Admission neutrophil-to-lymphocyte ratio to predict 30-day mortality in severe spontaneous basal ganglia hemorrhage

Genetically predicted hypotaurine levels mediate the relationship between immune cells and intracerebral hemorrhage

The evidence supports a strong link between immune cells and intracerebral hemorrhage (ICH). Nonetheless, the specific cause-and-effect associations between immune cells and ICH remain indeterminate. Here, our primary investigation compared immune cell infiltration in the ICH and sham groups using the GSE24265 dataset. Afterward, we extensively examined the relationship between immune cells and ICH by applying a two-sample Mendelian randomization (MR) analysis to identify the particular immune cells that may be associated with the initiation and advancement of ICH. Nevertheless, the specific processes that regulate the cause-and-effect connection between immune cells and ICH remain unknown. In this study, our objective was to investigate the connections between immune cell characteristics and plasma metabolites, as well as the links between plasma components and ICH. Our investigation uncovered that the levels of hypotaurine play a key role in the advancement of ICH, influencing the ratio of switched memory B cells among lymphocytes. Thus, our findings provide novel insights into the potential biological mechanisms underlying immune cell-mediated ICH.

An exploration on the machine-learning-based stroke prediction model

Introduction

With the rapid development of artificial intelligence technology, machine learning algorithms have been widely applied at various stages of stroke diagnosis, treatment, and prognosis, demonstrating significant potential. A correlation between stroke and cytokine levels in the human body has recently been reported. Our study aimed to establish machine-learning models based on cytokine features to enhance the decision-making capabilities of clinical physicians.

Methods

This study recruited 2346 stroke patients and 2128 healthy control subjects from Chongqing University Central Hospital. A predictive model was established through clinical experiments and collection of clinical laboratory tests and demographic variables at admission. Three classification algorithms, namely Random Forest, Gradient Boosting, and Support Vector Machine, were employed. The models were evaluated using methods such as ROC curves, AUC values, and calibration curves.

Results

Through univariate feature selection, we selected 14 features and constructed three machine-learning models: Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Machine (GBM). Our results indicated that in the training set, the RF model outperformed the GBM and SVM models in terms of both the AUC value and sensitivity. We ranked the features using the RF algorithm, and the results showed that IL-6, IL-5, IL-10, and IL-2 had high importance scores and ranked at the top. In the test set, the stroke model demonstrated a good generalization ability, as evidenced by the ROC curve, confusion matrix, and calibration curve, confirming its reliability as a predictive model for stroke.

Discussion

We focused on utilizing cytokines as features to establish stroke prediction models. Analyses of the ROC curve, confusion matrix, and calibration curve of the test set demonstrated that our models exhibited a strong generalization ability, which could be applied in stroke prediction.

How well does peripheral blood neutrophil-to-lymphocyte ratio predict the severity and prognosis of hemorrhagic Stroke

OBJECTIVE

We explored the blood neutrophil-to-lymphocyte ratio (NLR) as a prognostic marker and its relation with mortality and Modified Rankin Scale (mRS) score at discharge and at 3 months following ICH and also compared NLR with intracerebral hemorrhage (ICH) score, Sequential Organ Failure Assessment (SOFA) score and National Institutes of Health Stroke Scale (NIHSS) score.

METHODS

The investigators calculated the NIHSS score, SOFA score, ICH score and NLR of 90 adult patients within 3 days of onset of stroke with evidence of hemorrhagic stroke in brain imaging and correlated it with in-hospital mortality, 3-month mortality and mRS at 3 months following stroke using regression analysis.

RESULTS

Out of 90 individuals, there were 54 (60%) males and 36 (40%) females. The mRS score at 3 months significantly related to the admission NLR ratio >7 and SOFA score. Similarly, the in-hospital death and 3-month mortality was related to the admission NLR ratio >7 and ICH score. However, at a cut off value of NLR>3 for assessing the prognosis of the patients, we did not get significant results for mRS at 3 months following stroke and for in-hospital and 3-month mortality.

CONCLUSION

A high NLR ratio >7 predicted worse outcomes in terms of mortality and morbidity at 3-months following haemorrhagic stroke. Hence, like ICH score, NLR can predict 3-month mortality following an acute haemorrhagic stroke and can also predict morbidity following 3 months of brain haemorrhage.

Neutrophil-to-lymphocyte ratio, white blood cell, and C-reactive protein predicts poor outcome and increased mortality in intracerebral hemorrhage patients: a meta-analysis

Objective

Inflammation participates in the pathology and progression of secondary brain injury after intracerebral hemorrhage (ICH). This meta-analysis intended to explore the prognostic role of inflammatory indexes, including neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), white blood cell (WBC), and C-reactive protein (CRP) in ICH patients.

Methods

Embase, PubMed, Web of Science, and Cochrane Library were searched until June 2023. Two outcomes, including poor outcome and mortality were extracted and measured. Odds ratio (OR) and 95% confidence interval (CI) were presented for outcome assessment.

Results

Forty-six studies with 25,928 patients were included in this meta-analysis. The high level of NLR [OR (95% CI): 1.20 (1.13-1.27), p < 0.001], WBC [OR (95% CI): 1.11 (1.02-1.21), p = 0.013], and CRP [OR (95% CI): 1.29 (1.08-1.54), p = 0.005] were related to poor outcome in ICH patients. Additionally, the high level of NLR [OR (95% CI): 1.06 (1.02-1.10), p = 0.001], WBC [OR (95% CI): 1.39 (1.16-1.66), p < 0.001], and CRP [OR (95% CI): 1.02 (1.01-1.04), p = 0.009] were correlated with increased mortality in ICH patients. Nevertheless, PLR was not associated with poor outcome [OR (95% CI): 1.00 (0.99-1.01), p = 0.749] or mortality [OR (95% CI): 1.00 (0.99-1.01), p = 0.750] in ICH patients. The total score of risk of bias assessed by Newcastle-Ottawa Scale criteria ranged from 7-9, which indicated the low risk of bias in the included studies. Publication bias was low, and stability assessed by sensitivity analysis was good.

Conclusion

This meta-analysis summarizes that the high level of NLR, WBC, and CRP estimates poor outcome and higher mortality in ICH patients.

Preoperative systemic immune-inflammation index may predict prolonged mechanical ventilation in patients with spontaneous basal ganglia intracerebral hemorrhage undergoing surgical operation

Background

Prolonged mechanical ventilation (PMV) has been proven as a risk factor for poor prognosis in patients with neurocritical illness. Spontaneous basal ganglia intracerebral hemorrhage (ICH) is one common subtype of hemorrhagic stroke and is associated with high morbidity and mortality. The systemic immune-inflammation index (SII) is used as a novel and valuable prognostic marker for various neoplastic diseases and other critical illnesses.

Objective

This study aimed to analyze the predictive value of preoperative SII for PMV in patients with spontaneous basal ganglia ICH who underwent surgical operations.

Methods

This retrospective study was conducted in patients with spontaneous basal ganglia ICH who underwent surgical operations between October 2014 and June 2021. SII was calculated using the following formula: SII = platelet count × neutrophil count/lymphocyte count. Multivariate logistic regression analysis and receiver operating characteristics curve (ROC) were used to evaluate the potential risk factors of PMV after spontaneous basal ganglia ICH.

Results

A total of 271 patients were enrolled. Of these, 112 patients (47.6%) presented with PMV. Multivariate logistic regression analysis showed that preoperative GCS (OR, 0.780; 95% CI, 0.688-0.883; P < 0.001), hematoma size (OR, 1.031; 95% CI, 1.016-1.047; P < 0.001), lactic acid (OR, 1.431; 95% CI, 1.015-2.017; P = 0.041) and SII (OR, 1.283; 95% CI, 1.049-1.568; P = 0.015) were significant risk factors for PMV. The area under the ROC curve (AUC) of SII was 0.662 (95% CI, 0.595-0.729, P < 0.001), with a cutoff value was 2,454.51.

Conclusion

Preoperative SII may predict PMV in patients with spontaneous basal ganglia ICH undergoing a surgical operation.