Nomogram to predict hemorrhagic transformation for acute ischemic stroke in Western China: a retrospective analysis

A simple scoring to predict symptomatic intracranial hemorrhage after stroke thrombolysis: the EGAN score

BACKGROUND

Symptomatic intracranial hemorrhage (sICH) after intravenous thrombolysis represents a critical and fatal complication observed in acute ischemic stroke (AIS) patients. This study aims to establish a simple scoring model to predict sICH.

METHODS

We retrospectively conducted a cohort study of eligible AIS patients treated with rt-PA at a tertiary comprehensive stroke center from January 2018 to December 2022. Backward stepwise multivariable logistic regression provided the final model. The point score was generated from β-coefficients. The area under the curve (AUC) of the receiver operating characteristics (ROC) and the Hosmer-Lemeshow goodness-of-fit test were used to assess the discrimination and calibration of the model. The conditional probabilities were derived based on the Bayes theorem.

RESULTS

Of the included patients, sICH occurred in 26 (3.97%) of the 655. The EGAN score consisted of an early infarct sign (10 points), baseline glucose ≥200 mg/dL (11 points), atrial fibrillation (AF) (13 points), and an NIH Stroke Scale (NIHSS) score ≥10 (12 points). With a cut-off point of 13, the EGAN score demonstrated good discrimination (0.7453 [95% CI: 0.649-0.841]), sensitivity (80.77%), and specificity (58.19%), respectively, for identifying sICH.

CONCLUSIONS

This easy-to-use scoring model, based on predictors quickly obtained in clinical practices, offers a simple approach to screening for post-thrombolysis sICH and can serve as an alternative option in hospitals with limited resources for thrombolysis therapy.

Traditional and machine learning models for predicting haemorrhagic transformation in ischaemic stroke: a systematic review and meta-analysis

BACKGROUND

Haemorrhagic transformation (HT) is a severe complication after ischaemic stroke, but identifying patients at high risks remains challenging. Although numerous prediction models have been developed for HT following thrombolysis, thrombectomy, or spontaneous occurrence, a comprehensive summary is lacking. This study aimed to review and compare traditional and machine learning-based HT prediction models, focusing on their development, validation, and diagnostic accuracy.

METHODS

PubMed and Ovid-Embase were searched for observational studies or randomised controlled trials related to traditional or machine learning-based models. Data were extracted according to Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) checklist and risk of bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Performance data for prediction models that were externally validated at least twice and showed low risk of bias were meta-analysed.

RESULTS

A total of 100 studies were included, with 67 focusing on model development and 33 on model validation. Among 67 model development studies, 44 were traditional model studies involving 47 prediction models (with National Institutes of Health Stroke Scale score being the most frequently used predictor in 35 models), and 23 studies focused on machine learning prediction models (with support vector machines being the most common algorithm, used in 10 models). The 33 validation studies externally validated 34 traditional prediction models. Regarding study quality, 26 studies were assessed as having a low risk of bias, 11 as unclear, and 63 as high risk of bias. Meta-analysis of 15 studies validating eight models showed a pooled area under the receiver operating characteristic curve of approximately 0.70 for predicting HT.

CONCLUSION

While significant progress has been made in developing HT prediction models, both traditional and machine learning-based models still have limitations in methodological rigour, predictive accuracy, and clinical applicability. Future models should undergo more rigorous validation, adhere to standardised reporting frameworks, and prioritise predictors that are both statistically significant and clinically meaningful. Collaborative efforts across research groups are essential for validating these models in diverse populations and improving their broader applicability in clinical practice.

SYSTEMATIC REVIEW REGISTRATION

International Prospective Register of Systematic Reviews (CRD42022332816).

Development of a Predictive Nomogram for Intra-Hospital Mortality in Acute Ischemic Stroke Patients Using LASSO Regression

Background and Purpose

Ischemic stroke is a leading cause of mortality and disability globally, necessitating accurate prediction of intra-hospital mortality (IHM) for improved patient care. This study aimed to develop a practical nomogram for personalized IHM risk prediction in ischemic stroke patients.

Methods

A retrospective study of 422 ischemic stroke patients (April 2020 - December 2021) from Chongqing Medical University's First Affiliated Hospital was conducted, with patients divided into training (n=295) and validation (n=127) groups. Data on demographics, comorbidities, stroke risk factors, and lab results were collected. Stroke severity was assessed using NIHSS, and stroke types were classified by TOAST criteria. Least absolute shrinkage and selection operator (LASSO) regression was employed for predictor selection and nomogram construction, with evaluation through ROC curves, calibration curves, and decision curve analysis.

Results

LASSO regression and multivariate logistic regression identified four independent IHM predictors: age, admission NIHSS score, chronic obstructive pulmonary disease (COPD) diagnosis, and white blood cell count (WBC). A highly accurate nomogram based on these variables exhibited excellent predictive performance, with AUCs of 0.958 (training) and 0.962 (validation), sensitivities of 93.2% and 95.7%, and specificities of 93.1% and 90.9%, respectively. Calibration curves and decision curve analysis validated its clinical applicability.

Conclusion

Age, admission NIHSS score, COPD history, and WBC were identified as independent IHM predictors in ischemic stroke patients. The developed nomogram demonstrated high predictive accuracy and practical utility for mortality risk estimation. External validation and prospective studies are warranted for further confirmation of its clinical efficacy.

Traditional and Non-Traditional Lipid Parameters in Relation to Parenchymal Hemorrhage Following Endovascular Treatment for Acute Ischemic Stroke in Anterior Circulation

Purpose

Lipid-lowering therapy is integral in acute ischemic stroke (AIS), yet the connection between lipid parameters and parenchymal hemorrhage (PH) after endovascular treatment (EVT) for AIS is not well-defined. This research aims to assess the association between various lipid parameters and the PH risk following EVT.

Patients and Methods

We examined a database of patients who underwent EVT for AIS between September 2021 and May 2023 retrospectively. Traditional and non-traditional lipid parameters were documented. PH was identified on dual energy computed tomography images within 48 h. We employed logistic regression analysis and restricted cubic splines to examine the association between various lipid parameters and the risk of PH. The predictive capacity of the lipid parameters for PH was evaluated by comparing the area under the curve.

Results

The study included 384 patients, 65 of whom (17.7%) developed PH. After adjusting for potential confounders, only triglyceride was associated with PH among the traditional lipid parameters, while all non-traditional lipid parameters were related to PH. Based on ROC curve, the ratio of remnant cholesterol to high-density lipoprotein cholesterol (RC/HDL-C) exhibited the highest predictive capability for PH. Furthermore, our analysis revealed a significant nonlinear correlation between triglyceride, non-high-density lipoprotein cholesterol, RC, RC/HDL-C and PH risk.

Conclusion

In assessing the risk of PH after EVT, non-traditional lipid parameters are often superior to traditional lipid parameters. It is recommended that routine evaluation of non-traditional lipid parameters could also be conducted in clinical practice as well.

Correlation of Peripheral Blood Inflammatory Indicators to Prognosis After Intravenous Thrombolysis in Acute Ischemic Stroke: A Retrospective Study

Purpose

According to many previous studies, neutrophil-to-lymphocyte ratio (NLR), lymphocyte-to-monocyte ratio (LMR) and hypersensitive C-reactive protein (CRP) are commonly used as important indicators to assess the prognosis of intravenous thrombolysis in AIS patients. Based on this, we used two novel biomarkers C-NLR (CRP/neutrophil-to-lymphocyte ratio) and C-LMR (CRP×lymphocyte-to-monocyte ratio) to investigate their correlation with 90-day outcomes in AIS patients after intravenous thrombolysis.

Patients and Methods

A total of 204 AIS patients who received intravenous thrombolysis at the Stroke Center of Jiangsu Province Hospital of Chinese Medicine from January 2021 to December 2022 were retrospectively included. All patients were followed up 90 days after thrombolysis to assess their prognosis. Patients with a modified Rankin scale score (mRS) of 3-6 were included in the unfavorable outcome group, and those with a score of 0-2 were included in the favorable outcome group. Logistic regression analysis, receiver operating characteristic (ROC) curve, and Kaplan-Meier survival curve were used to investigate the association between C-NLR, C-LMR, and 90-day prognosis in AIS patients treated with early intravenous thrombolysis.

Results

C-NLR (OR=1.586, 95% CI=1.098~2.291, P=0.014) and C-LMR (OR=1.099, 95% CI=1.025~1.179, P=0.008) were independent risk factors for 90-day prognosis of AIS patients treated with early intravenous thrombolysis. The higher C-NLR and C-LMR were associated with unfavorable prognosis.

Conclusion

C-NLR and C-LMR can be used as biomarkers to predict prognosis of AIS patients treated with early intravenous thrombolysis.

A Novel Nomogram to Predict Symptomatic Intracranial Hemorrhage in Ischemic Stroke Patients After Intravenous Thrombolysis

Objective

This study aimed to create and validate a novel nomogram to predict the risk of symptomatic intracranial hemorrhage (sICH) in patients with acute ischemic stroke (AIS) who underwent intravenous thrombolysis (IVT).

Methods

In this retrospective study, 784 patients with AIS who received IVT were enrolled. The patients were randomly divided into two groups: a training set (n=550, 70%) and a testing set (n=234, 30%). Utilizing multivariable logistic regression analysis, relevant factors for the predictive nomogram were selected. The performance of the nomogram was evaluated using various metrics, including the area under the receiver operating characteristic curve (AUC-ROC), the Hosmer-Lemeshow goodness-of-fit test, calibration plots, and decision curve analysis (DCA).

Results

Multivariable logistic regression analysis showed that specific factors, including National Institutes of Health Stroke Scale (NIHSS) scores, Early infarct signs (EIS), and serum sodium, were identified as independent predictors of sICH. Subsequently, a nomogram was constructed using these predictors. The AUC-ROC values of the nomogram were 0.864 (95% CI: 0.810-0.919) and 0.831 (95% CI: 0.770-0.891) in the training and the validation sets, respectively. Both the calibration plots and the Hosmer-Lemeshow goodness-of-fit test showed favorable agreement in both the training and the validation sets. Additionally, the DCA indicated the practical clinical utility of the nomogram.

Conclusion

The novel nomogram, which included NIHSS, EIS and serum sodium as variables, had the potential for predicting the risk of sICH in patients with AIS after IVT.

Application and risk prediction of thrombolytic therapy in cardio-cerebrovascular diseases: a review

Cardiocerebrovascular diseases (CVDs) are the leading cause of death worldwide, consuming huge healthcare budget. For CVD patients, the prompt assessment and appropriate administration is the crux to save life and improve prognosis. Thrombolytic therapy, as a non-invasive approach to achieve recanalization, is the basic component of CVD treatment. Still, there are risks that limits its application. The objective of this review is to give an introduction on the utilization of thrombolytic therapy in cardiocerebrovascular blockage diseases, including coronary heart disease and ischemic stroke, and to review the development in risk assessment of thrombolytic therapy, comparing the performance of traditional scales and novel artificial intelligence-based risk assessment models.

Development and validation of a nomogram model for predicting unfavorable functional outcomes in ischemic stroke patients after acute phase

Introduction

Prediction of post-stroke functional outcome is important for personalized rehabilitation treatment, we aimed to develop an effective nomogram for predicting long-term unfavorable functional outcomes in ischemic stroke patients after acute phase.

Methods

We retrospectively analyzed clinical data, rehabilitation data, and longitudinal follow-up data from ischemic stroke patients who underwent early rehabilitation at multiple centers in China. An unfavorable functional outcome was defined as a modified Rankin Scale (mRS) score of 3-6 at 90 days after onset. Patients were randomly allocated to either a training or test cohort in a ratio of 4:1. Univariate and multivariate logistic regression analyses were used to identify the predictors for the development of a predictive nomogram. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive ability in both the training and test cohorts.

Results

A total of 856 patients (training cohort: n = 684; test cohort: n = 172) were included in this study. Among them, 518 patients experienced unfavorable outcomes 90 days after ischemic stroke. Trial of ORG 10172 in Acute Stroke Treatment classification (p = 0.024), antihypertensive agents use [odds ratio (OR) = 1.86; p = 0.041], 15-day Barthel Index score (OR = 0.930; p < 0.001) and 15-day mRS score (OR = 13.494; p < 0.001) were selected as predictors for the unfavorable outcome nomogram. The nomogram model showed good predictive performance in both the training (AUC = 0.950) and test cohorts (AUC = 0.942).

Conclusion

The constructed nomogram model could be a practical tool for predicting unfavorable functional outcomes in ischemic stroke patients underwent early rehabilitation after acute phase.

Elevated NT-proBNP predicts unfavorable outcomes in patients with acute ischemic stroke after thrombolytic therapy

OBJECTIVE

Few studies correlated n-terminal pro-brain natriuretic peptide (NT-proBNP) with early neurological deterioration (END) and prognosis of acute ischaemic stroke (AIS) patients with rt-PA intravenous thrombolysis. Therefore this study aimed to investigate the relationship between NT-proBNP and END, and prognosis after intravenous thrombolysis in patients with AIS.

METHODS

A total of 325 patients with AIS were enrolled. We performed the natural logarithm transformation on the NT-proBNP [ln(NT-proBNP)]. Univariate and multivariate logistic regression analyses were performed to assess the relationship between ln(NT-proBNP) and END, and prognosis and receiver operating characteristic (ROC) curves were used to show the sensitivity and specificity of NT-proBNP.

RESULTS

After thrombolysis, among 325 patients with AIS, 43 patients (13.2%) developed END. In addition, three months follow-up showed a poor prognosis in 98 cases (30.2%) and a good prognosis in 227 cases (69.8%). Multivariate logistic regression analysis showed that ln(NT-proBNP) was an independent risk factor for END (OR = 1.450,95%CI:1.072 ~ 1.963, P = 0.016) and poor prognosis at three months follow-up (OR = 1.767, 95%CI: 1.347 ~ 2.317, P < 0.001) respectively. According to ROC curve analysis, ln(NT-proBNP) (AUC 0.735, 95%CI: 0.674 ~0.796, P < 0.001) had a good predictive value for poor prognosis, with a predictive value of 5.12 and sensitivity and specificity of 79.59% and 60.35% respectively. When combined with NIHSS to predict END(AUC 0.718, 95%CI: 0.631 ~ 0.805, P < 0.001) and poor prognosis(AUC 0.780, 95%CI: 0.724 ~ 0.836, P < 0.001), the predictive value of the model is further improved.

CONCLUSION

NT-proBNP is independently associated with END and poor prognosis in patients with AIS following intravenous thrombolysis and has a particular predictive value for END and poor prognosis.

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.