interview for Cognitive Status-Modified (TICS-m). Participants' demographic, clinical, and therapeutic data were collected and statistically analyzed. Regression analyses were used to test the relationships between risk factors and changes in WMH volume and cognitive decline. RESULTS: Finally, we followed up with 225/261 participants for 2 years, with a mean age of 65.67 ± 10.73 years (65.6% men). WMH volume was observed to be increased in 113 patients, decreased in 74 patients, and remained stable in 58 patients. Patients with WMH progression were more often had a history of hypertension (p = 0.006) and a higher CSVD burden both at baseline and follow-up visit (p < 0.05). Longitudinally, the proportion of patients taking antihypertension medications on a regular basis in the regression group was higher than in the stable group (p = 0.01). When compared to the stable group, the presence of lacunes (OR 9.931, 95% CI 1.597-61.77, p = 0.014) was a stronger predictor of progression in WMH volume. 87 subjects (38.6%) displayed incident cognitive impairment. The progression of WMH volume was a significant risk factor for cognitive decline (p < 0.001). CONCLUSIONS: The longitudinal change of WMH is dynamic. The regressive WMH volume was associated with the use of antihypertensive medications on a regular basis. The presence of lacunes at the initial visit of the study was a stronger predictor of WMH progression. The progression of WMH volume could be useful in predicting cognitive decline in patients with minor stroke.

Long Noncoding RNA X-Inactive Specific Transcript Regulates Neuronal Cell Apoptosis in Ischemic Stroke Through miR-98/BACH1 Axis.

Long noncoding RNA X-inactive specific transcript (XIST) has been identified as a crucial regulator in neurodegenerative disorders. However, the role and mechanism of XIST in ischemic stroke remain elusive. In our study, we found that XIST expression was upregulated in both mice subjected to middle cerebral artery occlusion and oxygen-glucose deprivation (OGD)-treated neurons. Functional assays disclosed that the interference of XIST accelerated viability, and suppressed apoptosis and caspase-3 activity in OGD-treated neurons. Moreover, XIST interacted with miR-98, and miR-98 targeted BTB-to-CNC homology 1 (BACH1). miR-98 silencing or BACH1 overexpression counteracted XIST knockdown-mediated effects on cell viability and apoptosis in OGD-treated neurons. In conclusion, our data demonstrated that XIST facilitated the progression of ischemic stroke through regulating the miR-98/BACH1 axis. These findings might provide a novel therapeutic strategy for ischemic stroke treatment.

Differences of circulating inflammatory markers between large- and small vessel disease in patients with acute ischemic stroke.

BACKGROUND: The difference of inflammatory response between the pathogenesis of cerebral large- and small vessel disease after stroke remains unclear. In present study, we aim to determine the association of circulating inflammatory markers with different stroke subtype. METHODS: 99 patients with non-cardioembolic stroke were divided into large artery atherosclerosis (LAA) and small-artery occlusion (SAO) according to TOAST classification. A panel of plasma inflammatory markers including leukocyte, lymphocyte, CRP, fibrinogen, D-dimer, CD40L, IFN-γ, IL-1α, IL-1ß, IL-6, IL-8, IL-17 and TNF-α were measured within 72 hours following cerebral ischemia. The relation of their levels in plasma with stroke subtype was further studied. All statistical data analysis was performed by SPSS 17.0 software. RESULTS: We found that only CRP were closely associated with stroke subtype (p<0.05). Compared to SAO subgroup, the plasma levels of CRP was higher in LAA subgroup (p<0.05). The predictive efficiency of CRP more than 3.2 for LAA was 85.7% sensitivity. The influencing factor of CRP includes IL-6, lymphocyte, fibrinogen and D-dimer. CONCLUSION: LAA had a stronger activation of inflammation than SAO in the pathogenesis, which was associated with the changes of CRP.

Pro-inflammatory cytokine network in peripheral inflammation response to cerebral ischemia.

The key circulating pro-inflammatory cytokines and their interaction in peripheral inflammation after acute cerebral ischemia are poorly understood. CD40L, IFN-γ, IL-1α, IL-1ß, IL-6, IL-8, IL-17 and TNF-α were determined using multi-ELISA kit in stroke patients within 72 h of an acute ischemic attack. Leukocyte mRNAs were determined using real-time polymerase chain reactions (PCR). Stroke severity and clinical outcomes were evaluated by National Institutes of Health Stroke Scores (NIHSS) and modified Rankin Scale (mRS). Plasma/mRNA cytokine interactions were analyzed using the Bayesian network learning procedure. Compared to controls, stroke patients had higher IL-6, IL-8 and TNFα protein in plasma and lower IL-6, IL-8, TNFα, IL-1α, and IL-1ß mRNA in leukocyte within 72 h after stroke. However, only the elevation of IL-6 correlated with the severity and prognosis of their stroke. This was associated with a decreased IL-6 mRNA in leukocyte. Further study showed that Bayesian network analysis revealed that changes in the other cytokines were subsequent to IL-6 leukocyte cytokine RNA. The change of other cytokines in plasma proteins after ischemic brain injury appeared secondary to IL-6. Pro-inflammatory cytokines up-regulation in plasma and compensatory immunity depression in leukocyte involve in peripheral inflammation response to cerebral ischemia. IL-6 appears to be the key mediator of circulating pro-inflammatory cytokines network.

Cocktail blood biomarkers: prediction of clinical outcomes in patients with acute ischemic stroke.

BACKGROUND: Timely prediction of stroke outcomes is important for proper personalized treatment. In the present study, we aimed to develop cocktail blood biomarkers to increase prediction efficiency using a combination of hemostasis, inflammatory and repair-related biomarkers. METHODS: 105 patients suffering from acute ischemic stroke were divided into good outcome group and poor outcome group by modified Rankin Scale (mRS). Cytokines including CD40L, IFN-γ, IL-1α, IL-1ß, IL-6, IL-8, IL-17 and TNF-α, as well as hemostasis markers fibrinogen, fibrin degradation products (FDP), D-dimer, tissue plasminogen activator, and plasminogen activation inhibitor-1 in plasma were examined by ELISA. Repair-related biomarker microRNA-210 (miR-210) was measured by real-time PCR. The prediction efficiency was explored by receiver operator characteristic analysis. RESULTS: We demonstrated that FDP, IL-6 and miR-210 levels were closely associated with mRS in stroke patients. The prediction sensitivity of FDP, IL-6 and miR-210 for stroke outcome was 72.0, 86.7 and 82.5%, respectively. Using a combination of biomarkers including FDP, IL-6 and miR-210, the prognostic sensitivity of ischemic stroke increased to 95.2%. CONCLUSION: The combination of FDP, IL-6 and miR-210 has a high sensitivity for predicting stroke recovery, it serves as a potential cocktail blood biomarker. It provides a novel approach for stroke prognosis.

MicroRNA-210 as a novel blood biomarker in acute cerebral ischemia.

MicroRNA-210 (miR-210), a master and pleiotropic hypoxia-microRNA, plays multiple roles in brain ischemia. However, miR-210 expression and its function in humans have not been explored. The aim of our study is to evaluate the correlation of blood miR-210 with clinical findings in acute ischemic stroke. Blood samples were obtained from stroke patients (n=112) and healthy controls (n= 60). MiR-210 was measured at within 3, 7 and 14 days after stroke using a quantitative PCR technique. Stroke severity and clinical outcome were evaluated by NIHSS and modified Rankin Score. Both blood and brain miR-210 in ischemic mice was examined and the correlation was investigated. Compared to healthy controls, blood miRNA-210 was significantly decreased in stroke patients (0.93 vs. 1.36; P=0.001), especially at 7 days (0.56 vs. 1.36; P=0.001) and 14 days of stroke onset (0.50 vs. 1.36; P=0.001). The cut off point of miR-210 in diagnosis was 0.505 with 88.3 per cent sensitivity. MiR-210 level in stroke patients with good outcome was significantly higher than patients with poor outcome (1.2 vs. 0.44; P=0.012). The correlation between blood and brain miR-210 in ischemic mice was positive (R2=0.57, P=0.001). Blood miR-210 is a novel sensitive biomarker for clinical diagnosis and prognosis in acute cerebral ischemia.