Improved Ischemic Stroke Outcome Prediction Using Model Estimation of Outcome Probability: The THRIVE-c Calculation

Developing a nomogram model for 3-month prognosis in patients who had an acute ischaemic stroke after intravenous thrombolysis: a multifactor logistic regression model approach

OBJECTIVES

This study is to establish a nomination graph model for individualised early prediction of the 3-month prognosis of patients who had an acute ischaemic stroke (AIS) receiving intravenous thrombolysis with recombinant tissue plasminogen activator.

DESIGN

For the period from January 2016 through August 2022, 991 patients who had an acute stroke eligible for intravenous thrombolysis were included in the retrospective analysis study. The study was based on multifactor logistic regression.

PARTICIPANTS

Patients who received treatment from January 2016 to February 2021 were included in the training cohort, and those who received treatment from March 2021 to August 2022 were included in the testing cohort.

INTERVENTIONS

Each patient received intravenous thrombolysis within 4.5 hours of onset, with treatment doses divided into standard doses (0.9 mg/kg).

PRIMARY AND SECONDARY OUTCOME MEASURES

The primary outcome measure was a 3-month adverse outcome (modified Rankin Scale 3-6).

RESULTS

The National Institutes of Health Stroke Scale Score after thrombolysis (OR=1.18; 95% CI: 1.04 to 1.36; p = 0.015), door-to-needle time (OR=1.01; 95% CI: 1.00 to 1.02; p = 0.003), baseline blood glucose (OR=1.08; 95% CI: 1.00 to 1.16; p=0.042), blood homocysteine (OR=7.14; 95% CI: 4.12 to 12.71; p<0.001), monocytes (OR=0.05; 95% CI: 0.01 to 0.043; p=0.005) and monocytes/high-density lipoprotein (OR=62.93; 95% CI: 16.51 to 283.08; p<0.001) were independent predictors of adverse outcomes 3 months after intravenous thrombolysis, and the above six factors were included in the nominated DGHM2N nomogram. The area under the receiver operating characteristic curve value of the training cohort was 0.870 (95% CI: 0.841 to 0.899) and in the testing cohort was 0.822 (95% CI: 0.769 to 0.875).

CONCLUSIONS

A reliable nomogram model (DGHM2N model) was developed and validated in this study. This nomogram could individually predict the adverse outcome of patients who had an AIS receiving intravenous thrombolysis with alteplase for 3 months.

Prognostic value of combining 24-hour ASPECTS and hemoglobin to red cell distribution width ratio to the THRIVE score in predicting in-hospital mortality among ischemic stroke patients treated with intravenous thrombolysis

BACKGROUND

Acute ischemic stroke (AIS) is a significant global health issue, directly impacting mortality and disability. The Totaled Health Risks in Vascular Events (THRIVE) score is appreciated for its simplicity and ease of use to predict stroke clinical outcomes; however, it lacks laboratory and neuroimaging data, which limits its ability to predict outcomes precisely. Our study evaluates the impact of integrating the 24-hour Alberta Stroke Program Early CT Score (ASPECTS) and hemoglobin-to-red cell distribution width (HB/RDW) ratio into the THRIVE score using the multivariable fractional polynomial (MFP) method (combined THRIVE-MFP model) compared to the THRIVE-c model. We aim to assess their added value in predicting in-hospital mortality (IHM) prognosis.

MATERIALS AND METHODS

A retrospective study from January 2015 to July 2022 examined consecutive AIS patients receiving intravenous thrombolysis. Data on THRIVE scores, 24-hour ASPECTS, and HB/RDW levels were collected upon admission. The model was constructed using logistic regression and the MFP method. The prognostic value was determined using the area under the receiver operating characteristic curve (AuROC). Ischemic cerebral lesions within the middle cerebral artery territory were evaluated with non-contrast computed tomography (NCCT) after completing 24 hours of intravenous thrombolysis (24-hour ASPECTS).

RESULTS

Among a cohort of 345 patients diagnosed with AIS who received intravenous thrombolysis, 65 individuals (18.8%) experienced IHM. The combined THRIVE-MFP model was significantly superior to the THRIVE-c model in predicting IHM (AuROC 0.980 vs. 0.876, p<0.001), 3-month mortality (AuROC 0.947 vs. 0.892, p<0.001), and 3-month poor functional outcome (AuROC 0.910 vs. 0.853, p<0.001).

CONCLUSION

The combined THRIVE-MFP model showed excellent predictive performance, enhancing physicians' ability to stratify patient selection for intensive neurological monitoring and guiding treatment decisions. Incorporating 24-hour ASPECTS on NCCT and HB/RDW proved valuable in mortality prediction, particularly for hospitals with limited access to advanced neuroimaging resources.

Derivation and Validation of a Scoring System for Predicting Poor Outcome After Posterior Circulation Ischemic Stroke in China

BACKGROUND AND OBJECTIVES

Guidelines for posterior circulation ischemic stroke (PCIS) treatment are lacking and outcome prediction is crucial for patients and clinicians. We aimed to develop and validate a prognostic score to predict the poor outcome for patients with PCIS.

METHODS

The score was developed from a prospective derivation cohort named the Third China National Stroke Registry (August 2015-March 2018) and validated in a spatiotemporal independent validation cohort (December 2017-March 2023) in China. Patients with PCIS with acute infarctions defined as hyperintense lesions on diffusion-weighted imaging were included in this study. The poor outcome was measured as modified Rankin scale (mRS) score 3-6 at 3 months after PCIS. Multivariable logistic regression analysis was used to identify predictors for poor outcome. The prognostic score, namely PCIS Outcome Score (PCISOS), was developed by assigning points to variables based on their relative β-coefficients in the logistic model.

RESULTS

The PCISOS was derived from 3,294 patients (median age 62 [interquartile range (IQR) 55-70] years; 2,250 [68.3%] men) and validated in 501 patients (median age 61 [IQR 53-68] years; 404 [80.6%] men). Among them, 384 (11.7%) and 64 (12.8%) had poor outcome 3 months after stroke in respective cohorts. Age, mRS before admission, NIH Stroke Scale on admission, ischemic stroke history, infarction distribution, basilar artery, and posterior cerebral artery stenosis or occlusion were identified as independent predictors for poor outcome and included in PCISOS. This easy-to-use integer scoring system identified a marked risk gradient between 4 risk groups. PCISOS performed better than previous scores, with an excellent discrimination (C statistic) of 0.80 (95% CI 0.77-0.83) in the derivation cohort and 0.81 (95% CI 0.77-0.84) in the validation cohort. Calibration test showed high agreement between the predicted and observed outcomes in both cohorts.

DISCUSSION

PCISOS can be applied for patients with PCIS with acute infarctions to predict functional outcome at 3 months post-PCIS. This simple tool helps clinicians to identify patients with PCIS with higher risk of poor outcome and provides reliable outcome expectations for patients. This information might be used for personalized rehabilitation plan and patient selection for future clinical trials to reduce disability and mortality.

Application of a nomogram model for the prediction of 90-day poor outcomes following mechanical thrombectomy in patients with acute anterior circulation large-vessel occlusion

Background

The past decade has witnessed advancements in mechanical thrombectomy (MT) for acute large-vessel occlusions (LVOs). However, only approximately half of the patients with LVO undergoing MT show the best/independent 90-day favorable outcome. This study aimed to develop a nomogram for predicting 90-day poor outcomes in patients with LVO treated with MT.

Methods

A total of 187 patients who received MT were retrospectively analyzed. Factors associated with 90-day poor outcomes (defined as mRS of 4-6) were determined by univariate and multivariate logistic regression analyzes. One best-fit nomogram was established to predict the risk of a 90-day poor outcome, and a concordance index was utilized to evaluate the performance of the model. Additionally, 145 patients from a single stroke center were retrospectively recruited as the validation cohort to test the newly established nomogram.

Results

The overall incidence of 90-day poor outcomes was 45.16%, affecting 84 of 186 patients in the training set. Moreover, five variables, namely, age (odds ratio [OR]: 1.049, 95% CI [1.016-1.083]; p = 0.003), glucose level (OR: 1.163, 95% CI [1.038-1.303]; p = 0.009), baseline National Institute of Health Stroke Scale (NIHSS) score (OR: 1.066, 95% CI [0.995-1.142]; p = 0.069), unsuccessful recanalization (defined as a TICI grade of 0 to 2a) (OR: 3.730, 95% CI [1.688-8.245]; p = 0.001), and early neurological deterioration (END, defined as an increase of ≥4 points between the baseline NIHSS score and the NIHSS score at 24 h after MT) (OR: 3.383, 95% CI [1.411-8.106]; p = 0.006), were included in the nomogram to predict the potential risk of poor outcomes at 90 days following MT in LVO patients, with a C-index of 0.763 (0.693-0.832) in the training set and 0.804 (0.719-0.889) in the validation set.

Conclusion

The proposed nomogram provided clinical evidence for the effective control of these risk factors before or during the process of MT surgery in LVO patients.

Clinical Grading Scales and Neuroprognostication in Acute Brain Injury

Prediction of neurological clinical outcome after acute brain injury is critical because it helps guide discussions with patients and families and informs treatment plans and allocation of resources. Numerous clinical grading scales have been published that aim to support prognostication after acute brain injury. However, the development and validation of clinical scales lack a standardized approach. This in turn makes it difficult for clinicians to rely on prognostic grading scales and to integrate them into clinical practice. In this review, we discuss quality measures of score development and validation and summarize available scales to prognosticate outcomes after acute brain injury. These include scales developed for patients with coma, cardiac arrest, ischemic stroke, nontraumatic intracerebral hemorrhage, subarachnoid hemorrhage, and traumatic brain injury; for each scale, we discuss available validation studies.

Outcome prediction in large vessel occlusion ischemic stroke with or without endovascular stroke treatment: THRIVE-EVT

INTRODUCTION

The THRIVE score and the THRIVE-c calculation are validated ischemic stroke outcome prediction tools based on patient variables that are readily available at initial presentation. Randomized controlled trials (RCTs) have demonstrated the benefit of endovascular treatment (EVT) for many patients with large vessel occlusion (LVO), and pooled data from these trials allow for adaptation of the THRIVE-c calculation for use in shared clinical decision making regarding EVT.

METHODS

To extend THRIVE-c for use in the context of EVT, we extracted data from the Virtual International Stroke Trials Archive (VISTA) from 7 RCTs of EVT. Models were built in a randomly selected development cohort using logistic regression that included the predictors from THRIVE-c: age, NIH Stroke Scale (NIHSS) score, presence of hypertension, diabetes mellitus, and/or atrial fibrillation, as well as randomization to EVT and, where available, the Alberta Stroke Program Early CT Score (ASPECTS).

RESULTS

Good outcome was achieved in 366/787 (46.5%) of subjects randomized to EVT and in 236/795 (29.7%) of subjects randomized to control (P < 0.001), and the improvement in outcome with EVT was seen across age, NIHSS, and THRIVE-c good outcome prediction. Models to predict outcome using THRIVE elements (age, NIHSS, and comorbidities) together with EVT, with or without ASPECTS, had similar performance by ROC analysis in the development and validation cohorts (THRIVE-EVT ROC area under the curve (AUC) = 0.716 in development, 0.727 in validation, P = 0.30; THRIVE-EVT + ASPECTS ROC AUC = 0.718 in development, 0.735 in validation, P = 0.12).

CONCLUSION

THRIVE-EVT may be used alongside the original THRIVE-c calculation to improve outcome probability estimation for patients with acute ischemic stroke, including patients with or without LVO, and to model the potential improvement in outcomes with EVT for an individual patient based on variables that are available at initial presentation. Online calculators for THRIVE-c estimation are available at www.thrivescore.org and www.mdcalc.com/thrive-score-for-stroke-outcome.

Validation and comparison of multiple risk scores for prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis in VISTA

BACKGROUND AND AIMS

Prediction models/scores may help to identify patients at high risk of symptomatic intracerebral hemorrhage (sICH) after intravenous thrombolysis. We aimed to validate and compare the performance of different prediction models for sICH after thrombolysis using direct model estimation in the Virtual International Stroke Trials Archive (VISTA).

METHODS

We searched PubMed for potentially eligible prediction models from inception to 1 June 2019. Simple and practical models/scores were validated in VISTA. The primary outcome was sICH based on two criteria (National Institute of Neurological Diseases and Stroke, NINDS; Safe Implementation of Thrombolysis in Stroke-Monitoring Study, SITS-MOST) and the secondary outcome was parenchymal hematoma (PH). The discrimination performance of each model was evaluated using area under the curve (AUC) and calibration was evaluated by Hosmer-Lemeshow goodness-of-fit tests.

RESULTS

We found 13 prediction models and five models (HAT, MSS, SPAN-100, GRASPS and THRIVE) were finally validated in VISTA. A total of 1884 participants were eligible for our study, of whom the proportion with sICH was 4.6% (87/1884) per NINDS and 3.9% (73/1884) per SITS-MOST, and with PH was 11.3% (213/1884). MSS and GRASPS had the greatest predictive ability for sICH (NINDS criteria: MSS AUC 0.7, 95% CI 0.63-0.77, p < 0.001; GRASPS AUC 0.69, 95% CI 0.63-0.76, p < 0.001; SITS-MOST criteria: MSS, AUC 0.76, 95% CI 0.68-0.85, p < 0.001; GRASPS, AUC 0.79, 95% CI 0.71-0.87, p < 0.001). Similar results were found for PH (MSS AUC 0.68, 95% CI 0.64-0.73, p = 0.017; GRASPS AUC 0.68, 95% CI 0.63-0.72, p = 0.017). The calibration of each model was almost good.

CONCLUSION

MSS and GRASPS had good discrimination and calibration for sICH and PH after thrombolysis as assessed in VISTA. These two models could be used in clinical practice and clinical trials to identity individuals with high risk of sICH.

Symptomatic Intracranial Hemorrhage After Endovascular Stroke Treatment: External Validation of Prediction Models

BACKGROUND

Symptomatic intracranial hemorrhage (sICH) is a severe complication of reperfusion therapy for ischemic stroke. Multiple models have been developed to predict sICH or intracranial hemorrhage (ICH) after reperfusion therapy. We provide an overview of published models and validate their ability to predict sICH in patients treated with endovascular treatment in daily clinical practice.

METHODS

We conducted a systematic search to identify models either developed or validated to predict sICH or ICH after reperfusion therapy (intravenous thrombolysis and/or endovascular treatment) for ischemic stroke. Models were externally validated in the MR CLEAN Registry (n=3180; Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands). The primary outcome was sICH according to the Heidelberg Bleeding Classification. Model performance was evaluated with discrimination (c-statistic, ideally 1; a c-statistic below 0.7 is considered poor in discrimination) and calibration (slope, ideally 1, and intercept, ideally 0).

RESULTS

We included 39 studies describing 40 models. The most frequently used predictors were baseline National Institutes of Health Stroke Scale (NIHSS; n=35), age (n=22), and glucose level (n=22). In the MR CLEAN Registry, sICH occurred in 188/3180 (5.9%) patients. Discrimination ranged from 0.51 (SPAN-100 [Stroke Prognostication Using Age and National Institutes of Health Stroke Scale]) to 0.61 (SITS-SICH [Safe Implementation of Treatments in Stroke Symptomatic Intracerebral Hemorrhage] and STARTING-SICH [STARTING Symptomatic Intracerebral Hemorrhage]). Best calibrated models were IST-3 (intercept, -0.15 [95% CI, -0.01 to -0.31]; slope, 0.80 [95% CI, 0.50-1.09]), SITS-SICH (intercept, 0.15 [95% CI, -0.01 to 0.30]; slope, 0.62 [95% CI, 0.38-0.87]), and STARTING-SICH (intercept, -0.03 [95% CI, -0.19 to 0.12]; slope, 0.56 [95% CI, 0.35-0.76]).

CONCLUSIONS

The investigated models to predict sICH or ICH discriminate poorly between patients with a low and high risk of sICH after endovascular treatment in daily clinical practice and are, therefore, not clinically useful for this patient population.

Validation of the Charlotte large artery occlusion endovascular therapy outcome score using Viz.ai-derived cerebral blood volume index

BACKGROUND

The Charlotte large artery occlusion endovascular therapy outcome score (CLEOS) predicts poor 90-day outcomes for patients presenting with internal carotid artery (ICA) or middle cerebral artery (MCA) occlusions. It incorporates RAPID-derived cerebral blood volume (CBV) index, a marker of collateral circulation. We validated the predictive ability of CLEOS with Viz.ai-processed computed tomography perfusion (CTP) imaging.

METHODS

The original CLEOS derivation cohort was compared to a validation cohort consisting of all ICA and MCA thrombectomy patients treated at a large health system with Viz.ai-processed CTP. Rates of poor 90-day outcome (mRS 4-6) were compared in the derivation and validation cohorts, stratified by CLEOS. CLEOS was compared to previously described prediction models using area under the curve (AUC) analyses. Calibration of CLEOS was performed to compare predicted risk of poor outcomes with observed outcomes.

RESULTS

One-hundred eighty-one patients (mean age 66.4 years, median NIHSS 16) in the validation cohort were included. The validation cohort had higher median CTP core volumes (24 vs 8 ml) and smaller median mismatch volumes (81 vs 101 ml) than the derivation cohort. CLEOS-predicted poor outcomes strongly correlated with observed outcomes (R2 = 0.82). AUC for CLEOS in the validation cohort (0.72, 95% CI 0.64-0.80) was similar to the derivation cohort (AUC 0.75, 95% CI 0.70-0.80) and was comparable or superior to previously described prognostic models.

CONCLUSIONS

CLEOS can predict risk of poor 90-day outcomes in ICA and MCA thrombectomy patients evaluated with pre-intervention, Viz.ai-processed CTP.

Comparison of Outcomes of Ischemic Stroke Initially Imaged With Cranial Computed Tomography Alone vs Computed Tomography Plus Magnetic Resonance Imaging

IMPORTANCE

Patients with acute ischemic stroke often undergo magnetic resonance imaging (MRI) in addition to computed tomography (CT), but its association with clinical outcomes is uncertain.

OBJECTIVE

To assess whether clinical outcomes of patients with acute ischemic stroke with initial CT alone were noninferior to those with additional MRI.

DESIGN, SETTING, AND PARTICIPANTS

A retrospective observational propensity score-matched cohort study of clinical outcomes at discharge and 1 year for patients hospitalized with acute ischemic stroke was conducted at an academic medical center between January 2015 and December 2017. Data collection from an electronic medical record system performed from May 2020 through January 2022 was not completely blinded. Noninferiority margins were based on the designs of previous randomized clinical trials of ischemic stroke treatments. Statistical analysis was performed in January 2022. Participants were adults hospitalized with acute ischemic stroke with admission diagnosis based on CT. Exclusion criteria were primarily missing data. From 508 eligible patients, all 123 cases with additional MRI were propensity-score matched to 123 controls without.

EXPOSURE

MRI after initial diagnosis.

MAIN OUTCOMES AND MEASURES

Death or dependence at hospital discharge (modified Rankin Scale score of 3-6) and stroke or death occurring in survivors within 1 year after discharge.

RESULTS

Among 246 participants, the median age was 68 years (IQR, 58-78.8 years) and 131 (53.0%) were men. Death or dependence at discharge occurred more often in patients with additional MRI (59 of 123 [48.0%]) than in those with CT alone (52 of 123 [42.3%]; absolute difference, 5.7%; 95% CI, -6.7% to 18.1%), meeting the -7.50% criterion for noninferiority. Stroke or death within 1 year after discharge determined for 225 of 235 (96%) survivors occurred more often in patients with additional MRI (22 of 113 [19.5%]) than in those with CT alone (14 of 112 [12.5%]; relative risk, 1.14; 95% CI, 0.86-1.50), meeting the 0.725 relative risk criterion for noninferiority.

CONCLUSIONS AND RELEVANCE

This propensity score-matched cohort study of patients hospitalized with acute ischemic stroke found that a diagnostic imaging strategy of initial CT alone was noninferior to initial CT plus additional MRI with regard to clinical outcomes at discharge and at 1 year. Further research is needed to determine which patients hospitalized with acute ischemic stroke benefit from MRI.

Nijeholt G, van Es A, van der Lugt A, Majoie C, Burke J, Roozenbeek B, Lingsma H, Dippel D. Outcome Prediction Models for Endovascular Treatment of Ischemic Stroke: Systematic Review and External Validation

Supplemental Digital Content is available in the text.

Prediction models for outcome of patients with acute ischemic stroke who will undergo endovascular treatment have been developed to improve patient management. The aim of the current study is to provide an overview of preintervention models for functional outcome after endovascular treatment and to validate these models with data from daily clinical practice.

Predictive factors of functional independence after optimal reperfusion in anterior circulation ischaemic stroke with indication for intravenous thrombolysis plus mechanical thrombectomy

BACKGROUND AND PURPOSE

Intravenous thrombolysis plus mechanical thrombectomy (IVT + MT) is the best current management of acute stroke due to large-vessel occlusion and results in optimal reperfusion for most patients. Nevertheless, some of these patients do not subsequently achieve functional independence. The aim was to identify baseline factors associated with 3-month independence after optimal reperfusion and to validate a prediction model.

METHODS

All consecutive patients with intracranial anterior large-vessel occlusion, with indication for IVT + MT and achieving optimal reperfusion (defined as modified Treatment in Cerebral Ischaemia score 2b-3), from the THRACE trial and the ETIS registry, were included in order to identify a prediction model. The primary outcome was 3-month independence [modified Rankin Scale (mRS) score ≤ 2]. Multivariate inferences invoked forward logistic regression, multiple imputation and bootstrap resampling. Predictive performance was assessed by c-statistic. Model validation was conducted on patients from the ASTER trial.

RESULTS

Amongst 139 patients (mean age 65.5 years; 54.3% female), predictors of 3-month mRS ≤ 2 (n = 82) were younger age [odds ratio 0.62 per 10-year increase; 95% confidence interval (CI) 0.53-0.72] and higher Alberta Stroke Program Early Computed Tomography Score (ASPECTS) (odds ratio 1.65 per 1-point increase; 95% CI 1.47-1.86) with c-statistic 0.77. Model validation (n = 104/181 patients with 3-month mRS ≤ 2) demonstrated a moderate discrimination (c-statistic 0.74; 95% CI 0.66-0.81) combining age and ASPECTS. The validation model was improved by the adjunction of three candidate variables that were found to be predictors. Addition of baseline National Institutes of Health Stroke Scale (NIHSS) score, history of vascular risk factor and onset-to-reperfusion time significantly improved discrimination (c-statistic 0.85; 95% CI 0.83-0.87).

CONCLUSIONS

After optimal reperfusion, younger age, higher ASPECTS, lower NIHSS score, shorter onset-to-reperfusion time and absence of vascular risk factor were predictive of independence and could help to guide patient management.

Predicting Functional Outcome Based on Linked Data After Acute Ischemic Stroke: S-SMART Score

Prediction of outcome after stroke may help clinicians provide effective management and plan long-term care. We aimed to develop and validate a score for predicting good functional outcome available for hospitals after ischemic stroke using linked data. A total of 22,005 patients with acute ischemic stroke from the Clinical Research Center for Stroke Registry between July 2007 and December 2014 were included in the derivation group. We assessed functional outcomes using a modified Rankin scale (mRS) score at 3 months after ischemic stroke. We identified predictors related to good 3-month outcome (mRS score ≤ 2) and developed a score. External validations (geographic and temporal validations) of the developed model were performed. The prediction model performance was assessed using the area under the receiver operating characteristic curve (AUC) and the calibration test. Stroke severity, sex, stroke mechanism, age, pre-stroke mRS, and thrombolysis/thrombectomy treatment were identified as predictors for 3-month good functional outcomes in the S-SMART score (total 34 points). Patients with higher S-SMART scores had an increased likelihood of a good outcome. The AUC of the prediction score was 0.805 (0.798-0.811) in the derivation group and 0.812 (0.795-0.830) in the geographic validation group for good functional outcome. The AUC of the model was 0.812 (0.771-0.854) for the temporal validation group. Moreover, they had good calibration. The S-SMART score is a valid and useful tool to predict good functional outcome following ischemic stroke. This prediction model may assist in the estimation of outcomes to determine care plans after stroke.

Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke

Background and Purpose- The prediction of long-term outcomes in ischemic stroke patients may be useful in treatment decisions. Machine learning techniques are being increasingly adapted for use in the medical field because of their high accuracy. This study investigated the applicability of machine learning techniques to predict long-term outcomes in ischemic stroke patients. Methods- This was a retrospective study using a prospective cohort that enrolled patients with acute ischemic stroke. Favorable outcome was defined as modified Rankin Scale score 0, 1, or 2 at 3 months. We developed 3 machine learning models (deep neural network, random forest, and logistic regression) and compared their predictability. To evaluate the accuracy of the machine learning models, we also compared them to the Acute Stroke Registry and Analysis of Lausanne (ASTRAL) score. Results- A total of 2604 patients were included in this study, and 2043 (78%) of them had favorable outcomes. The area under the curve for the deep neural network model was significantly higher than that of the ASTRAL score (0.888 versus 0.839; P<0.001), while the areas under the curves of the random forest (0.857; P=0.136) and logistic regression (0.849; P=0.413) models were not significantly higher than that of the ASTRAL score. Using only the 6 variables that are used for the ASTRAL score, the performance of the machine learning models did not significantly differ from that of the ASTRAL score. Conclusions- Machine learning algorithms, particularly the deep neural network, can improve the prediction of long-term outcomes in ischemic stroke patients.

A Simple Hospital Mobility Scale for Acute Ischemic Stroke Patients Predicts Long-term Functional Outcome

Background. Stroke patients present restriction of mobility in the acute phase, and the use of a simple and specific scale can be useful to guide rehabilitation. Objective. To validate and propose a Hospital Mobility Scale (HMS) for ischemic stroke patients as well as to evaluate the HMS as a prognostic indicator. Methods. This study was performed in 2 phases: in the first, we developed the HMS content, and in the second, we defined its score and evaluated its psychometric properties. We performed a longitudinal prospective study consisting of 2 cohorts (derivation and validation cohorts). The data were collected in a stroke unit, and the following scales were applied during hospitalization: National Institutes of Health Stroke Scale to quantify stroke severity and the HMS to verify the degree of mobility. The primary outcome was the proportion of unfavorable functional outcomes, defined as a modified Barthel Index of <95. Results. We defined 3 tasks for HMS: sitting, standing, and gait. In the derivation cohort, the HMS presented an accuracy of 84.5% measured using the area under the receiver operating characteristic curve (95% CI = 78.3-90.7; P < .001), whereas in the validation cohort the accuracy was 87.8% (95% CI = 81.9%-93.7%; P < .001). The HMS presented a large standardized effect size (1.41) and excellent interexaminer agreement (intraclass correlation coefficient = 0.962; 95% CI = 0.917-0.983; P < .001). Conclusion. The HMS was able to predict accurately the functional outcome of poststroke patients, presented excellent interexaminer agreement, and was sensitive in detecting changes.

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.

THRIVE-c score predicts clinical outcomes in Chinese patients after thrombolysis

Objectives

Total Health Risks in Vascular Events-calculation score (THRIVE-c) is an easy use and patient-specific outcome predictive score by computing the logistic equation with patients' continuous variables. We validated its performance in Chinese ischemic stroke patients receiving intravenous thrombolysis (IVT) therapy.

Materials and Methods

We used data from the Thrombolysis Implementation and Monitor of Acute Ischemic Stroke in China (TIMS-China) registry to validate the THRIVE-c score in patients receiving IVT therapy. We evaluated the score performance using area under the receiver operating characteristic curve (AUC). Receiver operator characteristic curve (ROC) was used to compare THRIVE-c score performance with other scores in predicting clinical outcome and symptomatic intracranial hemorrhage (SICH). Calibration was assessed by Pearson correlation coefficient and Hosmer-Lemeshow test.

Results

Among the 1,128 patients receiving IVT therapy included in this study, AUC of the THRIVE-c score for 3-month SICH, poor functional outcome, and mortality rate was 0.70 (95% CI: 0.63-0.76), 0.75 (95% CI: 0.73-0.78) and 0.81 (95% CI: 0.77-0.85), respectively. The increased THRIVE-c score was associated with higher risk of developing SICH, poor functional outcome, or mortality in patients with acute ischemic stroke at 3 months after thrombolysis. The performance of the THRIVE-c score was similar to or superior to other predictive scores (THRIVE score, SEDAN score, DRAGON score, HIAT2 score).

Conclusions

The THRIVE-c score reliably predicts the risks of 3-month SICH, poor functional outcome, and mortality after IVT therapy in Chinese patients with ischemic stroke.

THRIVE score predicts clinical and radiological outcome after endovascular therapy or thrombolysis in patients with anterior circulation stroke in everyday clinical practice

BACKGROUND AND PURPOSE

Based on the data of several trials the Totaled Health Risks in Vascular Events (THRIVE) score has been shown to predict outcome after either intravenous thrombolysis (IVT) or endovascular therapy (ET) in acute stroke patients. It is unknown whether the THRIVE score can also predict outcome in everyday clinical practice. Using our prospectively obtained stroke database the utility of the THRIVE score to predict clinical and radiological outcome in everyday clinical practice was analysed.

METHODS

The relationships between THRIVE and good outcome (modified Rankin Scale ≤ 2 at discharge), poor outcome (modified Rankin Scale 5-6), in-hospital death, symptomatic intracranial haemorrhage (SICH) as well as infarct size were examined in patients with distal intracranial carotid artery, M1 and M2 occlusions after either IVT or ET.

RESULTS

From January 2008 to October 2016 a total of 546 patients were treated with IVT and 492 patients received ET with stent retrievers (with or without IVT). In both treatment groups the THRIVE score predicted clinical outcome (Mantel-Haenszel chi-squared tests for trend P < 0.001 for good outcome, P < 0.001 for poor outcome and P < 0.001 for in-hospital death). In the ET group the THRIVE score remained an independent predictor of outcome after controlling for recanalization. The THRIVE score was associated with the infarct size after IVT or ET, whereas it did not predict SICH rates in either treatment group.

CONCLUSIONS

In everyday clinical practice the THRIVE score strongly predicts clinical outcome and the extent of ischaemia after ET or IVT in patients with anterior circulation large vessel occlusions.