Search

Background and ObjectivesThe care of patients with large vessel occlusion (LVO) stroke has been revolutionized by endovascular thrombectomy (EVT). While EVT has a large effect size, most patients treated with EVT remain disabled or die within 90 days. A better understanding of outcomes may influence EVT selection criteria, novel therapies, and prognostication. We sought to identify associations between outcomes and brain regions involved in ischemic lesions.MethodsFor this cohort study, consecutive patients with LVO who were treated with EVT and underwent post-EVT MRI were identified from a tertiary referral center (2011–2019). Acute ischemic lesions were manually segmented from diffusion-weighted imaging and spatially normalized. Individual lesions were parcellated (atlas-defined 94 cortical regions, 14 subcortical nuclei, 20 white matter tracts) and reduced to 10 essential lesion patterns with the use of unsupervised dimensionality reduction techniques. Ninety-day modified Rankin Scale (mRS) score (>2) was modeled via bayesian regression, taking the 10 lesion patterns as inputs and controlling for lesion size, age, sex, acute NIH Stroke Scale (NIHSS) score, alteplase, prior stroke, intracerebral hemorrhage, and good reperfusion (Thrombolysis in Cerebral Infarction 2b–3). In comparative analyses, 90-day mRS score was modeled considering covariates only, and compartment-wise relevances for acute stroke severity and 90-day mRS score were evaluated.ResultsThere were 151 patients with LVO identified (age 68 ± 15 years, 52% female). The median NIHSS score was 16 (interquartile range 13–20); 56% had mRS score >2. Lesion locations predictive of 90-day mRS score involved bilateral but left hemispherically more pronounced precentral and postcentral gyri, insular and opercular cortex, and left putamen and caudate (area under the curve 0.91, highest probability density interval [HPDI] covering 90% certainty 0.90–0.92). The lesion location model outperformed the simpler model relying on covariates only (bayesian model comparison of 97% weight to the model with vs 3% weight to the model without lesion location). While lesions affecting subcortical nuclei had the highest relevance for stroke severity (posterior distribution mean 0.75, 90% HPDI 0.256–1.31), lesions affecting white matter tracts had the highest relevance for 90-day mRS score (0.656, 90% HPDI 0.0864–1.12).DiscussionThese data describe the significance for outcomes of specific brain regions involved in ischemic lesions on MRI after EVT. Future work in additional datasets is needed to confirm these granular findings.

IntroductionStroke causes different levels of impairment and the degree of recovery varies greatly between patients. The majority of recovery studies are biased towards patients with mild-to-moderate impairments, challenging a unified recovery process framework. Our aim was to develop a statistical framework to analyse recovery patterns in patients with severe and non-severe initial impairment and concurrently investigate whether they recovered differently.MethodsWe designed a Bayesian hierarchical model to estimate 3–6 months upper limb Fugl-Meyer (FM) scores after stroke. When focusing on the explanation of recovery patterns, we addressed confounds affecting previous recovery studies and considered patients with FM-initial scores FM-initial=5–30). In model comparisons, we evaluated whether impairment-level-specific recovery patterns indeed existed. Finally, we estimated the out-of-sample prediction performance for patients across the entire initial impairment range.ResultsRecovery data was assembled from eight patient cohorts (n=489). Data were best modelled by incorporating two subgroups (breakpoint: FM-initial=10). Both subgroups recovered a comparable constant amount, but with different proportional components: severely affected patients recovered more the smaller their impairment, while non-severely affected patients recovered more the larger their initial impairment. Prediction of 3–6 months outcomes could be done with an R2=63.5% (95% CI=51.4% to 75.5%).ConclusionsOur work highlights the benefit of simultaneously modelling recovery of severely-to-non-severely impaired patients and demonstrates both shared and distinct recovery patterns. Our findings provide evidence that the severe/non-severe subdivision in recovery modelling is not an artefact of previous confounds. The presented out-of-sample prediction performance may serve as benchmark to evaluate promising biomarkers of stroke recovery.

BACKGROUND AND PURPOSE Ischemic diffusion-weighted imaging-fluid-attenuated inversion recovery (DWI-FLAIR) mismatch may be useful in guiding acute stroke treatment decisions given its relationship to onset time and parenchymal viability; however, it relies on subjective grading. Radiomics is an emerging image quantification methodology that may objectively represent continuous image characteristics. We propose a novel radiomics approach to characterize DWI-FLAIR mismatch. METHODS Ischemic lesions were visually graded for FLAIR positivity (absent, subtle, obvious) among consecutive large vessel occlusion stroke patients who underwent hyperacute MRI. Radiomic features were extracted from within the lesions on DWI and FLAIR. The DWI-FLAIR mismatch radiomics signature was built with features systematically selected by a cross-validated ElasticNet linear regression model of mismatch. RESULTS We identified 103 patients with mean age 68 ± 16 years; 63% were female. FLAIR hyperintensity was absent in 25%, subtle in 55%, and obvious in 20%. Inter-rater agreement for visual grading was moderate (Κ = .58). The radiomics signature of DWI-FLAIR mismatch included native FLAIR histogram kurtosis and local binary pattern-filtered FLAIR gray-level cluster shade; both correlated with visual grading (ρ = -.42, p

Background and ObjectivesTo examine whether high white matter hyperintensity (WMH) burden is associated with greater stroke severity and worse functional outcomes in lesion pattern–specific ways.MethodsMR neuroimaging and NIH Stroke Scale data at index stroke and the modified Rankin Scale (mRS) score at 3–6 months after stroke were obtained from the MRI–Genetics Interface Exploration study of patients with acute ischemic stroke (AIS). Individual WMH volume was automatically derived from fluid-attenuated inversion recovery images. Stroke lesions were automatically segmented from diffusion-weighted imaging (DWI) images, parcellated into atlas-defined brain regions and further condensed to 10 lesion patterns via machine learning–based dimensionality reduction. Stroke lesion effects on AIS severity and unfavorable outcomes (mRS score >2) were modeled within purpose-built Bayesian linear and logistic regression frameworks. Interaction effects between stroke lesions and a high vs low WMH burden were integrated via hierarchical model structures. Models were adjusted for age, age2, sex, total DWI lesion and WMH volumes, and comorbidities. Data were split into derivation and validation cohorts.ResultsA total of 928 patients with AIS contributed to acute stroke severity analyses (age: 64.8 [14.5] years, 40% women) and 698 patients to long-term functional outcome analyses (age: 65.9 [14.7] years, 41% women). Stroke severity was mainly explained by lesions focused on bilateral subcortical and left hemispherically pronounced cortical regions across patients with both a high and low WMH burden. Lesions centered on left-hemispheric insular, opercular, and inferior frontal regions and lesions affecting right-hemispheric temporoparietal regions had more pronounced effects on stroke severity in case of high compared with low WMH burden. Unfavorable outcomes were predominantly explained by lesions in bilateral subcortical regions. In difference to the lesion location–specific WMH effects on stroke severity, higher WMH burden increased the odds of unfavorable outcomes independent of lesion location.DiscussionHigher WMH burden may be associated with an increased stroke severity in case of stroke lesions involving left-hemispheric insular, opercular, and inferior frontal regions (potentially linked to language functions) and right-hemispheric temporoparietal regions (potentially linked to attention). Our findings suggest that patients with specific constellations of WMH burden and lesion locations may have greater benefits from acute recanalization treatments. Future clinical studies are warranted to systematically assess this assumption and guide more tailored treatment decisions.

Cognitive and behavioural outcomes in stroke reflect the interaction between two complex anatomically-distributed patterns: the functional organization of the brain and the structural distribution of ischaemic injury. Conventional outcome models—for individual prediction or population-level inference—commonly ignore this complexity, discarding anatomical variation beyond simple characteristics such as lesion volume. This sets a hard limit on the maximum fidelity such models can achieve. High-dimensional methods can overcome this problem, but only at prohibitively large data scales. Drawing on one of the largest published collections of anatomically-registered imaging of acute stroke—N = 1333—here we use non-linear dimensionality reduction to derive a succinct latent representation of the anatomical patterns of ischaemic injury, agglomerated into 21 distinct intuitive categories. We compare the maximal predictive performance it enables against both simpler low-dimensional and more complex high-dimensional representations, employing multiple empirically-informed ground truth models of distributed structure–outcome relationships. We show our representation sets a substantially higher ceiling on predictive fidelity than conventional low-dimensional approaches, but lower than that achievable within a high-dimensional framework. Where descriptive simplicity is a necessity, such as within clinical care or research trials of modest size, the representation we propose arguably offers a favourable compromise of compactness and fidelity.

Background The treatment of stroke has been undergoing rapid changes. As treatment options progress, prediction of those under risk for complications becomes more important. Available models have, however, frequently been built based on data no longer representative of today’s care, in particular with respect to acute stroke management. Our aim was to build and validate prediction models for 4 clinically important, severe outcomes after stroke. Methods and Results We used German registry data from 152 710 patients with acute ischemic stroke obtained in 2016 (development) and 2017 (validation). We took into account potential predictors that were available at admission and focused on in‐hospital mortality, intracranial mass effect, secondary intracerebral hemorrhage, and deep vein thrombosis as outcomes. Validation cohort prediction and calibration performances were assessed using the following 4 statistical approaches: logistic regression with backward selection, l 1‐regularized logistic regression, k‐nearest neighbor, and gradient boosting classifier. In‐hospital mortality and intracranial mass effects could be predicted with high accuracy (both areas under the curve, 0.90 [95% CI, 0.90–0.90]), whereas the areas under the curve for intracerebral hemorrhage (0.80 [95% CI, 0.80–0.80]) and deep vein thrombosis (0.73 [95% CI, 0.73–0.73]) were considerably lower. Stroke severity was the overall most important predictor. Models based on gradient boosting achieved better performances than those based on logistic regression for all outcomes. However, area under the curve estimates differed by a maximum of 0.02. Conclusions We validated prediction models for 4 severe outcomes after acute ischemic stroke based on routinely collected, recent clinical data. Model performance was superior to previously proposed approaches. These predictions may help to identify patients at risk early after stroke and thus facilitate an individualized level of care.

ObjectiveTo examine whether high white matter hyperintensity (WMH) burden is associated with greater stroke severity and worse functional outcomes in lesion pattern-specific ways.MethodsMR neuroimaging and National Institutes of Health Stroke Scale data at index stroke, as well as modified Rankin Scale (mRS) at 3-6 months post-stroke were obtained from MRI-GENIE study of acute ischemic stroke (AIS) patients. Individual WMH volume was automatically derived from FLAIR-images. Stroke lesions were automatically segmented from DWI-images, spatially normalized and parcellated into atlas-defined brain regions. Stroke lesion effects on AIS severity and unfavorable outcomes (mRS>2) were modeled within a purpose-built machine learning and Bayesian regression framework. In particular, interaction effects between stroke lesions and a high versus low WMH burden were integrated via hierarchical model structures. Models were adjusted for the covariates age, age2, sex, total DWI-lesion and WMH volumes, and comorbidities. Data were split into derivation and validation cohorts.ResultsA total of 928 AIS patients contributed to stroke severity analyses (mean age: 64.8(14.5), 40% women), 698 patients to functional outcome analyses (mean age: 65.9(14.7), 41% women). Individual stroke lesions were represented in five anatomically distinct left-hemispheric and five right-hemispheric lesion patterns. Across all patients, acute stroke severity was substantially explained by three of these patterns, that were particularly focused on bilateral subcortical and left-hemispherically pronounced cortical regions. In high WMH burden patients, two lesion patterns consistently emerged as more pronounced in case of stroke severity: the first pattern was centered on left-hemispheric insular, opercular and inferior frontal regions, while the second pattern combined right-hemispheric temporo-parietal regions. Bilateral subcortical regions were most relevant in explaining long term unfavorable outcome. No WMH-specific lesion patterns of functional outcomes were substantiated. However, a higher overall WMH burden was associated with higher odds of unfavorable outcomes.ConclusionsHigher WMH burden increases stroke severity in case of stroke lesions involving left-hemispheric insular, opercular and inferior frontal regions (potentially linked to language functions) and right-hemispheric temporo-parietal regions (potentially linked to attention). These findings may contribute to augment stroke outcome predictions and motivate a WMH burden and stroke lesion pattern-specific clinical management of AIS patients.

Acute ischemic stroke affects men and women differently. In particular, women are often reported to experience higher acute stroke severity than men. We derived a low-dimensional representation of anatomical stroke lesions and designed a Bayesian hierarchical modeling framework tailored to estimate possible sex differences in lesion patterns linked to acute stroke severity (National Institute of Health Stroke Scale). This framework was developed in 555 patients (38% female). Findings were validated in an independent cohort (n = 503, 41% female). Here, we show brain lesions in regions subserving motor and language functions help explain stroke severity in both men and women, however more widespread lesion patterns are relevant in female patients. Higher stroke severity in women, but not men, is associated with left hemisphere lesions in the vicinity of the posterior circulation. Our results suggest there are sex-specific functional cerebral asymmetries that may be important for future investigations of sex-stratified approaches to management of acute ischemic stroke., Acute ischemic stroke impacts men and women differently. Here, the authors show how different lesion patterns in men and women are linked to the extent of stroke severity.

ObjectiveTo test the hypothesis that cognitive demands influence motor performance during recovery from acute stroke, we tested patients with acute stroke on 2 motor tasks with different cognitive demands and related task performance to cognitive impairment and neuroanatomic injury.MethodsWe assessed the contralesional and ipsilesional upper extremities of a cohort of 50 patients with weakness after unilateral acute ischemic stroke at 3 time points with 2 tasks: the Box & Blocks Test, a task with greater cognitive demand, and Grip Strength, a simple and ballistic motor task. We compared performance on the 2 tasks, related motor performance to cognitive dysfunction, and used voxel-based lesion symptom mapping to determine neuroanatomic sites associated with motor performance.ResultsConsistent across contralesional and ipsilesional upper extremities and most pronounced immediately after stroke, Box & Blocks scores were significantly more impaired than Grip Strength scores. The presence of cognitive dysfunction significantly explained up to 33% of variance in Box & Blocks performance but was not associated with Grip Strength performance. While Grip Strength performance was associated with injury largely restricted to sensorimotor regions, Box & Blocks performance was associated with broad injury outside sensorimotor structures, particularly the dorsal anterior insula, a region known to be important for complex cognitive function.ConclusionsTogether, these results suggest that cognitive demands influence upper extremity motor performance during recovery from acute stroke. Our findings emphasize the integrated nature of motor and cognitive systems and suggest that it is critical to consider cognitive demands during motor testing and neurorehabilitation after stroke.

The proportional recovery rule states that most survivors recover a fixed proportion (~70%) of lost function after stroke. A strong (negative) correlation between the initial score and subsequent change (outcome minus initial; i.e. recovery) is interpreted as empirical support for the proportional recovery rule. However, this rule has recently been critiqued, with a central observation being that the correlation of initial-scores with change over time is confounded in the situations in which it is typically assessed. This critique has prompted reassessments of patients’ behavioural trajectory following stroke in two prominent papers. The first of these, by van der Vliet and collaborators presented an impressive modelling of upper limb deficits following stroke, which avoided the confounded correlation of initial-scores with change. The second by Kundert and collaborators reassessed the value of the proportional recovery rule, as classically formulated as the correlation between initial-scores and change. They argued that, while effective prediction of recovery trajectories of individual patients is not supported by the available evidence, group-level inferences about the existence of proportional recovery are reliable. In this paper, we respond to the van der Vliet and Kundert papers by distilling the essence of the argument for why the classic assessment of proportional recovery is confounded. In this respect, we re-emphasize the role of mathematical coupling and compression to ceiling in the confounded nature of the correlation of initial-scores with change. We further argue that this confound will be present for both individual-level and group-level inference. We then focus on the difficulties that can arise from ceiling effects, even when initial-scores are not being correlated with change/ recovery. We conclude by emphasizing the need for new techniques to analyse recovery after stroke that are not confounded in the ways highlighted here.

Cognitive impairment is a frequent and disabling sequela of stroke. There is however incomplete understanding of how lesion topographies in the left and right cerebral hemisphere brain interact to cause distinct cognitive deficits. We integrated machine learning and Bayesian hierarchical modelling to enable a hemisphere-aware analysis of 1080 acute ischaemic stroke patients with deep profiling ∼3 months after stroke. We show the relevance of the left hemisphere in the prediction of language and memory assessments and relevance of the right hemisphere in the prediction of visuospatial functioning. Global cognitive impairments were equally well predicted by lesion topographies from both sides. Damage to the hippocampal and occipital regions on the left was particularly informative about lost naming and memory functions, while damage to these regions on the right was linked to lost visuospatial functioning. Global cognitive impairment was predominantly linked to lesioned tissue in the supramarginal and angular gyrus, the post-central gyrus as well as the lateral occipital and opercular cortices of the left hemisphere. Hence, our analysis strategy uncovered that lesion patterns with unique hemispheric distributions are characteristic of how cognitive capacity is lost due to ischaemic brain tissue damage., Bonkhoff et al. integrate machine learning and Bayesian hierarchical modelling to enable hemisphere-aware analysis of 1080 stroke patients. They quantify lateralization effects of cortical and subcortical regions, such as the pallidum and hippocampus, of middle and posterior cerebral artery vascular territories to the left for naming/memory and to the right for visuospatial functions., Graphical Abstract Graphical Abstract

Stroke ranks among the leading causes for morbidity and mortality worldwide. New and continuously improving treatment options such as thrombolysis and thrombectomy have revolutionized acute stroke treatment in recent years. Following modern rhythms, the next revolution might well be the strategic use of the steadily increasing amounts of patient-related data for generating models enabling individualized outcome predictions. Milestones have already been achieved in several health care domains, as big data and artificial intelligence have entered everyday life. The aim of this review is to synoptically illustrate and discuss how artificial intelligence approaches may help to compute single-patient predictions in stroke outcome research in the acute, subacute and chronic stage. We will present approaches considering demographic, clinical and electrophysiological data, as well as data originating from various imaging modalities and combinations thereof. We will outline their advantages, disadvantages, their potential pitfalls and the promises they hold with a special focus on a clinical audience. Throughout the review we will highlight methodological aspects of novel machine-learning approaches as they are particularly crucial to realize precision medicine. We will finally provide an outlook on how artificial intelligence approaches might contribute to enhancing favourable outcomes after stroke.

Introduction: MRI-detected white matter hyperintensity (WMH) burden is linked to the overall brain health and incident stroke outcomes. However, data are limited as to whether specific acute stroke lesion patterns purport greater stroke severity in patients with extensive pre-existing WMH. In this analysis, we sought to investigate lesion pattern-specific WMH effects on AIS severity. Methods: We analyzed clinical and lesion data from 621 AIS patients enrolled in the multi-site MRI-GENIE study. The acute NIHSS was modelled via Bayesian hierarchical regression. Using ten stroke lesion patterns, that served as input variables of main interest, we introduced a hierarchical level differentiating between patients with higher and lower than median WMH volume (WMHv). Lesion pattern posterior distributions for higher and lower WMHv patients were subtracted to infer substantial differences. Results: In this AIS cohort [age: 65.3±14.6, 60% male], a higher WMHv was associated with greater stroke severity only when specific left-hemispheric brain regions were infarcted. This “lesion pattern 3” was mainly characterized by left middle and inferior frontal gyrus, insular and opercular cortex, pre- and post-central gyrus, and subcortical basal ganglia regions ( Fig ). Conclusions: Higher WMH burden appears to enhance the detrimental effect of acute stroke lesions involving left-hemispheric brain regions underlying language and motor functions. This effect might be due to an exacerbated disruption of functional network integrity by the combination of WMH and stroke lesions and could be explored further in functional imaging studies that simultaneously considered information from both lesion types.

Objective: Ability of the brain to recover after an acute ischemic stroke (AIS) is linked to the pre-stroke burden of white matter hyperintensity (WMH), a radiographic marker of brain health. We sought to determine the excessive WMH burden in an AIS population and investigate its association with 3-month stroke outcomes. Data: We used 2,435 subjects from the MRI-GENIE study. Three-month functional outcomes of 872 subjects among those subjects were measured by 90-day modified Ranking Scale (mRS). Methods: We automatically quantified WMH volume (WMHv) on FLAIR images and adjusted for a brain volume. We modeled a trend using the factor analysis (FA) log-linear regression using age, sex, atrial fibrillation, diabetes, hypertension, coronary artery disease and smoking as input variables. We categorized three WMH burden groups based on the conditional probability given by the model (LOW: lower 33%, MED: middle 34%, and HIGH: upper 33%). The subgroups were compared with respect to mRS (median and dichotomized odds ratio (OR) (good/poor: mRS 0-2/3-6)). Results: Five FA components out of seven with significant relationship to WMHv (p2 =0.359). The HIGH group showed higher median (median=2, IQR=2) mRS score than LOW (median=1, IQR=1) and MED (median=1, IQR=1). The odds (OR) of good AIS outcome for LOW and MED were 1.8 (p=0.0001) and 1.6 (p=0.006) times higher than HIGH, respectively. Conclusion: Once accounted for clinical covariates, the excessive WMHv was associated with worse 3-month stroke outcomes. These data suggest that a life-time of injury to the white matter reflected in WMH is an important factor for stroke recovery and an indicator of the brain health.

Introduction: Endovascular thrombectomy (EVT) has revolutionized large vessel occlusion (LVO) stroke care. However, over half remain functionally disabled or die despite treatment. Understanding outcomes may influence EVT selection, novel therapies, and prognostication. We sought to identify associations between outcomes and brain regions involved in ischemic lesions. Methods: For consecutive LVO patients with post-EVT MRI, acute ischemic lesions were manually segmented from DWI and spatially normalized. Individual lesion volumes were automatically parcellated (atlas-defined 94 cortical regions, 14 subcortical nuclei, 20 white matter tracts) and then reduced to ten anatomically plausible lesion patterns using unsupervised dimensionality reduction techniques. Ninety-day modified Rankin Scale (mRS) was modeled via Bayesian regression, taking the ten lesion patterns as inputs and controlling for lesion size, age, sex, acute NIH Stroke Scale, alteplase, and TICI 2b-3 reperfusion. Results: We identified 153 LVO patients with mean age 68±15 years and 51% female. Median NIHSS was 16 (IQR 13-20), 56% received alteplase, and 84% achieved TICI2b-3. The lesion patterns predictive of 90-day mRS involved bilateral subcortical nuclei, pre- and postcentral gyri, insular and opercular cortex, as well as left-sided inferior frontal and angular gyri ( Figure 1A ). Lesions affecting white matter tracts had the highest relevance predicting 90-day mRS ( Figure 1B ). Conclusions: These data describe the significance for outcomes of specific brain regions involved in ischemic lesions on MRI after EVT. Future work in additional datasets is needed to confirm these granular findings.

IntroductionNeuroimaging measurements of brain structural integrity are thought to be surrogates for brain health, but precise assessments require dedicated advanced image acquisitions. By means of describing the texture of conventional images beyond what meets the naked eye, radiomic analyses hold potential for evaluating brain health. We sought to: 1) evaluate this novel approach to assess brain structural integrity by predicting white matter hyperintensities burdens (WMH) and 2) uncover associations between predictive radiomic features and patients’ clinical phenotypes.MethodsOur analyses were based on a multi-site cohort of 4,163 acute ischemic strokes (AIS) patients with T2-FLAIR MR images and corresponding deep-learning-generated total brain and WMH segmentation. Radiomic features were extracted from normal-appearing brain tissue (brain mask–WMH mask). Radiomics-based prediction of personalized WMH burden was done using ElasticNet linear regression. We built a radiomic signature of WMH with the most stable selected features predictive of WMH burden and then related this signature to clinical variables (age, sex, hypertension (HTN), atrial fibrillation (AF), diabetes mellitus (DM), coronary artery disease (CAD), and history of smoking) using canonical correlation analysis.ResultsRadiomic features were highly predictive of WMH burden (R2=0.855±0.011). Seven pairs of canonical variates (CV) significantly correlated the radiomics signature of WMH and clinical traits with respective canonical correlations of 0.81, 0.65, 0.42, 0.24, 0.20, 0.15, and 0.15 (FDR-corrected p-valuesCV1-6CV7=.012). The clinical CV1 was mainly influenced by age, CV2 by sex, CV3 by history of smoking and DM, CV4 by HTN, CV5 by AF and DM, CV6 by CAD, and CV7 by CAD and DM.ConclusionRadiomics extracted from T2-FLAIR images of AIS patients capture microstructural damage of the cerebral parenchyma and correlate with clinical phenotypes. Further research could evaluate radiomics to predict the progression of WMH.Research in contextEvidence before this studyWe did a systematic review on PubMed until December 1, 2020, for original articles and reviews in which radiomics were used to characterize stroke or cerebrovascular diseases. Radiomic analyses cover a broad ensemble of high-throughput quantification methods applicable to digitalized medical images that extract high-dimensional data by describing a given region of interest by its size, shape, histogram, and relationship between voxels. We used the search terms “radiomics” or “texture analysis”, and “stroke”, “cerebrovascular disease”, “small vessel disease”, or “white matter hyperintensities”. Our research identified 24 studies, 18 studying radiomics of stroke lesions and 6 studying cerebrovascular diseases. All the latter six studies were based on MRI (T1-FLAIR, dynamic contrast-enhanced imaging, T1 & T2-FLAIR, T2-FLAIR post-contrast, T2-FLAIR, and T2-TSE images). Four studies were describing small vessel disease, and two were predicting longitudinal progression of WMH. The average sample size was small with 96 patients included (maximum: 204). One study on 141 patients identified 7 T1-FLAIR radiomic features correlated with cardiovascular risk factors (age and hyperlipidemia) using univariate correlations. All studies were monocentric and performed on a single MRI scanner.Added value of this studyTo date and to the best of our knowledge, this is the largest radiomics study performed on cerebrovascular disease or any topic, and one of the very few to include a great diversity of participating sites with diverse clinical MRI scanners. This study is the first one to establish a radiomic signature of WMH and to interpret its relationship with common cardiovascular risk factors. Our findings add to the body of evidence that damage caused by small vessel disease extend beyond the visible white matter hyperintensities, but the added value resides in the detection of that subvisible damage on routinely acquired T2-FLAIR imaging. It also suggests that cardiovascular phenotypes might manifest in distinct textural patterns detectable on conventional clinical-grade T2-FLAIR images.Implications of all the available evidenceAssessing brain structural integrity has implications for treatment selection, follow-up, prognosis, and recovery prediction in stroke patients but also other neurological disease populations. Measuring cerebral parenchymal structural integrity usually requires advanced imaging such as diffusion tensor imaging or functional MRI. Translation of those neuroimaging biomarkers remains uncommon in clinical practice mainly because of their time-consuming and costly acquisition. Our study provides a potential novel solution to assess brains’ structural integrity applicable to standard, routinely acquired T2-FLAIR imaging.Future research could, for instance, benchmark this radiomics approach against diffusion or functional MRI metrics in the prediction of cognitive or functional outcomes after stroke.

Background and Purpose: Men and women are differently affected by acute ischemic stroke (AIS) in many aspects. Prior studies on sex disparities were limited by moderate sample sizes, varying years of data acquisition, and inconsistent inclusions of covariates leading to controversial findings. We aimed to analyze sex differences in AIS severity, treatments, and early outcome and to systematically evaluate the effect of important covariates in a large German stroke registry. Methods: Analyses were based on the Stroke Registry of Northwestern Germany from 2000 to 2018. We focused on admission-stroke severity and disability, acute recanalization treatment, and early stroke outcomes. Potential sex divergences were investigated via odds ratio (OR) using logistic regression models. Covariates were introduced in 3 steps: (1) base models (age and admission year), (2) partially adjusted models (additionally corrected for acute stroke severity and recanalization treatment), (3) fully adjusted models (additionally adjusted for onset-to-admission time interval, prestroke functional status, comorbidities, and stroke cause). Models were separately fitted for the periods 2000 to 2009 and 2010 to 2018. Results: Data from 761 106 patients with AIS were included. In fully adjusted models, there were no sex differences with respect to treatment with intravenous thrombolysis (2000–2009: OR, 0.99 [95% CI, 0.94–1.03]; 2010–2018: OR, 1.0 [0.98–1.02]), but women were more likely to receive intraarterial therapy (2010–2018: OR, 1.12 [1.08–1.15]). Despite higher disability on admission (2000–2009: OR, 1.10 [1.07–1.13]; 2010–2018: OR, 1.09 [1.07–1.10]), female patients were more likely to be discharged with a favorable functional outcome (2003–2009: OR, 1.05 [1.02–1.09]; 2010–2018: OR, 1.05 [1.04–1.07]) and experienced lower in-hospital mortality (2000–2009: OR, 0.92 [0.86–0.97]; 2010–2018: OR, 0.91 [0.88–0.93]). Conclusions: Female patients with AIS have a higher chance of receiving intraarterial treatment that cannot be explained by clinical characteristics, such as age, premorbid disability, stroke severity, or cause. Women have a more favorable in-hospital recovery than men because their higher disability upon admission was followed by a lower in-hospital mortality and a higher likelihood of favorable functional outcome at discharge after adjustment for covariates.

Acute ischemic stroke affects men and women differently in many ways. In particular, women are oftentimes reported to experience a higher acute stroke severity than men. Here, we derived a low-dimensional representation of anatomical stroke lesions and designed a sex-aware Bayesian hierarchical modelling framework for a large-scale, well phenotyped stroke cohort. This framework was tailored to carefully estimate possible sex differences in lesion patterns explaining acute stroke severity (NIHSS) in 1,058 patients (39% female). Anatomical regions known to subserve motor and language functions emerged as relevant regions for both men and women. Female patients, however, presented a more widespread pattern of stroke severity-relevant lesions than male patients. Furthermore, particularly lesions in the posterior circulation of the left hemisphere underlay a higher stroke severity exclusively in women. These sex-sensitive lesion pattern effects could be discovered and subsequently robustly replicated in two large independent, multisite lesion datasets. The constellation of findings has several important conceptual and clinical implications: 1) suggesting sex-specific functional cerebral asymmetries, and 2) motivating a sex-stratified approach to management of acute ischemic stroke. To go beyond sex-averaged stroke research, future studies should explicitly test whether acute therapies administered on the basis of sex-specific cutoff volumes of salvageable tissue will lead to improved outcomes in women after acute ischemic stroke.

ObjectiveThorough assessment of cerebral dysfunction after acute brain lesions is paramount to optimize predicting short- and long-term clinical outcomes. The potential of dynamic resting-state connectivity for prognosticating motor recovery has not been explored so far.MethodsWe built random forest classifier-based prediction models of acute upper limb motor impairment and recovery after stroke. Predictions were based on structural and resting-state fMRI data from 54 ischemic stroke patients scanned within the first days of symptom onset. Functional connectivity was estimated using both a static and dynamic approach. Individual motor performance was phenotyped in the acute phase and six months later.ResultsA model based on the time spent in specific dynamic connectivity configurations achieved the best discrimination between patients with and without motor impairments (out-of-sample area under the curve and 95%-confidence interval (AUC±95%-CI): 0.67±0.01). In contrast, patients with moderate-to-severe impairments could be differentiated from patients with mild deficits using a model based on the variability of dynamic connectivity (AUC±95%-CI: 0.83±0.01). Here, the variability of the connectivity between ipsilesional sensorimotor cortex and putamen discriminated the most between patients. Finally, motor recovery was best predicted by the time spent in specific connectivity configurations (AUC±95%-CI: 0.89±0.01) in combination with the initial motor impairment. Here, better recovery was linked to a shorter time spent in a functionally integrated network configuration in the acute phase post-stroke.InterpretationDynamic connectivity-derived parameters constitute potent predictors of acute motor impairment and post-stroke recovery, which in the future might inform personalized therapy regimens to promote recovery from acute stroke.

Background and PurposeTo explore the whole-brain dynamic functional network connectivity patterns in acute ischemic stroke (AIS) patients and their relation to stroke severity in the short and long term.MethodsWe investigated large-scale dynamic functional network connectivity of 41 AIS patients two to five days after symptom onset. Re-occurring dynamic connectivity configurations were obtained using a sliding window approach and k-means clustering. We evaluated differences in dynamic patterns between three NIHSS-stroke severity defined groups (mildly, moderately, and severely affected patients). Furthermore, we established correlation analyses between dynamic connectivity estimates and AIS severity as well as neurological recovery within the first 90 days after stroke (DNIHSS). Finally, we built Bayesian hierarchical models to predict acute ischemic stroke severity and examine the inter-relation of dynamic connectivity and clinical measures, with an emphasis on white matter hyperintensity lesion load.ResultsWe identified three distinct dynamic connectivity configurations in the early post-acute stroke phase. More severely affected patients (NIHSS 10–21) spent significantly more time in a highly segregated dynamic connectivity configuration that was characterized by particularly strong connectivity (three-level ANOVA: ppr = –0.68, pConclusionsOur findings demonstrate transiently increased segregation between multiple functional domains in case of severe AIS. Dynamic connectivity involving default mode network components significantly correlated with recovery in the first three months post-stroke.

Accurate predictions of motor impairment after stroke are of cardinal importance for the patient, clinician, and healthcare system. More than 10 years ago, the proportional recovery rule was introduced by promising that high-fidelity predictions of recovery following stroke were based only on the initially lost motor function, at least for a specific fraction of patients. However, emerging evidence suggests that this recovery rule is subject to various confounds and may apply less universally than previously assumed. Here, we systematically revisited stroke outcome predictions by applying strategies to avoid confounds and fitting hierarchical Bayesian models. We jointly analysed 385 post-stroke trajectories from six separate studies—one of the largest overall datasets of upper limb motor recovery. We addressed confounding ceiling effects by introducing a subset approach and ensured correct model estimation through synthetic data simulations. Subsequently, we used model comparisons to assess the underlying nature of recovery within our empirical recovery data. The first model comparison, relying on the conventional fraction of patients called ‘fitters’, pointed to a combination of proportional to lost function and constant recovery. ‘Proportional to lost’ here describes the original notion of proportionality, indicating greater recovery in case of a more severe initial impairment. This combination explained only 32% of the variance in recovery, which is in stark contrast to previous reports of >80%. When instead analysing the complete spectrum of subjects, ‘fitters’ and ‘non-fitters’, a combination of proportional to spared function and constant recovery was favoured, implying a more significant improvement in case of more preserved function. Explained variance was at 53%. Therefore, our quantitative findings suggest that motor recovery post-stroke may exhibit some characteristics of proportionality. However, the variance explained was substantially reduced compared to what has previously been reported. This finding motivates future research moving beyond solely behaviour scores to explain stroke recovery and establish robust and discriminating single-subject predictions.