Predicting the Outcome of Patients with Aneurysmal Subarachnoid Hemorrhage: A Machine-Learning-Guided Scorecard.

Aneurysmal subarachnoid hemorrhage (aSAH) frequently causes long-term disability, but predicting outcomes remains challenging. Routine parameters such as demographics, admission status, CT findings, and blood tests can be used to predict aSAH outcomes. The aim of this study was to compare the performance of traditional logistic regression with several machine learning algorithms using readily available indicators and to generate a practical prognostic scorecard based on machine learning. Eighteen routinely available indicators were collected as outcome predictors for individuals with aSAH. Logistic regression (LR), random forest (RF), support vector machines (SVMs), and fully connected neural networks (FCNNs) were compared. A scorecard system was established based on predictor weights. The results show that machine learning models and a scorecard achieved 0.75~0.8 area under the curve (AUC) predicting aSAH outcomes (LR 0.739, RF 0.749, SVM 0.762~0.793, scorecard 0.794). FCNNs performed best (~0.95) but lacked interpretability. The scorecard model used only five factors, generating a clinically useful tool with a total cutoff score of ≥5, indicating poor prognosis. We developed and validated machine learning models proven to predict outcomes more accurately in individuals with aSAH. The parameters found to be the most strongly predictive of outcomes were NLR, lymphocyte count, monocyte count, hypertension status, and SEBES. The scorecard system provides a simplified means of applying predictive analytics at the bedside using a few key indicators.

Safety and Efficacy of Tirofiban in Severe Ischemic Stroke Patients Undergoing Mechanical Thrombectomy.

Tirofiban has recently shown encouraging efficacy and safety among acute ischemic stroke (AIS) patients with mechanical thrombectomy (MT). However, the benefits of tirofiban varied among studies depending on the patient's condition, which was often not well analyzed. This study aimed to identify the characteristics of patients who may obtain the largest benefits from tirofiban. The efficacy endpoint was a favorable outcome defined as a modified Rankin Scale (mRS) score of 0~2 at 90 days. The safety endpoints were intracranial hemorrhage (ICH), symptomatic intracranial hemorrhage (sICH) and mortality at 90 days. Adjusted logistic regression analysis and subgroup analyses were utilized to investigate the factors associated with tirofiban and the outcome. All of 285 patients fit the inclusion criteria. Tirofiban was associated with a higher rate of favorable outcome (aOR 2.033, 95% CI, 1.002~4.123, p = 0.043) but not with an increased risk of ICH, sICH or mortality (p > 0.05). Moreover, subgroup analyses revealed that tirofiban was associated with favorable outcomes in patients with NIHSS > 14 (aOR 2.778, 95% CI 1.056~7.356, p = 0.038) but not in patients with NIHSS ≤ 14 (aOR 1.719, 95% CI 0.646~4.578, p = 0.278). No significant heterogeneity was found in the effect of tirofiban across the subgroups of age, sex, ASPECTS, time from onset to puncture, use of t-PA or stroke etiology (p for interaction > 0.05). The administration of tirofiban was associated with favorable outcomes in severe ischemic stroke patients, and further studies are needed to confirm this finding.

Hemifacial Spasm Caused by Distal Neurovascular Compression Confirmed by Lateral Spread Response Monitoring.

Primary hemifacial spasm (HFS) is likely related to a vascular compression of the facial nerve at its distal cisternal portion root exit Zone that has been reported during recent years. Most of these cases were found during secondary surgery or intraoperative monitoring of lateral spread response (LSR). Here we reported 2 patients with typical HFS caused by distal neurovascular compression that were successfully treated with microvascular decompression. Magnetic resonance imaging in both cases suggested that there was a contact between the vessel in cisternal segment and the facial nerve. LSR immediately disappeared after decompression of distal neurovascular compression. Resolution of spasm after the operation was achieved in both of these cases, with a short duration of vertigo and mild facial paralysis in case 1. Reviewing the literature, the majority of cases of distal neurovascular compression are found under the following 2 conditions:(1) When patients underwent a second operation. (2) When surgeons explored the distal part, the cisternal portion, after exploring the traditional root exit Zone without LSR disappearing. Therefore, it is the distal neurovascular compression at cisternal segment that may also be the cause of HFS. As for this kind of special HFS, these patients may also present with cranial nerve symptoms of VIII. In addition, magnetic resonance imaging can provide some information about compression sites. When we perform microvascular decompression, we should carefully pay attention to having an entire-root-exploration with intraoperative electrophysiology to find and decompress the real neurovascular compression.

Dynamic nomogram for predicting acute kidney injury in patients with acute ischemic stroke: A retrospective study.

Background: This study sought to develop and validate a dynamic nomogram chart to assess the risk of acute kidney injury (AKI) in patients with acute ischemic stroke (AIS). Methods: These data were drawn from the Medical Information Mart for Intensive Care III (MIMIC-III) database, which collects 47 clinical indicators of patients after admission to the hospital. The primary outcome indicator was the occurrence of AKI within 48 h of intensive care unit (ICU) admission. Independent risk factors for AKI were screened from the training set using univariate and multifactorial logistic regression analyses. Multiple logistic regression models were developed, and nomograms were plotted and validated in an internal validation set. Based on the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) to estimate the performance of this nomogram. Results: Nomogram indicators include blood urea nitrogen (BUN), creatinine, red blood cell distribution width (RDW), heart rate (HR), Oxford Acute Severity of Illness Score (OASIS), the history of congestive heart failure (CHF), the use of vancomycin, contrast agent, and mannitol. The predictive model displayed well discrimination with the area under the ROC curve values of 0.8529 and 0.8598 for the training set and the validator, respectively. Calibration curves revealed favorable concordance between the actual and predicted incidence of AKI (p > 0.05). DCA indicates the excellent net clinical benefit of nomogram in predicting AKI. Conclusion: In summary, we explored the incidence of AKI in patients with AIS during ICU stay and developed a predictive model to help clinical decision-making.

Neutrophil to lymphocyte ratio predicting poor outcome after aneurysmal subarachnoid hemorrhage: A retrospective study and updated meta-analysis.

Background: The relationship between neutrophil to lymphocyte ratio (NLR) and poor outcome of aneurysmal subarachnoid hemorrhage (aSAH) is controversial. We aim to evaluate the relationship between NLR on admission and the poor outcome after aSAH. Method: Part I: Retrospective analysis of aSAH patients in our center. Baseline characteristics of patients were collected and compared. Multivariate analysis was used to evaluate parameters independently related to poor outcome. Receiver operating characteristic (ROC) curve analysis was used to determine the best cut-off value of NLR. Part II: Systematic review and meta-analysis of relevant literature. Related literature was selected through the database. The pooled odds ratio (OR) and corresponding 95% confidence interval (CI) were calculated to evaluate the correlation between NLR and outcome measures. Results: Part I: A total of 240 patients with aSAH were enrolled, and 52 patients had a poor outcome. Patients with poor outcome at 3 months had a higher admission NLR, Hunt & Hess score, Barrow Neurological Institute (BNI) scale score, Subarachnoid Hemorrhage Early Brain Edema Score (SEBES), and proportion of hypertension history. After adjustment, NLR at admission remained an independent predictor of poor outcome in aSAH patients (OR 0.76, 95% CI 0.69-0.83; P < 0.001). The best cut-off value of NLR in ROC analysis is 12.03 (area under the curve 0.805, 95% CI 0.735 - 0.875; P < 0.001). Part II: A total of 16 literature were included. Pooled results showed that elevated NLR was significantly associated with poor outcome (OR 1.31, 95% CI 1.14-1.49; P < 0.0001) and delayed cerebral ischemia (DCI) occurrence (OR 1.32, 95% CI 1.11-1.56; P = 0.002). The results are more reliable in large sample sizes, low NLR cut-off value, multicenter, or prospective studies. Conclusion: Elevated NLR is an independent predictor of poor outcome and DCI occurrence in aSAH.

DJ-1 Alleviates Neuroinflammation and the Related Blood-Spinal Cord Barrier Destruction by Suppressing NLRP3 Inflammasome Activation via SOCS1/Rac1/ROS Pathway in a Rat Model of Traumatic Spinal Cord Injury.

DJ-1 has been shown to play essential roles in neuronal protection and anti-inflammation in nervous system diseases. This study aimed to explore how DJ-1 regulates neuroinflammation after traumatic spinal cord injury (t-SCI). The rat model of spinal cord injury was established by the clamping method. The Basso, Beattie, Bresnahan (BBB) score and the inclined plane test (IPT) were used to evaluate neurological function. Western blot was then applied to test the levels of DJ-1, NLRP3, SOCS1, and related proinflammatory factors (cleaved caspase 1, IL-1ß and IL-18); ROS level was also examined. The distribution of DJ-1 was assessed by immunofluorescence staining (IF). BSCB integrity was assessed by the level of MMP-9 and tight junction proteins (Claudin-5, Occludin and ZO-1). We found that DJ-1 became significantly elevated after t-SCI and was mainly located in neurons. Knockdown of DJ-1 with specific siRNA aggravated NLRP3 inflammasome-related neuroinflammation and strengthened the disruption of BSCB integrity. However, the upregulation of DJ-1 by Sodium benzoate (SB) reversed these effects and improved neurological function. Furthermore, SOCS1-siRNA attenuated the neuroprotective effects of DJ-1 and increased the ROS, Rac1 and NLRP3. In conclusion, DJ-1 may alleviate neuroinflammation and the related BSCB destruction after t-SCI by suppressing NLRP3 inflammasome activation by SOCS1/Rac1/ROS pathways. DJ-1 shows potential as a feasible target for mediating neuroinflammation after t-SCI.

Role of the Extracellular Traps in Central Nervous System.

It has been reported that several immune cells can release chromatin and granular proteins into extracellular space in response to the stimulation, forming extracellular traps (ETs). The cells involved in the extracellular trap formation are recognized including neutropils, macrophages, basophils, eosinophils, and mast cells. With the development of research related to central nervous system, the role of ETs has been valued in neuroinflammation, blood-brain barrier, and other fields. Meanwhile, it has been found that microglial cells as the resident immune cells of the central nervous system can also release ETs, updating the original understanding. This review aims to clarify the role of the ETs in the central nervous system, especially in neuroinflammation and blood-brain barrier.

Can Tirofiban Improve the Outcome of Patients With Acute Ischemic Stroke: A Propensity Score Matching Analysis.

Objective: To evaluate the efficacy and safety of tirofiban for patients with acute ischemic stroke (AIS), especially posterior circulation stroke (PCS). Methods: We enrolled consecutive patients with AIS who suffered large artery occlusion (LAO) and underwent mechanical thrombectomy (MT) between January 2016 and May 2020. Patients were divided into two groups according to whether tirofiban was used during MT. The primary efficacy outcome was a favorable functional outcome, defined as a modified Rankin Scale (mRS) score of 0-2 at 3 months. The safety outcomes were the rate of mortality at 3 months and the presence of intracranial hemorrhage (ICH) and symptomatic intracranial hemorrhage (sICH). Cohorts were balanced using 1:1 propensity score matching (PSM). Subgroup analysis was further performed to compare the efficacy and safety of tirofiban between the anterior circulation stroke (ACS) and PCS groups. Results: A total of 292 patients were eligible for this study and divided into the tirofiban group (n = 51) and the no-tirofiban group (n = 241). In the propensity-score-matched cohort, the tirofiban group had a higher rate of favorable outcomes than the no-tirofiban group (49.0 vs. 25.5%, p = 0.014), and the mortality at 3 months showed a greater downward trend in the tirofiban group than the no-tirofiban group (15.6 vs. 33.3% p = 0.064). The risk of sICH and ICH was the same between the tirofiban and control groups (17.6 vs. 27.4% p = 0.236, 31.3 vs. 45.1% p = 0.154, respectively). Tirofiban use was predictive of favorable outcomes [adjusted odds ratio (aOR) = 2.87, 95% confidence interval (CI) 1.52-6.44, p = 0.043] after multiple logistic regression analysis. Subgroup analysis revealed that tirofiban use was significantly associated with favorable outcomes in ACS (aOR = 3.66, 95% CI 1.24-5.22, p = 0.019) but not in PCS (aOR = 1.12, 95% CI 0.47-7.52, p = 0.570). Conclusion: We demonstrated that tirofiban may be associated with improving favorable outcome for the AIS patients who underwent MT, without increasing ICH or sICH. Furthermore, our results indicated that for PCS patients tirofiban may not be associated with favorable outcome, and more comprehensive randomized controlled trials are needed to confirm this finding.

The Role of the Blood Neutrophil-to-Lymphocyte Ratio in Aneurysmal Subarachnoid Hemorrhage.

Aneurysmal subarachnoid hemorrhage (aSAH) is an important type of stroke with the highest rates of mortality and disability. Recent evidence indicates that neuroinflammation plays a critical role in both early brain injury and delayed neural deterioration after aSAH, contributing to unfavorable outcomes. The neutrophil-to-lymphocyte ratio (NLR) is a peripheral biomarker that conveys information about the inflammatory burden in terms of both innate and adaptive immunity. This review summarizes relevant studies that associate the NLR with aSAH to evaluate whether the NLR can predict outcomes and serve as an effective biomarker for clinical management. We found that increased NLR is valuable in predicting the clinical outcome of aSAH patients and is related to the risk of complications such as delayed cerebral ischemia (DCI) or rebleeding. Combined with other indicators, the NLR provides improved accuracy for predicting prognosis to stratify patients into different risk categories. The underlying pathophysiology is highlighted to identify new potential targets for neuroprotection and to develop novel therapeutic strategies.