The stroke prognosis instrument II (SPI-II) : A clinical prediction instrument for patients with transient ischemia and nondisabling ischemic stroke

PRERISK: A Personalized, Artificial Intelligence-Based and Statistically-Based Stroke Recurrence Predictor for Recurrent Stroke

BACKGROUND

Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors' engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence.

METHODS

We analyzed clinical and socioeconomic data from a prospectively collected public health care-based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014-2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models.

RESULTS

Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74-0.77), 0.60 (95% CI, 0.58-0.61), and 0.71 (95% CI, 0.69-0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72-0.75), 0.59 (95% CI, 0.57-0.61), and 0.67 (95% CI, 0.66-0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement (P<0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors.

CONCLUSIONS

PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.

Development and validation of a clinical prediction model for ischemic stroke recurrence after successful stent implantation in symptomatic intracranial atherosclerotic stenosis

OBJECTIVE

This study aimed to analyze the risk factors for recurrent ischemic stroke in patients with symptomatic intracranial atherosclerotic stenosis (ICAS) who underwent successful stent placement and to establish a nomogram prediction model.

METHODS

We utilized data from a prospective collection of 430 consecutive patients at Jining NO.1 People's Hospital from November 2021 to November 2022, conducting further analysis on the subset of 400 patients who met the inclusion criteria. They were further divided into training (n=321) and validation (n=79) groups. In the training group, we used univariate and multivariate COX regression to find independent risk factors for recurrent stroke and then created a nomogram. The assessment of the nomogram's discrimination and calibration was performed through the examination of various measures including the Consistency index (C-index), the area under the receiver operating characteristic (ROC) curves (AUC), and the calibration plots. Decision curve analysis (DCA) was used to evaluate the clinical utility of the nomogram by quantifying the net benefit to the patient under different threshold probabilities.

RESULTS

The nomogram for predicting recurrent ischemic stroke in symptomatic ICAS patients after stent placement utilizes six variables: coronary heart disease (CHD), smoking, multiple ICAS, systolic blood pressure (SBP), in-stent restenosis (ISR), and fasting plasma glucose. The C-index (0.884 for the training cohort and 0.87 for the validation cohort) and the time-dependent AUC (>0.7) indicated satisfactory discriminative ability of the nomogram. Furthermore, DCA indicated a clinical net benefit from the nomogram.

CONCLUSIONS

The predictive model constructed includes six predictive factors: CHD, smoking, multiple ICAS, SBP, ISR and fasting blood glucose. The model demonstrates good predictive ability and can be utilized to predict ischemic stroke recurrence in patients with symptomatic ICAS after successful stent placement.

Development and internal validation of machine learning-based models and external validation of existing risk scores for outcome prediction in patients with ischaemic stroke

Aims

We developed new machine learning (ML) models and externally validated existing statistical models [ischaemic stroke predictive risk score (iScore) and totalled health risks in vascular events (THRIVE) scores] for predicting the composite of recurrent stroke or all-cause mortality at 90 days and at 3 years after hospitalization for first acute ischaemic stroke (AIS).

Methods and results

In adults hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models [random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBOOST)] and externally validated the iScore and THRIVE scores for predicting the composite outcomes after AIS hospitalization, using data from 721 patients and 90 potential predictor variables. At 90 days and 3 years, 11 and 34% of patients, respectively, reached the composite outcome. For the 90-day prediction, the area under the receiver operating characteristic curve (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year prediction, the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE.

Conclusion

The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for long-term outcome prediction. Our findings warrant comparative analyses of ML and existing statistical method-based risk prediction tools for outcome prediction after AIS in new data sets.

Baseline Stroke Risk and Efficacy of Dual-Antiplatelet Therapy: A Post Hoc Analysis of the POINT Trial

BACKGROUND

High-risk transient ischemic attacks and minor ischemic strokes are followed by a variable risk of ischemic stroke. We aimed to determine how baseline stroke risk modified the efficacy of clopidogrel-aspirin (referred to here as dual-antiplatelet therapy [DAPT]) for transient ischemic attack and minor ischemic stroke.

METHODS

We performed an unplanned secondary analysis of the POINT trial (Platelet-Oriented Inhibition in New Transient Ischemic Attack and Minor Ischemic Stroke). We first evaluated the associations of the CHA2DS2-VASc and stroke prognosis instrument II (SPI-II) scores with the risk of incident ischemic stroke and major hemorrhage (intracranial hemorrhage or major systemic hemorrhage). We then tested for heterogeneity of the relative and absolute treatment effect of DAPT relative to aspirin across low- and high-risk patient subgroups.

RESULTS

A total of 4841 trial participants were included in this analysis, with 2400 participants assigned to treatment with short-term DAPT and 2430 participants to treatment with aspirin and placebo. The dichotomized SPI-II score, but not the CHA2DS2-VASc score (P=0.18), was associated with the risk of incident ischemic stroke. A high-risk SPI-II score (>3) was associated with greater risk of incident ischemic stroke (hazard ratio of incident ischemic stroke relative to low-risk SPI-II score of 1.84 [95% CI, 1.44-2.35]; P<0.001) and numerically greater risk of major hemorrhage though not meeting statistical significance (hazard ratio, 1.80 [95% CI, 0.90-3.57]; P=0.10). The relative risk reduction with DAPT was similar across SPI-II strata (Pinteraction=0.31). The absolute risk reduction for ischemic stroke with DAPT compared with aspirin was nearly 4-fold higher (2.80% versus 0.76%; number needed to treat, 31 versus 131) in the high-risk SPI-II stratum relative to the low-risk stratum. The absolute risk increase for major hemorrhage with DAPT compared with aspirin was 3-fold higher (0.84% versus 0.30%; number needed to harm, 119 versus 331) in the high-risk SPI-II stratum relative to the low-risk stratum.

CONCLUSIONS

Stratification by baseline stroke risk identifies a patient subgroup that derives greater absolute benefit from treatment with DAPT.

REGISTRATION

URL: https://www.clinicaltrials.gov; Unique identifier: NCT00991029.

Systematic Review of Machine Learning Applied to the Secondary Prevention of Ischemic Stroke

Ischemic stroke is a serious disease posing significant threats to human health and life, with the highest absolute and relative risks of a poor prognosis following the first occurrence, and more than 90% of strokes are attributable to modifiable risk factors. Currently, machine learning (ML) is widely used for the prediction of ischemic stroke outcomes. By identifying risk factors, predicting the risk of poor prognosis and thus developing personalized treatment plans, it effectively reduces the probability of poor prognosis, leading to more effective secondary prevention. This review includes 41 studies since 2018 that used ML algorithms to build prognostic prediction models for ischemic stroke, transient ischemic attack (TIA), and acute ischemic stroke (AIS). We analyzed in detail the risk factors used in these studies, the sources and processing methods of the required data, the model building and validation, and their application in different prediction time windows. The results indicate that among the included studies, the top five risk factors in terms of frequency were cardiovascular diseases, age, sex, national institutes of health stroke scale (NIHSS) score, and diabetes. Furthermore, 64% of the studies used single-center data, 65% of studies using imbalanced data did not perform data balancing, 88% of the studies did not utilize external validation datasets for model validation, and 72% of the studies did not provide explanations for their models. Addressing these issues is crucial for enhancing the credibility and effectiveness of the research, consequently improving the development and implementation of secondary prevention measures.

Intracranial arterial stenosis and recurrence in stroke patients with different risk stratifications by Essen stroke risk score

OBJECTIVES

We sought to investigate whether the prognostic value of intracranial arterial stenosis (ICAS) is consistent across different risk stratifications using the Essen Stroke Risk score (ESRS).

METHODS

We derived data from the Clopidogrel in High-Risk Patients with Acute Nondisabling Cerebrovascular Events trial. Patients without complete baseline brain imaging data were excluded. Participants were categorized into different risk groups based on ESRS (low risk, 0-2, and high risk ≥ 3). The main outcome was stroke recurrence within 3 and 12 months. Hazard ratios (HRs) and 95% confidence intervals (95%CIs) of ICAS, and other factors associated with stroke recurrence within 3 and 12 months were estimated using the Cox regression method.

RESULTS

During the 3-month follow-up, 54 patients (7.9%) had recurrent stroke in the low-risk group, and 39 patients (9.6%) had recurrent stroke in the high-risk group. ICAS was associated with a higher risk of stroke within 3 months (HR = 2.761; 95%CI = 1.538-4.957; P < 0.001) in the low-risk group, but not in the high-risk group (HR = 1.501; 95%CI = 0.701-3.213; P = 0.296). ICAS was independently associated with higher recurrent risk in the low-risk group (HR = 2.540; 95%CI = 1.472-4.381; P < 0.001), but not in the high-risk group (HR = 1.951; 95%CI = 0.977-3.893; P = 0.058) within 12 months.

CONCLUSION

ICAS was an independent predictor of both 3- and 12-month stroke recurrence in low-risk but not high-risk patients with minor ischemic stroke or transient ischemic attack according to ESRS stratification.

The Predictive Value of Essen and SPI-II on the Risk of 5-Year Recurrence in Chinese Patients with Acute Ischemic Stroke

Background

The risk prediction score for stroke recurrence is an important tool for stratifying patients based on the risk of cerebrovascular events and selecting potential preventive treatments.

Objective

The study aimed to validate the Essen Stroke Risk Score (ESRS) and Stroke Prognosis Instrument II (SPI-II) for predicting long-term risk of stroke recurrence and combined vascular events in Chinese patients with acute ischemic stroke (AIS).

Methods

A total of 876 consecutive patients with non-atrial fibrillation AIS were recruited. The Kaplan-Meier (KM) method was used to estimate the cumulative incidence of stroke recurrence and combined vascular events in different subgroups stratified by the ESRS and SPI-II scores. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the predictive value of the two scores for stroke recurrence and combined vascular events.

Results

The KM estimate for 5-year cumulative incidence of stroke recurrence and combined vascular events was 28.7% (95% confidence interval [CI], 25.4-32.0) and 35.6% (95% CI, 32.3-38.9), respectively, in Chinese AIS patients. The risk of stroke recurrence and combined vascular events were increased significantly with increasing ESRS and SPI-II scores. The ESRS and SPI-II scores had similar predictive accuracy for stroke recurrence (AUC 0.57 [95% CI 0.52-0.64] vs 0.59 [95% CI 0.55-0.64]) and combined vascular events (AUC 0.59 [95% CI 0.55-0.63] vs 0.62 [95% CI 0.58-0.66]) at 5 years.

Conclusion

In Chinese patients with AIS, both ESRS and SPI-II scores were able to stratify the risk of 5-year recurrent stroke and combined vascular events. The predictive power of the two scores were modest and a prediction model suitable for Chinese IS populations is needed.

Prediction of recurrent ischaemic stroke using radiomics data and machine learning methods in patients with acute ischaemic stroke: protocol for a multicentre, large sample, prospective observational cohort study in China

INTRODUCTION

Stroke is a leading cause of mortality and disability worldwide. Recurrent strokes result in prolonged hospitalisation and worsened functional outcomes compared with the initial stroke. Thus, it is critical to identify patients who are at high risk of stroke recurrence. This study is positioned to develop and validate a prediction model using radiomics data and machine learning methods to identify the risk of stroke recurrence in patients with acute ischaemic stroke (AIS).

METHODS AND ANALYSIS

A total of 1957 patients with AIS will be needed. Enrolment at participating hospitals will continue until the required sample size is reached, and we will recruit as many participants as possible. Multiple indicators including basic clinical data, image data, laboratory data, CYP2C19 genotype and follow-up data will be assessed at various time points during the registry, including baseline, 24 hours, 7 days, 1 month, 3 months, 6 months, 9 months and 12 months. The primary outcome was stroke recurrence. The secondary outcomes were death events, prognosis scores and adverse events. Imaging images were processed using deep learning algorithms to construct a programme capable of automatically labelling the lesion area and extracting radiomics features. The machine learning algorithms will be applied to integrate cross-scale, multidimensional data for exploratory analysis. Then, an ischaemic stroke recurrence prediction model of the best performance for patients with AIS will be established. Calibration, receiver operating characteristic and decision curve analyses will be evaluated.

ETHICS AND DISSEMINATION

This study has received ethical approval from the Medical Ethics Committee of the Second Affiliated Hospital of Nanchang University (medical research review No.34/2021), and informed consent will be obtained voluntarily. The research findings will be disseminated through publication in journals and presented at conferences.

TRIAL REGISTRATION NUMBER

ChiCTR2200055209.

Validation and comparison of the stroke prognosis instrument (SPI-II) and the essen stroke risk score (ESRS) in predicting stroke recurrence in Asian population

BACKGROUND

Currently, there are limited data on the accuracy of available risk scores to predict stroke recurrence in the Asian population.

METHOD

A single-center, retrospective cohort study was conducted among patients with acute ischemic stroke during January 2014 - December 2018. Longitudinal data with three years of follow-up among these patients were collected and validated through both electronic and manual chart review. The area under the receiver-operating curve (AUROC) method or C-statistic and calibration plot were used to evaluate and compare the Stroke Prognosis Instrument II (SPI-II) and the Essen Stroke Risk Score (ESRS) in predicting the long-term risk of recurrent ischemic stroke. The predictive performances of the two scores were compared using DeLong's method.

RESULTS

The study cohort consisted of 543 patients, including 181 and 362 patients with and without recurrent events. There were no significant differences in mean age and gender between the two groups. Recurrence cases tended to have significant more risk factors compared to those without events. Among cases with recurrent events, 134 (74.03%) and 65.74% (119) cases were classified as high-risk based on SPI-II and ESRS, respectively. The AUROC curve of the SPI-II and ESRS score was 0.646 (95% CI, 0.594-0.697) and 0.614 (95%CI, 0.563-0.665), respectively (p = 0.394). Based on the calibration plot, the SPI-II and ESRS scores showed similar moderate predictive performance on recurrence stroke with a C statistic (95% CI) of 0.655 (95% CI: 0.603-0.707) and 0.631 (95% CI 0.579-0.684), respectively.

CONCLUSION

Both ESRS and SPI-II scores had moderate predictive performance in Thai population.

A Nomogram for Predicting the Recurrence of Acute Non-Cardioembolic Ischemic Stroke: A Retrospective Hospital-Based Cohort Analysis

Non-cardioembolic ischemic stroke (IS) is the predominant subtype of IS. This study aimed to construct a nomogram for recurrence risks in patients with non-cardioembolic IS in order to maximize clinical benefits. From April 2015 to December 2019, data from consecutive patients who were diagnosed with non-cardioembolic IS were collected from Lanzhou University Second Hospital. The least absolute shrinkage and selection operator (LASSO) regression analysis was used to optimize variable selection. Multivariable Cox regression analyses were used to identify the independent risk factors. A nomogram model was constructed using the "rms" package in R software via multifactor Cox regression. The accuracy of the model was evaluated using the receiver operating characteristic (ROC), calibration curve, and decision curve analyses (DCA). A total of 729 non-cardioembolic IS patients were enrolled, including 498 (68.3%) male patients and 231 (31.7%) female patients. Among them, there were 137 patients (18.8%) with recurrence. The patients were randomly divided into training and testing sets. The Kaplan-Meier survival analysis of the training and testing sets consistently revealed that the recurrence rates in the high-risk group were significantly higher than those in the low-risk group (p < 0.01). Moreover, the receiver operating characteristic curve analysis of the risk score demonstrated that the area under the curve was 0.778 and 0.760 in the training and testing sets, respectively. The nomogram comprised independent risk factors, including age, diabetes, platelet-lymphocyte ratio, leukoencephalopathy, neutrophil, monocytes, total protein, platelet, albumin, indirect bilirubin, and high-density lipoprotein. The C-index of the nomogram was 0.752 (95% CI: 0.705~0.799) in the training set and 0.749 (95% CI: 0.663~0.835) in the testing set. The nomogram model can be used as an effective tool for carrying out individualized recurrence predictions for non-cardioembolic IS.

Thirteen-year trends in risk scores predictive values for subsequent stroke in patients with acute ischemic event

INTRODUCTION

A high residual risk of subsequent stroke suggested that the predictive ability of Stroke Prognosis Instrument-II (SPI-II) and Essen Stroke Risk Score (ESRS) may have changed over the years.

AIM

To explore the predictive values of the SPI-II and ESRS for 1-year subsequent stroke risk in a pooled analysis of three consecutive national cohorts in China over 13 years.

RESULTS

In the China National Stroke Registries (CNSRs), 10.7% (5297/50,374) of the patients had a subsequent stroke within 1 year; area under the curve (AUC) of SPI-II and ESRS was .60 (95% confidence interval [CI]: .59-.61) and .58 (95% CI: .57-.59), respectively. For SPI-II, the AUC was .60 (95% CI: .59-.62) in CNSR-I, .60 (95% CI: .59-.62) in CNSR-II, and .58 (95% CI: .56-.59) in CNSR-III over the past 13 years. The declining trend was also found in ESRS scale (CNSR-I: .60 [95% CI: .59-.61]; CNSR-II: .60 [95% CI: .59-.62]; and CNSR-III: .56 [95% CI: .55-.58]).

CONCLUSIONS

The predictive power of the traditional risk scores SPI-II and ESRS was limited and gradually decreased over the past 13 years, thus the scales may not be useful for current clinical practice. Further derivation of risk scales with additional imaging features and biomarkers may be warranted.

Strokes and Predictors of Outcomes

Stroke is a leading cause of long-term disability and fifth leading cause of death. Acute ischemic stroke, intracerebral hemorrhage, and subarachnoid hemorrhage, the 3 subtypes of strokes, have varying treatment modalities. Common themes in management advocate for early interventions to reduce morbidity and mortality but not all perception is supported through randomized controlled trials. Each stroke subtype has varying premorbid-related and ictus-related outcome predictive models that have differing sensitivities and specificities.

Value of Intraplaque Neovascularization on Contrast-Enhanced Ultrasonography in Predicting Ischemic Stroke Recurrence in Patients With Carotid Atherosclerotic Plaque

OBJECTIVE

Patients with a history of ischemic stroke are at risk for a second ischemic stroke. This study aimed to investigate the relationship between carotid plaque enhancement on perfluorobutane microbubble contrast-enhanced ultrasonography (CEUS) and future recurrent stroke, and to determine whether plaque enhancement can contribute to risk assessment for recurrent stroke compared with the Essen Stroke Risk Score (ESRS).

MATERIALS AND METHODS

This prospective study screened 151 patients with recent ischemic stroke and carotid atherosclerotic plaques at our hospital between August 2020 and December 2020. A total of 149 eligible patients underwent carotid CEUS, and 130 patients who were followed up for 15-27 months or until stroke recurrence were analyzed. Plaque enhancement on CEUS was investigated as a possible risk factor for stroke recurrence and as a possible adjunct to ESRS.

RESULTS

During follow-up, 25 patients (19.2%) experienced recurrent stroke. Patients with plaque enhancement on CEUS had an increased risk of stroke recurrence events (22/73, 30.1%) compared to those without plaque enhancement (3/57, 5.3%), with an adjusted hazard ratio (HR) of 38.264 (95% confidence interval [CI]:14.975-97.767; P < 0.001) according to a multivariable Cox proportional hazards model analysis, indicating that the presence of carotid plaque enhancement was a significant independent predictor of recurrent stroke. When plaque enhancement was added to the ESRS, the HR for stroke recurrence in the high-risk group compared to that in the low-risk group (2.188; 95% CI, 0.025-3.388) was greater than that of the ESRS alone (1.706; 95% CI, 0.810-9.014). A net of 32.0% of the recurrence group was reclassified upward appropriately by the addition of plaque enhancement to the ESRS.

CONCLUSION

Carotid plaque enhancement was a significant and independent predictor of stroke recurrence in patients with ischemic stroke. Furthermore, the addition of plaque enhancement improved the risk stratification capability of the ESRS.

Examining the Associations between Post-Stroke Cognitive Function and Common Comorbid Conditions among Stroke Survivors

A considerable complication for stroke survivors is the subsequent development of cognitive decline or dementia. In this study, the relationship between the inflammation-centered comorbidity burden on post-stroke cognitive function among community-dwelling stroke survivors capable of independent living was examined. Data for this secondary analysis were collected from stroke survivors (n = 97) participating in a randomized clinical trial. Participants provided baseline responses, regarding cognitive function (mini-mental status exam, MMSE; Montreal cognitive assessment, MoCA), history of stroke comorbid conditions, and the Stroke Prognosis Instrument-II (SPI-II), an index of stroke comorbidity and recurrent stroke risk within the next two years. Relationships and differences between groups were tested for significance using Spearman's correlation, Kruskal-Wallis, or Mann-Whitney U tests. Most stroke survivors (69%) had multiple comorbidities. Total SPI-II scores were negatively correlated to both MoCA and MMSE scores (r = -0.25, p = 0.01; r = -0.22, p = 0.03, respectively), and differences in MoCA scores among SPI-II risk groups (low, medium, high) were evident (p = 0.05). In contrast, there were no differences in MoCA or MMSE scores when comorbid conditions were examined individually. Lastly, no gender differences were evident in cognitive assessments. Our data support the premise that comorbidity's burden impacts post-stroke cognitive decline, more than a single comorbid condition. Inflammation may be an important component of this comorbidity burden. Future studies that operationalize this concept will better illuminate the complex phenomenon of post-stroke cognitive decline for improved clinical rehabilitation modalities.

Recurrence prediction of Essen Stroke Risk and Stroke Prognostic Instrument-II scores in ischemic stroke: A study of 5-year follow-up

OBJECTIVE

To evaluate the predictive accuracy of the Essen Stroke Risk Score and the Stroke Prognostic Instrument II score on the long-term recurrence in Chinese patients with acute ischemic stroke.

METHODS

Patients with acute ischemic stroke were enrolled and had completed ESRS and SPI-II scores. Patients were stratified according to the Essen Stroke Risk Score and Stroke Prognostic Instrument II score and were followed until stroke recurrence or composite endpoint event (stroke recurrence, myocardial infarction or cardiovascular death). We estimated stratified incidence rates and calculated the cumulative risks at 5 years using Kaplan-Meier estimates. We used receiver operating characteristic (ROC) curves to compare the predictive ability of the Essen Stroke Risk Score and Stroke Prognostic Instrument II score.

RESULTS

A total of 578 patients completed the follow-up. The cumulative 5-year event rates were 32.3% (95% CI, 28.2% to 36.4%) for recurrent stroke and 37.9% (95% CI: 33.8%-42.0%) for composite endpoint event. The cumulative risk of all outcomes increased with increasing risk scores. AUC for ESRS and SPI-II risk scores were 0.613 (95% CI: 0.565-0.661) and 0.613 (95% CI: 0.564-0.662) for 5-year stroke recurrence respectively and correspondingly 0.622 (95% CI: 0.576-0.668) and 0.627 (95% CI: 0.581-0.674) for composite endpoint events.

CONCLUSION

In Chinese patients with acute ischemic stroke, both Essen Stroke Risk Score and Stroke Prognostic Instrument II scores could equally stratify the risk of 5-year recurrent stroke and combined vascular events.

GSTCNet: Gated spatio-temporal correlation network for stroke mortality prediction

Stroke continues to be the most common cause of death in China. It has great significance for mortality prediction for stroke patients, especially in terms of analyzing the complex interactions between non-negligible factors. In this paper, we present a gated spatio-temporal correlation network (GSTCNet) to predict the one-year post-stroke mortality. Based on the four categories of risk factors: vascular event, chronic disease, medical usage and surgery, we designed a gated correlation graph convolution kernel to capture spatial features and enhance the spatial correlation between feature categories. Bi-LSTM represents the temporal features of five timestamps. The novel gated correlation attention mechanism is then connected to the Bi-LSTM to realize the comprehensive mining of spatio-temporal correlations. Using the data on 2275 patients obtained from the neurology department of a local hospital, we constructed a series of sequential experiments. The experimental results show that the proposed model achieves competitive results on each evaluation metric, reaching an AUC of 89.17%, a precision of 97.75%, a recall of 95.33% and an F1-score of 95.19%. The interpretability analysis of the feature categories and timestamps also verified the potential application value of the model for stroke.

Neural network-based clustering model of ischemic stroke patients with a maximally distinct distribution of 1-year vascular outcomes

Clustering stroke patients with similar characteristics to predict subsequent vascular outcome events is critical. This study aimed to compare several clustering methods, particularly a deep neural network-based model, and identify the best clustering method with a maximally distinct 1-year outcome in patients with ischemic stroke. Prospective stroke registry data from a comprehensive stroke center from January 2011 to July 2018 were retrospectively analyzed. Patients with acute ischemic stroke within 7 days of onset were included. The primary outcomes were the composite of all strokes (either hemorrhagic or ischemic), myocardial infarction, and all-cause mortality within one year. Neural network-based clustering models (deep lifetime clustering) were compared with other clustering models (k-prototype and semi-supervised clustering, SSC) and a conventional risk score (Stroke Prognostic Instrument-II, SPI-II) to obtain a distinct distribution of 1-year vascular events. Ultimately, 7,650 patients were included, and the 1-year primary outcome event occurred in 13.1%. The DLC-Kuiper UB model had a significantly higher C-index (0.674), log-rank score (153.1), and Brier score (0.08) than the other cluster models (SSC and DLC-MMD) and the SPI-II score. There were significant differences in primary outcome events among the 3 clusters (41.7%, 13.4%, and 6.5% in clusters 0, 1, and 2, respectively) when the DLC-Kuiper UB model was used. A neural network-based clustering model, the DLC-Kuiper UB model, can improve the clustering of stroke patients with a maximally distinct distribution of 1-year vascular outcomes among each cluster. Further studies are warranted to validate this deep neural network-based clustering model in ischemic stroke.

Machine Learning-Based Prediction of Subsequent Vascular Events After 6 Months in Chinese Patients with Minor Ischemic Stroke

Background

To develop and validate a machine learning model for predicting subsequent vascular events (SVE) 6 months after mild ischemic stroke (MIS) in Chinese patients.

Methods

A retrospective analysis was performed on 495 newly diagnosed MIS patients by collecting their basic information, past medical history, initial NIHSS score, symptoms, obstruction sites of MIS, and MRI results. According to the ratio of 7:3, the dataset was divided into a training set (n=346) and a testing set (n=149) through stratified random sampling. In the training set, the recursive feature elimination (RFE) was used to select the optimal combination of features, and two machine learning algorithms, including the logistic regression (LR) and support vector machines (SVM), were used to build the prediction model, which was further validated by using 5-fold cross-validation. The receiver operating characteristic (ROC) curve was used on the testing set to evaluate the model’s performance, and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated. The calibration curve and decision curve of the two models were further compared.

Results

SVE occurred in 56 cases (11.3%) of 495 patients with MIS during the 6-month follow-up. Finally, the best 15 predictive features were selected, and the top three predictive features were diabetes, posterior cerebral artery lesion, and fasting blood glucose in order. In the testing set, the AUC of the LR model was 0.929 (95% CI: 0.875–0.964), and its accuracy, sensitivity, and specificity were 0.832, 0.765, and 0.841, respectively. The AUC of the SVM model was 0.992 (95% CI: 0.962–1.000), and its accuracy, sensitivity, and specificity were 0.966, 0.824, and 0.985, respectively. The SVM model’s discrimination, calibration, and clinical validity are better than those of the LR model.

Conclusion

The predictive models developed using machine learning methods can predict the risk of SVE after 6 months following MIS in Chinese patients.

What is the added value of CT-angiography in patients with transient ischemic attack?

Background

Transient ischemic attack (TIA) is an important predictor for a pending stroke. Guidelines recommend a workup for TIA-patients similar to that of stroke patients, including an assessment of the extra- and intracranial arteries for vascular pathologies with direct therapeutic implications via computed tomography angiography (CTA). Aim of our study was a systematic analysis of TIA-patients receiving early CTA-imaging and to evaluate the predictive value of TIA-scores and clinical characteristics for ipsilateral vascular pathologies and the need of an invasive treatment.

Methods

We analysed clinical and imaging data from TIA patients being admitted to a tertiary university hospital between September 2015 and March 2018. Following subgroups were identified: 1) no- or low-grade vascular pathology 2) ipsilateral high-risk vascular pathology and 3) high-risk findings that needed invasive, surgical or interventional treatment. We investigated established TIA-scores (ABCD₂-, the ABCD₃- and the SPI-II score) and various clinical characteristics as predictive factors for ipsilateral vascular pathologies and the need for invasive treatment.

Results

Of 812 patients, 531 (65.4%) underwent initial CTA in the emergency department. In 121 (22.8%) patients, ipsilateral vascular pathologies were identified, of which 36 (6.7%) needed invasive treatment. The ABCD₂-, ABCD₃- and SPI-II-scores were not predictive for ipsilateral vascular pathologies or the need for invasive treatment. We identified male sex (OR 1.579, 95%CI 1.049–2.377, p = 0.029), a short duration of symptoms (OR 0.692, 95% CI 0.542–0.884, p = 0.003), arterial hypertension (OR 1.718, 95%CI 0.951–3.104, p = 0.073) and coronary heart disease (OR 1.916, 95%CI 1.184–3.101, p = 0.008) as predictors for ipsilateral vascular pathologies. As predictors for the need of invasive treatment, a short duration of symptoms (OR 0.565, 95%CI 0.378–0.846, p = 0.006), arterial hypertension (OR 2.612, 95%OR 0.895–7.621, p = 0.079) and hyperlipidaemia (OR 5.681, 95%CI 0.766–42.117, p = 0.089) as well as the absence of atrial fibrillation (OR 0.274, OR 0.082–0.917, p = 0.036) were identified.

Conclusion

More than every fifth TIA-patient had relevant vascular findings revealed by acute CTA. TIA-scores were not predictive for these findings. Patients with a short duration of symptoms and a vascular risk profile including coronary heart disease, arterial hypertension and hyperlipidaemia most likely might benefit from early CTA to streamline further diagnostics and therapy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12883-021-02523-y.

Program of Rehabilitative Exercise and Education to Avert Vascular Events After Non-Disabling Stroke or Transient Ischemic Attack (PREVENT Trial): A Randomized Controlled Trial

Background

Non-disabling stroke (NDS) and transient ischemic attack (TIA) herald the possibility of future, more debilitating vascular events. Evidence is conflicting about potency of exercise and education in reducing risk factors for second stroke.

Methods

Three-site, single-blinded, randomized controlled trial with 184 participants <3 months of NDS or TIA (mean age, 65 years; 66% male) randomized to usual care (UC) or UC + 12-week program of exercise and education (PREVENT). Primary (resting systolic blood pressure) and secondary outcomes (diastolic blood pressure [DBPrest], high-density lipoprotein cholesterol [HDL-C], low-density lipoprotein cholesterol [LDL-C], total cholesterol [TC], TC/HDL, triglycerides, fasting glucose, and body mass index) were assessed at baseline, post-intervention, and 6- and 12-month follow-up. Peak oxygen consumption (VO₂peak) was measured at baseline, post-intervention, 12-month assessments.

Results

Significant between-group differences at post-intervention favored PREVENT group over UC: DBPrest (mean difference [MD]: −3.2 mmHg, 95% confidence interval [CI]: −6.3, −.2, P = .04) and LDL-C (MD: −.31 mmol/L, 95% CI: −.42, −.20, P = .02). Trends of improvement in PREVENT group were noted in several variables between baseline and 6-month follow-up but not sustained at 12-month follow-up. Of note, VO₂ peak did not change over time in either group.

Conclusion

Impact of PREVENT on vascular risk factor reduction was more modest than anticipated, possibly because several outcome variables approximated normative values at baseline and training intensity may have been sub-optimal. Further investigation is warranted to determine when exercise and education programs are viable adjuncts to pharmaceutical management for reduction of risk factors for second stroke.

Clinical Trial Registration-URL:http://www.clinicaltrials.gov. Unique identifier: #NCT00885456

Interpretability analysis of one-year mortality prediction for stroke patients based on deep neural network

Clinically, physicians collect the benchmark medical data to establish archives for a stroke patient and then add the follow up data regularly. It has great significance on prognosis prediction for stroke patients. In this paper, we present an interpretable deep learning model to predict the one-year mortality risk on stroke. We design sub-modules to reconstruct features from original clinical data that highlight the dissimilarity and temporality of different variables. The model consists of Bidirectional Long Short-Term Memory (Bi-LSTM), in which a novel correlation attention module is proposed that takes the correlation of variables into consideration. In experiments, datasets are collected clinically from the department of neurology in a local AAA hospital. It consists of 2,275 stroke patients hospitalized in the department of neurology from 2014 to 2016. Our model achieves a precision of 0.9414, a recall of 0.9502 and an F1-score of 0.9415. In addition, we provide the analysis of the interpretability by visualizations with reference to clinical professional guidelines.

Risk Stratification in Patients with Ischemic Stroke and Residual Cardiovascular Risk with Current Secondary Prevention

Purpose

Suboptimal secondary prevention in patients with stroke causes a remaining cardiovascular risk desirable to reduce. We have validated a prognostic model for secondary preventive settings and estimated future cardiovascular risk and theoretical benefit of reaching guideline recommended risk factor targets.

Patients and Methods

The SMART-REACH (Secondary Manifestations of Arterial Disease-Reduction of Atherothrombosis for Continued Health) model for 10-year and lifetime risk of cardiovascular events was applied to 465 patients in the Norwegian Cognitive Impairment After Stroke (Nor-COAST) study, a multicenter observational study with two-year follow-up by linkage to national registries for cardiovascular disease and mortality. The residual risk when reaching recommended targets for blood pressure, low-density lipoprotein cholesterol, smoking cessation and antithrombotics was estimated.

Results

In total, 11.2% had a new event. Calibration plots showed adequate agreement between estimated and observed 2-year prognosis (C-statistics 0.63, 95% confidence interval 0.55–0.71). Median estimated 10-year risk of recurrent cardiovascular events was 42% (Interquartile range (IQR) 32–54%) and could be reduced to 32% by optimal guideline-based therapy. The corresponding numbers for lifetime risk were 70% (IQR 63–76%) and 61%. We estimated an overall median gain of 1.4 (IQR 0.2–3.4) event-free life years if guideline targets were met.

Conclusion

Secondary prevention was suboptimal and residual risk remains elevated even after optimization according to current guidelines. Considerable interindividual variation in risk exists, with a corresponding variation in benefit from intensification of treatment. The SMART-REACH model can be used to identify patients with the largest benefit from more intensive treatment and follow-up.

Predicting Recurrence for Patients With Ischemic Cerebrovascular Events Based on Process Discovery and Transfer Learning

The recurrence of Ischemic cerebrovascular events (ICE) often results in a high rate of mortality and disability. However, due to the lack of labeled follow-up data in hospitals, prediction methods using traditional machine learning are usually not available or reliable. Therefore, we propose a new framework for predicting the long-term recurrence risk in patients with ICE after discharge from hospitals based on process mining and transfer learning, to point out high-risk patients for intervention. First, process models are discovered from clinical guidelines for analyzing the similarity of ICE population data collected by different medical institutions, and the control flow found are taken as added characteristics of patients. Then we use the in-hospital data (target domain) and the national stroke screening data (source domain), to develop risk prediction models applying instance filter and weight-based transfer learning method. To verify our method, 205 cases from a tertiary hospital and 2954 cases from the screening cohort (2015-2017) are tested. Experimental results show that our framework can improve the performance of three instance-based transfer algorithms. This study provides a comprehensive and efficient approach for applying transfer learning, to alleviate the limitation of insufficient labeled follow-up data in hospitals.

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

Background: The long-term risk of recurrent ischemic stroke, estimated to be between 17% and 30%, cannot be reliably assessed at an individual level. Our goal was to study whether machine-learning can be trained to predict stroke recurrence and identify key clinical variables and assess whether performance metrics can be optimized. Methods: We used patient-level data from electronic health records, six interpretable algorithms (Logistic Regression, Extreme Gradient Boosting, Gradient Boosting Machine, Random Forest, Support Vector Machine, Decision Tree), four feature selection strategies, five prediction windows, and two sampling strategies to develop 288 models for up to 5-year stroke recurrence prediction. We further identified important clinical features and different optimization strategies. Results: We included 2091 ischemic stroke patients. Model area under the receiver operating characteristic (AUROC) curve was stable for prediction windows of 1, 2, 3, 4, and 5 years, with the highest score for the 1-year (0.79) and the lowest score for the 5-year prediction window (0.69). A total of 21 (7%) models reached an AUROC above 0.73 while 110 (38%) models reached an AUROC greater than 0.7. Among the 53 features analyzed, age, body mass index, and laboratory-based features (such as high-density lipoprotein, hemoglobin A1c, and creatinine) had the highest overall importance scores. The balance between specificity and sensitivity improved through sampling strategies. Conclusion: All of the selected six algorithms could be trained to predict the long-term stroke recurrence and laboratory-based variables were highly associated with stroke recurrence. The latter could be targeted for personalized interventions. Model performance metrics could be optimized, and models can be implemented in the same healthcare system as intelligent decision support for targeted intervention.

Early detection of small volume stroke and thromboembolic sources with computed tomography: Rationale and design of the ENCLOSE study

Background

Computed tomography is the most frequently used imaging modality in acute stroke imaging protocols. Detection of small volume infarcts in the brain and cardioembolic sources of stroke is difficult with current computed tomography protocols. Furthermore, the role of computed tomography findings to predict recurrent ischemic stroke is unclear. With ENCLOSE, we aim to improve (1) the detection of small volume infarcts with thin slice computed tomography perfusion (CTP) images and thromboembolic source with cardiac computed tomography techniques in the acute stage of ischemic stroke and (2) prediction of recurrent ischemic stroke with computed tomography-derived predictors.

Methods/design: ENCLOSE is a prospective multicenter observational cohort study, which will be conducted in three Dutch stroke centers (ClinicalTrials.gov Identifier: NCT04019483). Patients (≥18 years) with suspected acute ischemic stroke who undergo computed tomography imaging within 9 h after symptom onset are eligible. Computed tomography imaging includes non-contrast CT, CTP, and computed tomography angiography (CTA) from base of the heart to the top of the brain. Dual-energy CT data will be acquired when possible, and thin-slice CTP reconstructions will be obtained in addition to standard 5 mm CTP data. CTP data will be processed with commercially available software and locally developed model-based methods. The post-processed thin-slice CTP images will be compared to the standard CTP images and to magnetic resonance diffusion-weighted imaging performed within 48 h after admission. Detection of cardioembolic sources of stroke will be evaluated on the CTA images. Recurrence will be evaluated 90 days and two years after the index event. The added value of imaging findings to prognostic models for recurrent ischemic stroke will be evaluated.

Conclusion

The aim of ENCLOSE is to improve early detection of small volume stroke and thromboembolic sources and to improve prediction of recurrence in patients with acute ischemic stroke.

Risk of Ischemic Stroke after an Inpatient Hospitalization for Transient Ischemic Attack in the United States

INTRODUCTION

A diagnosis of transient ischemic attack (TIA) must be followed by prompt investigation and rapid initiation of measures to prevent stroke. Prior studies evaluating the risk of stroke after TIA were conducted in the emergency room or clinic settings. Experience of patients admitted to the hospital after a TIA is not well known. We sought to assess the early risk of ischemic stroke after inpatient hospitalization for TIA.

METHODS

We used the 2010-2015 Nationwide Readmissions Database to identify all hospitalizations with the primary discharge diagnosis of TIA and investigated the incidence of ischemic stroke readmissions within 90 days of discharge from the index hospitalization.

RESULTS

Of 639,569 index TIA admissions discharged alive (mean ± SD age 70.4 ± 14.4 years, 58.7% female), 9,131 (1.4%) were readmitted due to ischemic stroke within 90 days. Male sex, head/neck vessel atherosclerosis, hypertension, diabetes, atrial flutter/fibrillation, previous history of TIA/stroke, illicit drug use, and higher Charlson Comorbidity Index score were independently associated with readmissions due to ischemic stroke. Ischemic stroke readmissions were associated with excess mortality, discharge disposition other than to home, and elevated cost.

CONCLUSIONS

Patients hospitalized for TIA have a lower risk of ischemic stroke compared to that reported in the studies based on the emergency room and/or outpatient clinic evaluation. Among these patients, those with cardiovascular comorbidities remain at a higher risk of readmission due to ischemic stroke despite undergoing an inpatient evaluation and should therefore be the target for future preventive strategies.

A score to predict one-year risk of recurrence after acute ischemic stroke

BACKGROUND

An acute ischemic stroke carries a substantial risk of further recurrences. We aimed at developing and validating a prognostic tool to predict one-year stroke recurrence after acute ischemic stroke.

METHODS

An integer score was derived by Cox regression analysis on a hospital-referred cohort of 3246 acute ischemic stroke patients from Switzerland, and tested for external validity in three similar independent cohorts from Athens (n = 2495), Milan (n = 1279), and Helsinki (n = 714) by means of calibration and discrimination.

RESULTS

In the derivation cohort, the recurrence rate was 7% (n = 228/3246). We developed a nine-point score comprising: previous stroke or transient ischemic attack (1-point), stroke mechanism (small vessel disease and unknown mechanism: 0-points; rare stroke mechanism: 3-points; other mechanisms: 1-point), pre-stroke antiplatelets (1-point), active malignancy (2-points), chronic cerebrovascular lesions on imaging (1-point) and absence of early ischemic changes on first imaging (1-point). In the derivation cohort, the one-year risk of re-stroke was 3.0% (95%CI 1.9-4.1) in 932 (29%) patients with a score 0-1, 7.2% (6.1-8.3) in 2038 (63%) with a score 2-4, and 19.2% (14.6-23.9) in 276 (8%) with a score ≥ 5. The score calibrated well in the Athens (recurrences = 208/2495), but not in the Helsinki (recurrences = 15/714) or Milan (recurrences = 65/1279) cohorts. The AUC was 0.67 in the derivation cohort, and 0.56, 0.70, and 0.63 in the Athens, Helsinki, and Milan cohorts, respectively.

CONCLUSION

We developed a score to predict one-year stroke recurrence risk in patients with acute ischemic stroke. Since the score was not completely validated when applied to external datasets where it displayed poor to fair calibration and discrimination, additional efforts are required to ameliorate our accuracy for predicting stroke recurrence, by better refining this prognostic tool or developing new ones. Clinical and radiological markers of established cerebrovascular disease and stroke etiology were better predictors than the usual demographic vascular risk factors.

Prediction of long-term recurrent ischemic stroke: the added value of non-contrast CT, CT perfusion, and CT angiography

Purpose

The aim of this study was to evaluate whether the addition of brain CT imaging data to a model incorporating clinical risk factors improves prediction of ischemic stroke recurrence over 5 years of follow-up.

Methods

A total of 638 patients with ischemic stroke from three centers were selected from the Dutch acute stroke study (DUST). CT-derived candidate predictors included findings on non-contrast CT, CT perfusion, and CT angiography. Five-year follow-up data were extracted from medical records. We developed a multivariable Cox regression model containing clinical predictors and an extended model including CT-derived predictors by applying backward elimination. We calculated net reclassification improvement and integrated discrimination improvement indices. Discrimination was evaluated with the optimism-corrected c-statistic and calibration with a calibration plot.

Results

During 5 years of follow-up, 56 patients (9%) had a recurrence. The c-statistic of the clinical model, which contained male sex, history of hyperlipidemia, and history of stroke or transient ischemic attack, was 0.61. Compared with the clinical model, the extended model, which contained previous cerebral infarcts on non-contrast CT and Alberta Stroke Program Early CT score greater than 7 on mean transit time maps derived from CT perfusion, had higher discriminative performance (c-statistic 0.65, P = 0.01). Inclusion of these CT variables led to a significant improvement in reclassification measures, by using the net reclassification improvement and integrated discrimination improvement indices.

Conclusion

Data from CT imaging significantly improved the discriminatory performance and reclassification in predicting ischemic stroke recurrence beyond a model incorporating clinical risk factors only.

Electronic supplementary material

The online version of this article (10.1007/s00234-020-02526-5) contains supplementary material, which is available to authorized users.

Matrix Gla protein polymorphism rs1800801 associates with recurrence of ischemic stroke

The MGP single nucleotide polymorphism (SNP) rs1800801 has previously been associated with recurrent ischemic stroke in a Spanish cohort. Here, we tested for association of this SNP with ischemic stroke recurrence in a North American Caucasian cohort. Acute ischemic stroke patients admitted between 10/2009 and 12/2016 at three hospitals within a large healthcare system in the northeastern United States that were enrolled in a healthcare system-wide exome sequencing program were retrospectively reviewed. Patients with recurrent stroke within 1 year after index event were compared to those without recurrence. Of 9,348 suspected acute ischemic strokes admitted between 10/2009 and 12/2016, 1,727 (18.5%) enrolled in the exome-sequencing program. Among those, 1,068 patients had exome sequencing completed and were eligible for inclusion. Recurrent stroke within the first year of stroke was observed in 79 patients (7.4%). In multivariable analysis, stroke prior to the index stroke (OR 9.694, 95% CI 5.793-16.224, p ≤ 0.001), pro-coagulant status (OR = 3.563, 95% CI 1.504-8.443, p = 0.004) and the AA genotype of SNP rs1800801 (OR = 2.408, 95% CI 1.079-4.389, p = 0.004) were independently associated with recurrent stroke within the first year. The AA genotype of the MGP SNP rs1800801 is associated with recurrence within the first year after ischemic stroke in North American Caucasians. Study of stroke subtypes and additional populations will be required to determine if incorporation of allelic status at this SNP into current risk scores improves prediction of recurrent ischemic stroke.

Prevalence and predictors of statin utilization among patient populations at high vascular risk in Ghana

BACKGROUND

Inadequate implementation of evidence-based preventive measures for individuals at high risk of cardiovascular disease (CVD) will only worsen the current epidemic of CVDs in sub-Saharan Africa. We assessed rates and predictors of statin utilization among two high CVD risk patient populations, people with type 2 diabetes mellitus (T2DM) and those with stroke, encountered across five hospitals in Ghana.

METHODS

A cross-sectional study among 1427 patients with T2DM and 159 stroke survivors encountered at 5 hospitals (1 primary-level, 2 secondary level and 2 tertiary level) in Ghana between July 2015 and June 2018. We collected baseline demographic and clinical details including statin prescription from medical records. Factors associated with statin prescription among T2DM for primary prevention and stroke survivors for secondary prevention were evaluated using multivariate logistic regression analysis.

RESULTS

Among patients with T2DM without CVDs, 240 (16.8%) were on statins for primary prevention. Factors associated with statin use among diabetics expressed as aOR (95% CI) were being treated at a tertiary level hospital 5.86 (3.22-10.68), hypertension comorbidity 1.80 (1.25-2.60), and lower income 0.43 (0.26-0.70). Among 159 stroke survivors, 22 (14.0%) were on statins with the following associated factors: lower income 0.16 (0.03-0.77), secondary level vs. tertiary level education 0.21 (0.05-0.97) and having T2DM 4.69 (1.63-13.49).

CONCLUSION

Approximately 1 in 6 individuals with T2DM without CVD and 1 in 7 stroke survivors are prescribed statins in Ghana. Efforts to bridge this practice gap and improve access to life saving preventative medications for CVD risk reduction in low-and-middle income countries are urgently warranted.

An analysis of the risk of perioperative ischemic stroke in patients undergoing non-cardiovascular and non-neurological surgeries

Objectives: This study aimed to assess the preoperative risk factor for perioperative ischemic stroke (PIS) in patients undergoing non-cardiovascular and non-neurological surgeries.Methods: Patients were retrospectively enrolled and grouped into two groups at a ratio of 1:2 according to their PIS status, i.e. patients with PIS in disease group, and patients without PIS in control group. Univariate analysis and multivariate logistic regression analysis were performed on admission laboratory test indices and preoperative risk factors for stroke. The pooled cohort equation (PCE), Essen Stroke Risk Score (ESRS), and Stroke Prognostic Instrument II (SPI-II) were used to separately assess the risk of stroke in patients with or without a history of stroke.Results: There were significant differences between the two groups in the levels of high-density lipoprotein cholesterol (HDL-C), prealbumin, renal insufficiency, dyslipidemia, coronary heart disease, anemia, and hemoglobin; the incidence of electrolyte disturbance; and previous histories of smoking, drinking, and stroke. Multivariate logistic regression analysis showed that renal insufficiency, histories of smoking and stroke, and decreased HDL-C can increase the risk of PIS. There were no significant differences between the disease group and the control group in ESRS or SPI-II score in patients with stroke history. There was a significant difference between the two groups in the risk of PIS evaluated by PCE in patients without stroke history.Conclusions: History of stroke and smoking, renal insufficiency, and low HDL-C are independent risk factors for PIS. It is feasible to assess the risk of stroke in preoperative patients using PCE in clinical practice.

Blood Biomarkers for Stroke Diagnosis and Management

Biomarkers are objective indicators used to assess normal or pathological processes, evaluate responses to treatment and predict outcomes. Many blood biomarkers already guide decision-making in clinical practice. In stroke, the number of candidate biomarkers is constantly increasing. These biomarkers include proteins, ribonucleic acids, lipids or metabolites. Although biomarkers have the potential to improve the diagnosis and the management of patients with stroke, there is currently no marker that has demonstrated sufficient sensitivity, specificity, rapidity, precision, and cost-effectiveness to be used in the routine management of stroke, thus highlighting the need for additional work. A better standardization of clinical, laboratory and statistical procedures between centers is indispensable to optimize biomarker performance. This review focuses on blood biomarkers that have shown promise for translation into clinical practice and describes some newly reported markers that could add to routine stroke care. Avenues for the discovery of new stroke biomarkers and future research are discussed. The description of the biomarkers is organized according to their expected application in clinical practice: diagnosis, treatment decision, and outcome prediction.

Clinical Risk Score for Predicting Recurrence Following a Cerebral Ischemic Event

Introduction: Recurrent stroke has a higher rate of death and disability. A number of risk scores have been developed to predict short-term and long-term risk of stroke following an initial episode of stroke or transient ischemic attack (TIA) with limited clinical utilities. In this paper, we review different risk score models and discuss their validity and clinical utilities.

Methods: The PubMed bibliographic database was searched for original research articles on the various risk scores for risk of stroke following an initial episode of stroke or TIA. The validation of the models was evaluated by examining the internal and external validation process as well as statistical methodology, the study power, as well as the accuracy and metrics such as sensitivity and specificity.

Results: Different risk score models have been derived from different study populations. Validation studies for these risk scores have produced conflicting results. Currently, ABCD² score with diffusion weighted imaging (DWI) and Recurrence Risk Estimator at 90 days (RRE-90) are the two acceptable models for short-term risk prediction whereas Essen Stroke Risk Score (ESRS) and Stroke Prognosis Instrument-II (SPI-II) can be useful for prediction of long-term risk.

Conclusion: The clinical risk scores that currently exist for predicting short-term and long-term risk of recurrent cerebral ischemia are limited in their performance and clinical utilities. There is a need for a better predictive tool which can overcome the limitations of current predictive models. Application of machine learning methods in combination with electronic health records may provide platform for development of new-generation predictive tools.

Quality of Care for Veterans With Transient Ischemic Attack and Minor Stroke

Importance

The timely delivery of guideline-concordant care may reduce the risk of recurrent vascular events for patients with transient ischemic attack (TIA) and minor stroke. Although many health care organizations measure stroke care quality, few evaluate performance for patients with TIA or minor stroke, and most include only a limited subset of guideline-recommended processes.

Objective

To assess the quality of guideline-recommended TIA and minor stroke care across the Veterans Health Administration (VHA) system nationwide.

Design, Setting, and Participants

This cohort study included 8201 patients with TIA or minor stroke cared for in any VHA emergency department (ED) or inpatient setting during federal fiscal year 2014 (October 1, 2013, through September 31, 2014). Patients with length of stay longer than 6 days, ventilator use, feeding tube use, coma, intensive care unit stay, inpatient rehabilitation stay before discharge, or receipt of thrombolysis were excluded. Outlier facilities for each process of care were identified by constructing 95% CIs around the facility pass rate and national pass rate sites when the 95% CIs did not overlap. Data analysis occurred from January 16, 2016, through June 30, 2017.

Main Outcomes and Measures

Ten elements of care were assessed using validated electronic quality measures.

Results

In the 8201 patients included in the study (mean [SD] age, 68.8 [11.4] years; 7877 [96.0%] male; 4856 [59.2%] white), performance varied across elements of care: brain imaging by day 2 (6720/7563 [88.9%]; 95% CI, 88.2%-89.6%), antithrombotic use by day 2 (6265/7477 [83.8%]; 95% CI, 83.0%-84.6%), hemoglobin A1c measurement by discharge or within the preceding 120 days (2859/3464 [82.5%]; 95% CI, 81.2%-83.8%), anticoagulation for atrial fibrillation by day 7 after discharge (1003/1222 [82.1%]; 95% CI, 80.0%-84.2%), deep vein thrombosis prophylaxis by day 2 (3253/4346 [74.9%]; 95% CI, 73.6%-76.2%), hypertension control by day 90 after discharge (4292/5979 [71.8%]; 95% CI, 70.7%-72.9%), neurology consultation by day 1 (5521/7823 [70.6%]; 95% CI, 69.6%-71.6%), electrocardiography by day 2 or within 1 day prior (5073/7570 [67.0%]; 95% CI, 65.9%-68.1%), carotid artery imaging by day 2 or within 6 months prior (4923/7685 [64.1%]; 95% CI, 63.0%-65.2%), and moderate- to high-potency statin prescription by day 7 after discharge (3329/7054 [47.2%]; 95% CI, 46.0%-48.4%). Performance varied substantially across facilities (eg, neurology consultation had a facility outlier rate of 53.0%). Performance was higher for admitted patients than for patients cared for only in EDs with the greatest disparity for carotid artery imaging (4478/5927 [75.6%] vs 445/1758 [25.3%]; P < .001).

Conclusions and Relevance

This national study of VHA system quality of care for patients with TIA or minor stroke identified opportunities to improve care quality, particularly for patients who were discharged from the ED. Health care systems should engage in ongoing TIA care performance assessment to complement existing stroke performance measurement.

Processes of Care Associated With Risk of Mortality and Recurrent Stroke Among Patients With Transient Ischemic Attack and Nonsevere Ischemic Stroke

IMPORTANCE

Early evaluation and management of patients with transient ischemic attack (TIA) and nonsevere ischemic stroke improves outcomes.

OBJECTIVE

To identify processes of care associated with reduced risk of death or recurrent stroke among patients with TIA or nonsevere ischemic stroke.

DESIGN, SETTING, AND PARTICIPANTS

This cohort study included all patients with TIA or nonsevere ischemic stroke at Department of Veterans Affairs emergency department or inpatient settings from October 2010 to September 2011. Multivariable logistic regression was used to model associations of processes of care and without-fail care, defined as receiving all guideline-concordant processes of care for which patients are eligible, with risk of death and recurrent stroke. Data were analyzed from March 2018 to April 2019.

MAIN OUTCOMES AND MEASURES

Risk of all-cause mortality and recurrent ischemic stroke at 90 days and 1 year was calculated. Overall, 28 processes of care were examined. Without-fail care was assessed for 6 processes: brain imaging, carotid artery imaging, hypertension medication intensification, high- or moderate-potency statin therapy, antithrombotics, and anticoagulation for atrial fibrillation.

RESULTS

Among 8076 patients, the mean (SD) age was 67.8 (11.6) years, 7752 patients (96.0%) were men, 5929 (73.4%) were white, 474 (6.1%) had a recurrent ischemic stroke within 90 days, 793 (10.7%) had a recurrent ischemic stroke within 1 year, 320 (4.0%) died within 90 days, and 814 (10.1%) died within 1 year. Overall, 9 processes were independently associated with lower odds of both 90-day and 1-year mortality after adjustment for multiple comparisons: carotid artery imaging (90-day adjusted odds ratio [aOR], 0.49; 95% CI, 0.38-0.63; 1-year aOR, 0.61; 95% CI, 0.52-0.72), antihypertensive medication class (90-day aOR, 0.58; 95% CI, 0.45-0.74; 1-year aOR, 0.70; 95% CI, 0.60-0.83), lipid measurement (90-day aOR, 0.68; 95% CI, 0.51-0.90; 1-year aOR, 0.64; 95% CI, 0.53-0.78), lipid management (90-day aOR, 0.46; 95% CI, 0.33-0.65; 1-year aOR, 0.67; 95% CI, 0.53-0.85), discharged receiving statin medication (90-day aOR, 0.51; 95% CI, 0.36-0.73; 1-year aOR, 0.70; 95% CI, 0.55-0.88), cholesterol-lowering medication intensification (90-day aOR, 0.47; 95% CI, 0.26-0.83; 1-year aOR, 0.56; 95% CI, 0.41-0.77), antithrombotics by day 2 (90-day aOR, 0.56; 95% CI, 0.40-0.79; 1-year aOR, 0.69; 95% CI, 0.55-0.87) or at discharge (90-day aOR, 0.59; 95% CI, 0.41-0.86; 1-year aOR, 0.69; 95% CI, 0.54-0.88), and neurology consultation (90-day aOR, 0.67; 95% CI, 0.52-0.87; 1-year aOR, 0.74; 95% CI, 0.63-0.87). Anticoagulation for atrial fibrillation was associated with lower odds of 1-year mortality only (aOR, 0.59; 95% CI, 0.40-0.85). No processes were associated with reduced risk of recurrent stroke after adjustment for multiple comparisons. The rate of without-fail care was 15.3%; 1216 patients received all guideline-concordant processes of care for which they were eligible. Without-fail care was associated with a 31.2% lower odds of 1-year mortality (aOR, 0.69; 95% CI, 0.55-0.87) but was not independently associated with stroke risk.

CONCLUSIONS AND RELEVANCE

Patients who received 6 readily available processes of care had lower adjusted mortality 1 year after TIA or nonsevere ischemic stroke. Clinicians caring for patients with TIA and nonsevere ischemic stroke should seek to ensure that patients receive all guideline-concordant processes of care for which they are eligible.

Thinking About the Future: A Review of Prognostic Scales Used in Acute Stroke

Background: There are many prognostic scales that aim to predict functional outcome following acute stroke. Despite considerable research interest, these scales have had limited impact in routine clinical practice. This may be due to perceived problems with internal validity (quality of research), as well as external validity (generalizability of results). We set out to collate information on exemplar stroke prognosis scales, giving particular attention to the scale content, derivation, and validation.

Methods: We performed a focused literature search, designed to return high profile scales that use baseline clinical data to predict mortality or disability. We described prognostic utility and collated information on the content, development and validation of the tools. We critically appraised chosen scales based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modeling Studies (CHARMS).

Results: We chose 10 primary scales that met our inclusion criteria, six of which had revised/modified versions. Most primary scales used 5 input variables (range: 4–13), with substantial overlap in the variables included. All scales included age, eight included a measure of stroke severity, while five scales incorporated pre-stroke level of function (often using modified Rankin Scale), comorbidities and classification of stroke type. Through our critical appraisal, we found issues relating to excluding patients with missing data from derivation studies, and basing the selection of model variable on significance in univariable analysis (in both cases noted for six studies). We identified separate external validation studies for all primary scales but one, with a total of 60 validation studies.

Conclusions: Most acute stroke prognosis scales use similar variables to predict long-term outcomes and most have reasonable prognostic accuracy. While not all published scales followed best practice in development, most have been subsequently validated. Lack of clinical uptake may relate more to practical application of scales rather than validity. Impact studies are now necessary to investigate clinical usefulness of existing scales.

Stroke Minimization through Additive Anti-atherosclerotic Agents in Routine Treatment (SMAART): study protocol for a randomized controlled trial

Background

There is an unprecedented rise in the prevalence of stroke in sub-Saharan Africa (SSA). Secondary prevention guidelines recommend that antihypertensive, statin and antiplatelet therapy be initiated promptly after ischemic stroke and adhered to in a persistent fashion to achieve optimal vascular-risk reduction. However, these goals are seldom realized in routine clinical care settings in SSA due to logistical challenges.

We seek to assess whether a polypill containing fixed doses of three antihypertensive agents, a statin and antiplatelet therapy taken once daily per os for 12 months among recent stroke survivors would result in carotid intimal thickness regression compared with usual care (UC).

Methods

The Stroke Minimization through Additive Anti-atherosclerotic Agents in Routine Treatment (SMAART) trial is a phase 2, open-label, evaluator-blinded trial involving 120 Ghanaian recent-ischemic-stroke survivors. Using a computer-generated sequence, patients will be randomly allocated 1:1 into either the intervention arm or UC. Patients in the intervention arm will receive Polycap DS® (containing aspirin, 100 mg; atenolol, 50 mg; ramipril, 5 mg; thiazide, 12.5 mg; simvastatin, 20 mg) taken as two capsules once daily. Patients in the UC will receive separate, individual secondary preventive medications prescribed at the physician’s discretion. Both groups will be followed for 12 months to assess changes in carotid intimal thickness regression – a surrogate marker of atherosclerosis – as primary outcome measure. Secondary outcome measures include adherence to therapy, safety and tolerability, health-related quality of life, patient satisfaction, functional status, depression and cognitive dysfunction.

Discussion

An efficacy-suggesting SMAART trial could inform the future design of a multi-center, double-blinded, placebo-controlled, parallel-group, randomized controlled trial comparing the clinical efficacy of the polypill strategy for vascular risk moderation among stroke survivors in SSA.

Trial registration

ClinicalTrials.gov, ID: NCT03329599. Registered on 11 February 2017.

Electronic supplementary material

The online version of this article (10.1186/s13063-018-2564-0) contains supplementary material, which is available to authorized users.

Predictors of Stroke Events in Patients with Transient Ischemic Attack Attributable to Intracranial Stenotic Lesions

Objective The purpose of this study was to identify the predictors of subsequent ischemic stroke events in patients with transient ischemic attack (TIA) attributable to intracranial arterial occlusive lesions. Methods The study population included 82 patients (55 men; mean age, 69.3±12.1 years) with TIA caused by intracranial arterial occlusive lesions who were admitted to our stroke care unit within 48 h of the onset of a TIA between April 2008 and November 2015. TIA was diagnosed if focal neurological symptoms ascribable to a vascular etiology lasted less than 24 h, irrespective of the presence of ischemic insults on imaging. The primary endpoint was an ischemic stroke event within 90 days of the onset of a TIA. Results The 90-day risk of ischemic stroke after the onset of a TIA was 14.6% [95% confidence interval (CI): 8.6-23.9%]. Cox proportional hazards multivariate analyses revealed that diffusion-weighted imaging (DWI) positivity [hazard ratio (HR), 8.73; 95%CI, 2.20-41.59; p=0.002], prior ischemic stroke (HR, 4.03; 95%CI, 1.07-15.99; p=0.040), and a high serum level of alkaline phosphatase (ALP) on admission (HR, 1.15; 95%CI, 1.05-1.26; p=0.002, for every +10 U/L) were significant independent predictors of ischemic stroke within 90 days after the onset of a TIA. Conclusion Our results suggested that patients with a TIA attributable to intracranial artery disease who showed DWI lesions, prior ischemic stroke, or high serum levels of ALP on admission were at high risk of subsequent ischemic stroke events.

Targeting Pioglitazone Hydrochloride Therapy After Stroke or Transient Ischemic Attack According to Pretreatment Risk for Stroke or Myocardial Infarction

Importance

There is growing recognition that patients may respond differently to therapy and that the average treatment effect from a clinical trial may not apply equally to all candidates for a therapy.

Objective

To determine whether, among patients with an ischemic stroke or transient ischemic attack and insulin resistance, those at higher risk for future stroke or myocardial infarction (MI) derive more benefit from the insulin-sensitizing drug pioglitazone hydrochloride compared with patients at lower risk.

Design, Setting, and Participants

A secondary analysis was conducted of the Insulin Resistance Intervention After Stroke trial, a double-blind, placebo-controlled trial of pioglitazone for secondary prevention. Patients were enrolled from 179 research sites in 7 countries from February 7, 2005, to January 15, 2013, and were followed up for a mean of 4.1 years through the study's end on July 28, 2015. Eligible participants had a qualifying ischemic stroke or transient ischemic attack within 180 days of entry and insulin resistance without type 1 or type 2 diabetes.

Interventions

Pioglitazone or matching placebo.

Main Outcomes and Measures

A Cox proportional hazards regression model was created using baseline features to stratify patients above or below the median risk for stroke or MI within 5 years. Within each stratum, the efficacy of pioglitazone for preventing stroke or MI was calculated. Safety outcomes were death, heart failure, weight gain, and bone fracture.

Results

Among 3876 participants (1338 women and 2538 men; mean [SD] age, 63 [11] years), the 5-year risk for stroke or MI was 6.0% in the pioglitazone group among patients at lower baseline risk compared with 7.9% in the placebo group (absolute risk difference, -1.9% [95% CI, -4.4% to 0.6%]). Among patients at higher risk, the risk was 14.7% in the pioglitazone group vs 19.6% for placebo (absolute risk difference, -4.9% [95% CI, -8.6% to 1.2%]). Hazard ratios were similar for patients below or above the median risk (0.77 vs 0.75; P = .92). Pioglitazone increased weight less among patients at higher risk but increased the risk for fracture more.

Conclusions and Relevance

After an ischemic stroke or transient ischemic attack, patients at higher risk for stroke or MI derive a greater absolute benefit from pioglitazone compared with patients at lower risk. However, the risk for fracture is also higher.

Trial Registration

clinicaltrials.gov Identifier: NCT00091949.

Recent advances in the management of transient ischemic attacks

Significant advances in our understanding of transient ischemic attack (TIA) have taken place since it was first recognized as a major risk factor for stroke during the late 1950's. Recently, numerous studies have consistently shown that patients who have experienced a TIA constitute a heterogeneous population, with multiple causative factors as well as an average 5–10% risk of suffering a stroke during the 30 days that follow the index event. These two attributes have driven the most important changes in the management of TIA patients over the last decade, with particular attention paid to effective stroke risk stratification, efficient and comprehensive diagnostic assessment, and a sound therapeutic approach, destined to reduce the risk of subsequent ischemic stroke. This review is an outline of these changes, including a discussion of their advantages and disadvantages, and references to how new trends are likely to influence the future care of these patients.

Smoking cessation and outcome after ischemic stroke or TIA

OBJECTIVE

To assess whether smoking cessation after an ischemic stroke or TIA improves outcomes compared to continued smoking.

METHODS

We conducted a prospective observational cohort study of 3,876 nondiabetic men and women enrolled in the Insulin Resistance Intervention After Stroke (IRIS) trial who were randomized to pioglitazone or placebo within 180 days of a qualifying stroke or TIA and followed up for a median of 4.8 years. A tobacco use history was obtained at baseline and updated during annual interviews. The primary outcome, which was not prespecified in the IRIS protocol, was recurrent stroke, myocardial infarction (MI), or death. Cox regression models were used to assess the differences in stroke, MI, and death after 4.8 years, with correction for adjustment variables prespecified in the IRIS trial: age, sex, stroke (vs TIA) as index event, history of stroke, history of hypertension, history of coronary artery disease, and systolic and diastolic blood pressures.

RESULTS

At the time of their index event, 1,072 (28%) patients were current smokers. By the time of randomization, 450 (42%) patients had quit smoking. Among quitters, the 5-year risk of stroke, MI, or death was 15.7% compared to 22.6% for patients who continued to smoke (adjusted hazard ratio 0.66, 95% confidence interval 0.48-0.90).

CONCLUSION

Cessation of cigarette smoking after an ischemic stroke or TIA was associated with significant health benefits over 4.8 years in the IRIS trial cohort.