Early prediction of the 3-month outcome for individual acute ischemic stroke patients who received intravenous thrombolysis using the N2H3 nomogram model

HERMES-24 Score Derivation and Validation for Simple and Robust Outcome Prediction After Large Vessel Occlusion Treatment

BACKGROUND

Clinicians need simple and highly predictive prognostic scores to assist practical decision-making. We aimed to develop a simple outcome prediction score applied 24 hours after anterior circulation acute ischemic stroke treatment with endovascular thrombectomy and validate it in patients treated both with and without endovascular thrombectomy.

METHODS

Using the HERMES (Highly Effective Reperfusion Evaluated in Multiple Endovascular Stroke Trials) collaboration data set (n=1764), patients in the endovascular thrombectomy arm were divided randomly into a derivation cohort (n=430) and a validation cohort (n=441). From a set of candidate predictors, logistic regression modeling using forward variable selection was used to select a model that was both parsimonious and highly predictive for modified Rankin Scale (mRS) ≤2 at 90 days. The score was validated in validation cohort, control arm (n=893), and external validation cohorts from the ESCAPE-NA1 (Efficacy and Safety of Nerinetide for the Treatment of Acute Ischaemic Stroke; n=1066) and INTERRSeCT (Identifying New Approaches to Optimize Thrombus Characterization for Predicting Early Recanalization and Reperfusion With IV Alteplase and Other Treatments Using Serial CT Angiography; n=614).

RESULTS

In the derivation cohort, we selected 2 significant predictors of mRS ≤2 (National Institutes of Health Stroke Scale score at 24 hours and age [β-coefficient, 0.34 and 0.06]) and derived the HERMES-24 score: age (years)/10+National Institutes of Health Stroke Scale score at 24 hours. The HERMES-24 score was highly predictive for mRS ≤2 (c-statistic 0.907 [95% CI, 0.879-0.935]) in the derivation cohort. In the validation cohort and the control arm, the HERMES-24 score predicts mRS ≤2 (c-statistic, 0.914 [95% CI, 0.886-0.944] and 0.909 [95% CI, 0.887-0.930]). Observed provability of mRS ≤2 ranged between 3.1% and 3.4% when HERMES-24 score ≥25, while it ranged between 90.6% and 93.0% when HERMES-24 score <10 in the derivation cohort, validation cohort, and control arm. The HERMES-24 score also showed c-statistics of 0.894 and 0.889 for mRS ≤2 in the ESCAPE-NA1 and INTERRSeCT populations.

CONCLUSIONS

The post-treatment HERMES-24 score is a simple validated score that predicts a 3-month outcome after anterior circulation large vessel occlusion stroke regardless of intervention, which helps prognostic discussion with families on day 2.

Development and validation of outcome prediction model for reperfusion therapy in acute ischemic stroke using nomogram and machine learning

OBJECTIVE

To develop logistic regression nomogram and machine learning (ML)-based models to predict 3-month unfavorable functional outcome for acute ischemic stroke (AIS) patients undergoing reperfusion therapy.

METHODS

Patients undergoing reperfusion therapy (intravenous thrombolysis and/or endovascular treatment) were prospectively recruited. Unfavorable outcome was defined as 3-month modified Rankin Scale (mRS) score 3-6. The independent risk factors associated with unfavorable outcome were obtained by regression analysis and included in the prediction model. The performance of nomogram was assessed by the area under the curve (AUC), calibration curve, and decision curve analysis (DCA). ML models were compared with nomogram using AUC; the generalizability of all models was ascertained in an external cohort.

RESULTS

A total of 505 patients were enrolled, with 256 in the model construction, and 249 in the external validation. Five variables were identified as prognostic factors: baseline NIHSS, D-dimer level, random blood glucose (RBG), blood urea nitrogen (BUN), and systolic blood pressure (SBP) before reperfusion. The AUC values of nomogram were 0.865, 0.818, and 0.779 in the training set, test set, and external validation, respectively. The calibration curve and DCA indicated appreciable reliability and good net benefits. The best three ML models were extra trees (ET), CatBoost, and random forest (RF) models; all of them showed favorable discrimination in the training cohort, and confirmed in the test and external sets.

CONCLUSION

Baseline NIHSS, D-dimer, RBG, BUN, and SBP before reperfusion were independent predictors for 3-month unfavorable outcome after reperfusion therapy in AIS patients. Both nomogram and ML models showed good discrimination and generalizability.

Predicting ineffective thrombolysis in acute ischemic stroke with clinical and biochemical markers

**Ischemic stroke remains a leading cause of morbidity and mortality globally. Despite the advances in thrombolytic therapy, notably recombinant tissue plasminogen activator (rtPA), patient outcomes are highly variable. This study aims to introduce a novel predictive model, the Acute Stroke Thrombolysis Non-Responder Prediction Model (ASTN-RPM), to identify patients unlikely to benefit from rtPA within the critical early recovery window. We conducted a retrospective cohort study at Baoding No.1 Central Hospital including 709 adult patients diagnosed with acute ischemic stroke and treated with intravenous alteplase within the therapeutic time window. The ASTN-RPM was developed using Least Absolute Shrinkage and Selection Operator (LASSO) regression technique, incorporating a wide range of biomarkers and clinical parameters. Model performance was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Decision Curve Analysis (DCA). ASTN-RPM effectively identified patients at high risk of poor response to thrombolysis, with an AUC of 0.909 in the training set and 0.872 in the validation set, indicating high sensitivity and specificity. Key predictors included posterior circulation stroke, high admission NIHSS scores, extended door to needle time, and certain laboratory parameters like homocysteine levels. The ASTN-RPM stands as a potential tool for refining clinical decision-making in ischemic stroke management. By anticipating thrombolytic non-response, clinicians can personalize treatment strategies, possibly improving patient outcomes and reducing the burden of ineffective interventions. Future studies are needed for external validation and to explore the incorporation of emerging biomarkers and imaging data.

A new machine learning algorithm with high interpretability for improving the safety and efficiency of thrombolysis for stroke patients: A hospital-based pilot study

Background

Thrombolysis is the first-line treatment for patients with acute ischemic stroke. Previous studies leveraged machine learning to assist neurologists in selecting patients who could benefit the most from thrombolysis. However, when designing the algorithm, most of the previous algorithms traded interpretability for predictive power, making the algorithms hard to be trusted by neurologists and be used in real clinical practice.

Methods

Our proposed algorithm is an advanced version of classical k-nearest neighbors classification algorithm (KNN). We achieved high interpretability by changing the isotropy in feature space of classical KNN. We leveraged a cohort of 189 patients to prove that our algorithm maintains the interpretability of previous models while in the meantime improving the predictive power when compared with the existing algorithms. The predictive powers of models were assessed by area under the receiver operating characteristic curve (AUC).

Results

In terms of interpretability, only onset time, diabetes, and baseline National Institutes of Health Stroke Scale (NIHSS) were statistically significant and their contributions to the final prediction were forced to be proportional to their feature importance values by the rescaling formula we defined. In terms of predictive power, our advanced KNN (AUC 0.88) outperformed the classical KNN (AUC 0.75, p = 0.0192 ).

Conclusions

Our preliminary results show that the advanced KNN achieved high AUC and identified consistent significant clinical features as previous clinical trials/observational studies did. This model shows the potential to assist in thrombolysis patient selection for improving the successful rate of thrombolysis.

Prognostic role of dynamic neutrophil-to-lymphocyte ratio in acute ischemic stroke after reperfusion therapy: A meta-analysis

Background

The prognostic role of the neutrophil-to-lymphocyte ratio (NLR), an inflammatory marker, in acute ischemic stroke (AIS) after reperfusion therapy remains controversial. Therefore, this meta-analysis sought to assess the correlation between the dynamic NLR and the clinical outcomes of patients with AIS after reperfusion therapy.

Methods

PubMed, Web of Science, and Embase databases were searched to identify relevant literature from their inception to 27 October 2022. The clinical outcomes of interest included poor functional outcome (PFO) at 3 months, symptomatic intracerebral hemorrhage (sICH), and 3-month mortality. The NLR on admission (pre-treatment) and post-treatment was collected. The PFO was defined as a modified Rankin scale (mRS) of >2.

Results

A total of 17,232 patients in 52 studies were included in the meta-analysis. The admission NLR was higher in the 3-month PFO (standardized mean difference [SMD] = 0.46, 95% confidence interval [CI] = 0.35-0.57), sICH (SMD = 0.57, 95% CI = 0.30-0.85), and mortality at 3 months (SMD = 0.60, 95% CI = 0.34-0.87). An elevated admission NLR was associated with an increased risk of 3-month PFO (odds ratio [OR] = 1.13, 95% CI = 1.09-1.17), sICH (OR = 1.11, 95% CI = 1.06-1.16), and mortality at 3 months (OR = 1.13, 95% CI = 1.07-1.20). The post-treatment NLR was significantly higher in the 3-month PFO (SMD = 0.80, 95% CI = 0.62-0.99), sICH (SMD = 1.54, 95% CI = 0.97-2.10), and mortality at 3 months (SMD = 1.00, 95% CI = 0.31-1.69). An elevated post-treatment NLR was significantly associated with an increased risk of 3-month PFO (OR = 1.25, 95% CI = 1.16-1.35), sICH (OR = 1.14, 95% CI = 1.01-1.29), and mortality at 3 months (OR = 1.28, 95% CI = 1.09-1.50).

Conclusion

The admission and post-treatment NLR can be used as cost-effective and easily available biomarkers to predict the 3-month PFO, sICH, and mortality at 3 months in patients with AIS treated with reperfusion therapy. The post-treatment NLR provides better predictive power than the admission NLR.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier: CRD42022366394.

The feasibility and accuracy of machine learning in improving safety and efficiency of thrombolysis for patients with stroke: Literature review and proposed improvements

In the treatment of ischemic stroke, timely and efficient recanalization of occluded brain arteries can successfully salvage the ischemic brain. Thrombolysis is the first-line treatment for ischemic stroke. Machine learning models have the potential to select patients who could benefit the most from thrombolysis. In this study, we identified 29 related previous machine learning models, reviewed the models on the accuracy and feasibility, and proposed corresponding improvements. Regarding accuracy, lack of long-term outcome, treatment option consideration, and advanced radiological features were found in many previous studies in terms of model conceptualization. Regarding interpretability, most of the previous models chose restrictive models for high interpretability and did not mention processing time consideration. In the future, model conceptualization could be improved based on comprehensive neurological domain knowledge and feasibility needs to be achieved by elaborate computer science algorithms to increase the interpretability of flexible algorithms and shorten the processing time of the pipeline interpreting medical images.

Prognostic nomogram for the outcomes in acute stroke patients with intravenous thrombolysis

Background and purpose

The prediction of neurological outcomes in ischemic stroke patients is very useful in treatment choices, as well as in post-stroke management. This study is to develop a convenient nomogram for the bedside evaluation of stroke patients with intravenous thrombolysis.

Materials and methods

We reviewed all enrolled stroke patients with intravenous thrombolysis retrospectively. Favorable outcome was defined as modified Rankin Score (mRs) less than 2 at 90 days post thrombolysis. We compared the clinical characteristics between patients with favorable outcome and poor outcome. Then, we applied logistic regression models and compared their predictability.

Results

A total of 918 patients were enrolled in this study, 448 patients from one hospital were included to develop a nomogram, whereas 470 patients from the other hospital were used for the external validation. Associated risk factors were identified by multivariate logistic regression. The nomogram was validated by the area under the receiver operating characteristic curve (AUC). A nomogram was developed with baseline NIHSS, blood sugar, blood cholesterol level, part-and full anterior circulation infarction (OCSP type). The AUC was 0.767 (95% CI 0.653–0.772) and 0.836 (95% CI 0.697–0.847) in the derivation and external validation cohorts, respectively. The calibration plot for the probability of severe neurological outcome showed an optimal agreement between the prediction by nomogram and actual observation in both derivation and validation cohorts.

Conclusion

A convenient outcome evaluation nomogram for patients with intravenous thrombolysis was developed, which could be used by physicians in making clinical decisions and predicting patients’ prognosis.

Delavatine A attenuates OGD/R-caused PC12 cell injury and apoptosis through suppressing the MKK7/JNK signaling pathway

Delavatine A (DA) is an unusual isoquinoline alkaloid with a novel skeleton isolated from Chinese folk medicine Incarvillea delavayi. Studies conducted in our lab have demonstrated that DA has potential anti-inflammatory activity in LPS-treated BV-2 cells. DA, however, has not been studied for its protective effect on neuronal cells yet. Thus, to explore whether DA can protect neurons, oxygen and glucose deprivation/reperfusion (OGD/R)-injured PC12 cell and middle cerebral artery occlusion/reperfusion (MCAO/R) rat model were used to assess the protective efficacy of DA against OGD/R damaged PC12 cells and MCAO/R injured rats. Our results demonstrated that DA pretreatment (0.31-2.5 μM) dose-dependently increased cell survival and mitochondrial membrane potential (MMP), whereas it lowered the leakage of lactate dehydrogenase (LDH), intracellular cumulation of Ca²⁺, and overproduction of reactive oxygen species (ROS), and inhibited the apoptosis rate in OGD/R-injured PC12 cells. Western blot demonstrated that DA pretreatment lowered the expression of apoptotic proteins and repressed the activation of the MKK7/JNK pathway. It was also found that the neuroprotective efficacy of DA was significantly reversed by co-treatment with the JNK agonist anisomycin, suggesting that DA reduced PC12 cell injury and apoptosis by suppressing the MKK7/JNK pathway. Furthermore, DA oral administration greatly alleviated the neurological dysfunction and reduced the infarct volume of MCAO/R rats. Taken together, DA could ameliorate OGD/R-caused PC12 cell injury and improve brain ischemia/reperfusion (I/R) damage in MCAO/R rats, and its neuroprotection might be attributed to suppressing the MKK7/JNK signaling pathway.

Role of Neutrophil-Lymphocyte Ratio in the Prognosis of Acute Ischaemic Stroke After Reperfusion Therapy: A Systematic Review and Meta-analysis

Background

Inflammation may mediate response to acute reperfusion therapy (RT) in acute cerebral ischaemia. Neutrophil-lymphocyte ratio (NLR), an inflammatory biomarker, may play an important role in acute ischaemic stroke (AIS) prognostication.

Objective

This meta-analysis sought to examine the effect of NLR on functional outcomes, mortality and adverse outcomes in AIS patients receiving RT.

Methods

Individual studies were retrieved from PubMed/Medline, EMBASE and Cochrane databases. Data were extracted using a standardised data sheet and meta-analysis on association of admission (pre-RT) or delayed (post-RT) NLR with clinical/safety outcomes after RT was conducted.

Results

Thirty-five studies (n = 10 308) were identified for the systematic review with 27 (n = 8537) included in the meta-analyses. Lower admission NLR was associated with good functional outcomes (GFOs), defined as 3-month modified Rankin scale (mRS) 0–2 (SMD = −.46; 95% CI = −.62 to −.29; P < .0001), mRS 0–1 (SMD = −.44; 95% CI = −.66 to −.22; P < .0001) and early neurological improvement (ENI) (SMD = −.55; 95 %CI = −.84 to −.25; P < .0001). Lower delayed admission NLR was also associated with GFOs (SMD = −.80; 95%CI = −.91 to −.68; P < .0001). Higher admission NLR was significantly associated with mortality (SMD = .49; 95%CI = .12 to .85; P = .009), intracerebral haemorrhage (ICH) (SMD = .34; 95% CI = .09 to .59; P = .007), symptomatic ICH (sICH) (SMD = .48; 95% CI = .07 to .90; P = .022) and stroke-associated infection or pneumonia (SMD = .85; 95% CI = .50, 1.19; P < .0001). Higher delayed NLR was significantly associated with sICH (SMD = 1.40; 95% CI = .60 to 2.19; P = .001), ICH (SMD = .94; 95% CI = .41 to 1.46; P < .0001) and mortality (SMD = 1.12; 95% CI = .57 to 1.67; P < .0001). There were variations in outcomes across RT groups.

Conclusion

Higher admission or delayed NLR is significantly associated with worse morbidity, mortality and safety outcomes in AIS patients receiving RT.