Reclassifying stroke lesion anatomy

A roadmap for research in post-stroke fatigue: Consensus-based core recommendations from the third Stroke Recovery and Rehabilitation Roundtable

RATIONALE

Fatigue affects almost half of all people living with stroke. Stroke survivors rank understanding fatigue and how to reduce it as one of the highest research priorities.

METHODS

We convened an interdisciplinary, international group of clinical and pre-clinical researchers and lived experience experts. We identified four priority areas: (1) best measurement tools for research, (2) clinical identification of fatigue and potentially modifiable causes, (3) promising interventions and recommendations for future trials, and (4) possible biological mechanisms of fatigue. Cross-cutting themes were aphasia and the voice of people with lived experience. Working parties were formed and structured consensus building processes were followed.

RESULTS

We present 20 recommendations covering outcome measures for research, development, and testing of new interventions and priority areas for future research on the biology of post-stroke fatigue. We developed and recommend the use of the Stroke Fatigue Clinical Assessment Tool.

CONCLUSIONS

By synthesizing current knowledge in post-stroke fatigue across clinical and pre-clinical fields, our work provides a roadmap for future research into post-stroke fatigue.

Scaling behaviours of deep learning and linear algorithms for the prediction of stroke severity

Deep learning has allowed for remarkable progress in many medical scenarios. Deep learning prediction models often require 105-107 examples. It is currently unknown whether deep learning can also enhance predictions of symptoms post-stroke in real-world samples of stroke patients that are often several magnitudes smaller. Such stroke outcome predictions however could be particularly instrumental in guiding acute clinical and rehabilitation care decisions. We here compared the capacities of classically used linear and novel deep learning algorithms in their prediction of stroke severity. Our analyses relied on a total of 1430 patients assembled from the MRI-Genetics Interface Exploration collaboration and a Massachusetts General Hospital-based study. The outcome of interest was National Institutes of Health Stroke Scale-based stroke severity in the acute phase after ischaemic stroke onset, which we predict by means of MRI-derived lesion location. We automatically derived lesion segmentations from diffusion-weighted clinical MRI scans, performed spatial normalization and included a principal component analysis step, retaining 95% of the variance of the original data. We then repeatedly separated a train, validation and test set to investigate the effects of sample size; we subsampled the train set to 100, 300 and 900 and trained the algorithms to predict the stroke severity score for each sample size with regularized linear regression and an eight-layered neural network. We selected hyperparameters on the validation set. We evaluated model performance based on the explained variance (R2) in the test set. While linear regression performed significantly better for a sample size of 100 patients, deep learning started to significantly outperform linear regression when trained on 900 patients. Average prediction performance improved by ∼20% when increasing the sample size 9× [maximum for 100 patients: 0.279 ± 0.005 (R2, 95% confidence interval), 900 patients: 0.337 ± 0.006]. In summary, for sample sizes of 900 patients, deep learning showed a higher prediction performance than typically employed linear methods. These findings suggest the existence of non-linear relationships between lesion location and stroke severity that can be utilized for an improved prediction performance for larger sample sizes.

Mechanisms of Post-Stroke Fatigue: A Follow-Up From the Third Stroke Recovery and Rehabilitation Roundtable

BACKGROUND

Post-stroke fatigue (PSF) is a significant and highly prevalent symptom, whose mechanisms are poorly understood. The third Stroke Recovery and Rehabilitation Roundtable paper on PSF focussed primarily on defining and measuring PSF while mechanisms were briefly discussed. This companion paper to the main paper is aimed at elaborating possible mechanisms of PSF.

METHODS

This paper reviews the available evidence that potentially explains the pathophysiology of PSF and draws parallels from fatigue literature in other conditions. We start by proposing a case for phenotyping PSF based on structural, functional, and behavioral characteristics of PSF. This is followed by discussion of a potentially significant role of early inflammation in the development of fatigue, specifically the impact of low-grade inflammation and its long-term systemic effects resulting in PSF. Of the many neurotransmitter systems in the brain, the dopaminergic systems have the most evidence for a role in PSF, along with a role in sensorimotor processing. Sensorimotor neural network dynamics are compromised as highlighted by evidence from both neurostimulation and neuromodulation studies. The double-edged sword effect of exercise on PSF provides further insight into how PSF might emerge and the importance of carefully titrating interventional paradigms.

CONCLUSION

The paper concludes by synthesizing the presented evidence into a unifying model of fatigue which distinguishes between factors that pre-dispose, precipitate, and perpetuate PSF. This framework will help guide new research into the biological mechanisms of PSF which is a necessary prerequisite for developing treatments to mitigate the debilitating effects of post-stroke fatigue.

A roadmap for research in post-stroke fatigue: Consensus-based core recommendations from the third Stroke Recovery and Rehabilitation Roundtable

RATIONALE

Fatigue affects almost half of all people living with stroke. Stroke survivors rank understanding fatigue and how to reduce it as one of the highest research priorities.

METHODS

We convened an interdisciplinary, international group of clinical and pre-clinical researchers and lived experience experts. We identified four priority areas: (1) best measurement tools for research, (2) clinical identification of fatigue and potentially modifiable causes, (3) promising interventions and recommendations for future trials, and (4) possible biological mechanisms of fatigue. Cross-cutting themes were aphasia and the voice of people with lived experience. Working parties were formed and structured consensus building processes were followed.

RESULTS

We present 20 recommendations covering outcome measures for research, development, and testing of new interventions and priority areas for future research on the biology of post-stroke fatigue. We developed and recommend the use of the Stroke Fatigue Clinical Assessment Tool.

CONCLUSIONS

By synthesizing current knowledge in post-stroke fatigue across clinical and pre-clinical fields, our work provides a roadmap for future research into post-stroke fatigue.

Artificial intelligence (AI) for neurologists: do digital neurones dream of electric sheep?

Artificial intelligence (AI) is routinely mentioned in journals and newspapers, and non-technical outsiders may have difficulty in distinguishing hyperbole from reality. We present a practical guide to help non-technical neurologists to understand healthcare AI. AI is being used to support clinical decisions in treating neurological disorders. We introduce basic concepts of AI, such as machine learning and natural language processing, and explain how AI is being used in healthcare, giving examples its benefits and challenges. We also cover how AI performance is measured, and its regulatory aspects in healthcare. An important theme is that AI is a general-purpose technology like medical statistics, with broad utility applicable in various scenarios, such that niche approaches are outpaced by approaches that are broadly applicable in many disease areas and specialties. By understanding AI basics and its potential applications, neurologists can make informed decisions when evaluating AI used in their clinical practice. This article was written by four humans, with generative AI helping with formatting and image generation.

Predicting the Onset of Ischemic Stroke With Fast High-Resolution 3D MR Spectroscopic Imaging

BACKGROUND

Neurometabolite concentrations provide a direct index of infarction progression in stroke. However, their relationship with stroke onset time remains unclear.

PURPOSE

To assess the temporal dynamics of N-acetylaspartate (NAA), creatine, choline, and lactate and estimate their value in predicting early (<6 hours) vs. late (6-24 hours) hyperacute stroke groups.

STUDY TYPE

Cross-sectional cohort.

POPULATION

A total of 73 ischemic stroke patients scanned at 1.8-302.5 hours after symptom onset, including 25 patients with follow-up scans.

FIELD STRENGTH/SEQUENCE

A 3 T/magnetization-prepared rapid acquisition gradient echo sequence for anatomical imaging, diffusion-weighted imaging and fluid-attenuated inversion recovery imaging for lesion delineation, and 3D MR spectroscopic imaging (MRSI) for neurometabolic mapping.

ASSESSMENT

Patients were divided into hyperacute (0-24 hours), acute (24 hours to 1 week), and subacute (1-2 weeks) groups, and into early (<6 hours) and late (6-24 hours) hyperacute groups. Bayesian logistic regression was used to compare classification performance between early and late hyperacute groups by using different combinations of neurometabolites as inputs.

STATISTICAL TESTS

Linear mixed effects modeling was applied for group-wise comparisons between NAA, creatine, choline, and lactate. Pearson's correlation analysis was used for neurometabolites vs. time. P < 0.05 was considered statistically significant.

RESULTS

Lesional NAA and creatine were significantly lower in subacute than in acute stroke. The main effects of time were shown on NAA (F = 14.321) and creatine (F = 12.261). NAA was significantly lower in late than early hyperacute patients, and was inversely related to time from symptom onset across both groups (r = -0.440). The decrease of NAA and increase of lactate were correlated with lesion volume (NAA: r = -0.472; lactate: r = 0.366) in hyperacute stroke. Discrimination was improved by combining NAA, creatine, and choline signals (area under the curve [AUC] = 0.90).

DATA CONCLUSION

High-resolution 3D MRSI effectively assessed the neurometabolite changes and discriminated early and late hyperacute stroke lesions.

EVIDENCE LEVEL

1.

TECHNICAL EFFICACY

Stage 2.

The elusive metric of lesion load

One of the widely used metrics in lesion-symptom mapping is lesion load that codes the amount of damage to a given brain region of interest. Lesion load aims to reduce the complex 3D lesion information into a feature that can reflect both site of damage, defined by the location of the region of interest, and size of damage within that region of interest. Basically, the process of estimation of lesion load converts a voxel-based lesion map into a region-based lesion map, with regions defined as atlas-based or data-driven spatial patterns. Here, after examining current definitions of lesion load, four methodological issues are discussed: (1) lesion load is agnostic to the location of damage within the region of interest, and it disregards damage outside the region of interest, (2) lesion load estimates are prone to errors introduced by the uncertainty in lesion delineation, spatial warping of the lesion/region, and binarization of the lesion/region, (3) lesion load calculation depends on brain parcellation selection, and (4) lesion load does not necessarily reflect a white matter disconnection. Overall, lesion load, when calculated in a robust way, can serve as a clinically-useful feature for explaining and predicting post-stroke outcome and recovery.

Optimizing automated white matter hyperintensity segmentation in individuals with stroke

White matter hyperintensities (WMHs) are a risk factor for stroke. Consequently, many individuals who suffer a stroke have comorbid WMHs. The impact of WMHs on stroke recovery is an active area of research. Automated WMH segmentation methods are often employed as they require minimal user input and reduce risk of rater bias; however, these automated methods have not been specifically validated for use in individuals with stroke. Here, we present methodological validation of automated WMH segmentation methods in individuals with stroke. We first optimized parameters for FSL's publicly available WMH segmentation software BIANCA in two independent (multi-site) datasets. Our optimized BIANCA protocol achieved good performance within each independent dataset, when the BIANCA model was trained and tested in the same dataset or trained on mixed-sample data. BIANCA segmentation failed when generalizing a trained model to a new testing dataset. We therefore contrasted BIANCA's performance with SAMSEG, an unsupervised WMH segmentation tool available through FreeSurfer. SAMSEG does not require prior WMH masks for model training and was more robust to handling multi-site data. However, SAMSEG performance was slightly lower than BIANCA when data from a single site were tested. This manuscript will serve as a guide for the development and utilization of WMH analysis pipelines for individuals with stroke.

The relevance of rich club regions for functional outcome post-stroke is enhanced in women

This study aimed to investigate the influence of stroke lesions in predefined highly interconnected (rich-club) brain regions on functional outcome post-stroke, determine their spatial specificity and explore the effects of biological sex on their relevance. We analyzed MRI data recorded at index stroke and ~3-months modified Rankin Scale (mRS) data from patients with acute ischemic stroke enrolled in the multisite MRI-GENIE study. Spatially normalized structural stroke lesions were parcellated into 108 atlas-defined bilateral (sub)cortical brain regions. Unfavorable outcome (mRS > 2) was modeled in a Bayesian logistic regression framework. Effects of individual brain regions were captured as two compound effects for (i) six bilateral rich club and (ii) all further non-rich club regions. In spatial specificity analyses, we randomized the split into "rich club" and "non-rich club" regions and compared the effect of the actual rich club regions to the distribution of effects from 1000 combinations of six random regions. In sex-specific analyses, we introduced an additional hierarchical level in our model structure to compare male and female-specific rich club effects. A total of 822 patients (age: 64.7[15.0], 39% women) were analyzed. Rich club regions had substantial relevance in explaining unfavorable functional outcome (mean of posterior distribution: 0.08, area under the curve: 0.8). In particular, the rich club-combination had a higher relevance than 98.4% of random constellations. Rich club regions were substantially more important in explaining long-term outcome in women than in men. All in all, lesions in rich club regions were associated with increased odds of unfavorable outcome. These effects were spatially specific and more pronounced in women.

Optimal CT perfusion thresholds for core and penumbra in acute posterior circulation infarction

Background

At least 20% of strokes involve the posterior circulation (PC). Compared to the anterior circulation, posterior circulation infarction (POCI) are frequently misdiagnosed. CT perfusion (CTP) has advanced stroke care by improving diagnostic accuracy and expanding eligibility for acute therapies. Clinical decisions are predicated upon precise estimates of the ischaemic penumbra and infarct core. Current thresholds for defining core and penumbra are based upon studies of anterior circulation stroke. We aimed to define the optimal CTP thresholds for core and penumbra in POCI.

Methods

Data were analyzed from 331-patients diagnosed with acute POCI enrolled in the International-stroke-perfusion-registry (INSPIRE). Thirty-nine patients with baseline multimodal-CT with occlusion of a large PC-artery and follow up diffusion weighted MRI at 24-48 h were included. Patients were divided into two-groups based on artery-recanalization on follow-up imaging. Patients with no or complete recanalisation were used for penumbral and infarct-core analysis, respectively. A Receiver operating curve (ROC) analysis was used for voxel-based analysis. Optimality was defined as the CTP parameter and threshold which maximized the area-under-the-curve. Linear regression was used for volume based analysis determining the CTP threshold which resulted in the smallest mean volume difference between the acute perfusion lesion and follow up MRI. Subanalysis of PC-regions was performed.

Results

Mean transit time (MTT) and delay time (DT) were the best CTP parameters to characterize ischaemic penumbra (AUC = 0.73). Optimal thresholds for penumbra were a DT >1 s and MTT>145%. Delay time (DT) best estimated the infarct core (AUC = 0.74). The optimal core threshold was a DT >1.5 s. The voxel-based analyses indicated CTP was most accurate in the calcarine (Penumbra-AUC = 0.75, Core-AUC = 0.79) and cerebellar regions (Penumbra-AUC = 0.65, Core-AUC = 0.79). For the volume-based analyses, MTT >160% demonstrated best correlation and smallest mean-volume difference between the penumbral estimate and follow-up MRI (R ² = 0.71). MTT >170% resulted in the smallest mean-volume difference between the core estimate and follow-up MRI, but with poor correlation (R ² = 0.11).

Conclusion

CTP has promising diagnostic utility in POCI. Accuracy of CTP varies by brain region. Optimal thresholds to define penumbra were DT >1 s and MTT >145%. The optimal threshold for core was a DT >1.5 s. However, CTP core volume estimates should be interpreted with caution.

A Focus on the Role of DSC-PWI Dynamic Radiomics Features in Diagnosis and Outcome Prediction of Ischemic Stroke

Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of Ft-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

Precision medicine in stroke: towards personalized outcome predictions using artificial intelligence

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.