Identifying Neuroimaging Markers of Motor Disability in Acute Stroke by Machine Learning Techniques

Normative connectome-based analysis of sensorimotor deficits in acute subcortical stroke

The interrelation between acute ischemic stroke, persistent disability, and uncertain prognosis underscores the need for improved methods to predict clinical outcomes. Traditional approaches have largely focused on analysis of clinical metrics, lesion characteristics, and network connectivity, using techniques such as resting-state functional magnetic resonance imaging (rs-fMRI) and diffusion tensor imaging (DTI). However, these methods are not routinely used in acute stroke diagnostics. This study introduces an innovative approach that not only considers the lesion size in relation to the National Institutes of Health Stroke Scale (NIHSS score), but also evaluates the impact of disrupted fibers and their connections to cortical regions by introducing a disconnection value. By identifying fibers traversing the lesion and estimating their number within predefined regions of interest (ROIs) using a normative connectome atlas, our method bypasses the need for individual DTI scans. In our analysis of MRI data (T1 and T2) from 51 patients with acute or subacute subcortical stroke presenting with motor or sensory deficits, we used simple linear regression to assess the explanatory power of lesion size and disconnection value on NIHSS score. Subsequent hierarchical multiple linear regression analysis determined the incremental value of disconnection metrics over lesion size alone in relation to NIHSS score. Our results showed that models incorporating the disconnection value accounted for more variance than those based solely on lesion size (lesion size explained 44% variance, disconnection value 60%). Furthermore, hierarchical regression revealed a significant improvement (p < 0.001) in model fit when adding the disconnection value, confirming its critical role in stroke assessment. Our approach, which integrates a normative connectome to quantify disconnections to cortical regions, provides a significant improvement in assessing the current state of stroke impact compared to traditional measures that focus on lesion size. This is achieved by taking into account the lesion's location and the connectivity of the affected white matter tracts, providing a more comprehensive assessment of stroke severity as reflected in the NIHSS score. Future research should extend the validation of this approach to larger and more diverse populations, with a focus on refining its applicability to clinical assessment and long-term outcome prediction.

Contributions of Machine Learning in the Management of Stroke: A Bibliometric Analysis of the 50 Most Cited Articles

BACKGROUND

Though currently considered a 'black box,' machine learning (ML) has a promising future to ameliorate the health-care burden of stroke which is the second leading cause of mortality worldwide. Through this study, we sought to review the most influential articles on the applications of ML in stroke.

METHODS

Web of Sciences database was searched, and a list of the top 50 most cited articles, assessing the application of ML in stroke, was prepared by 2 authors, independently. Subsequently, a detailed analysis was performed to characterize the most impactful studies.

RESULTS

The total number of citations to the top 50 articles were 2959 (range 35-243 citations) with a median of 47 citations. Highest number of articles were published in the journal Stroke and the United States was the major contributing country. The majority of the studies focused on the utilization of ML to improve stroke risk prediction, diagnosis, and outcome prediction. Statistical analysis revealed an insignificant association between the total and mean number of citations and the impact factor of the journal (P = 0.516 and 0.987, respectively).

CONCLUSIONS

Recent years have witnessed a surge in the application of ML in stroke, with an enhancement in interest and funding over the years. ML has revolutionized the management of stroke and continues to aid in the neurosurgical decision-making and care in stroke patients.

Behavioral and neuroanatomical correlates of facial emotion processing in post-stroke depression

BACKGROUND

Emotion processing deficits are known to accompany depressive symptoms and are often seen in stroke patients. Little is known about the influence of post-stroke depressive (PSD) symptoms and specific brain lesions on altered emotion processing abilities and how these phenomena develop over time. This potential relationship may impact post-stroke rehabilitation of neurological and psychosocial function. To address this scientific gap, we investigated the relationship between PSD symptoms and emotion processing abilities in a longitudinal study design from the first days post-stroke into the early chronic phase.

METHODS

Twenty-six ischemic stroke patients performed an emotion processing task on videos with emotional faces ('happy,' 'sad,' 'anger,' 'fear,' and 'neutral') at different intensity levels (20%, 40%, 60%, 80%, 100%). Recognition accuracies and response times were measured, as well as scores of depressive symptoms (Montgomery-Åsberg Depression Rating Scale). Twenty-eight healthy participants matched in age and sex were included as a control group. Whole-brain support-vector regression lesion-symptom mapping (SVR-LSM) analyses were performed to investigate whether specific lesion locations were associated with the recognition accuracy of specific emotion categories.

RESULTS

Stroke patients performed worse in overall recognition accuracy compared to controls, specifically in the recognition of happy, sad, and fearful faces. Notably, more depressed stroke patients showed an increased processing towards specific negative emotions, as they responded significantly faster to angry faces and recognized sad faces of low intensities significantly more accurately. These effects obtained for the first days after stroke partly persisted to follow-up assessment several months later. SVR-LSM analyses revealed that inferior and middle frontal regions (IFG/MFG) and insula and putamen were associated with emotion-recognition deficits in stroke. Specifically, recognizing happy facial expressions was influenced by lesions affecting the anterior insula, putamen, IFG, MFG, orbitofrontal cortex, and rolandic operculum. Lesions in the posterior insula, rolandic operculum, and MFG were also related to reduced recognition accuracy of fearful facial expressions, whereas recognition deficits of sad faces were associated with frontal pole, IFG, and MFG damage.

CONCLUSION

PSD symptoms facilitate processing negative emotional stimuli, specifically angry and sad facial expressions. The recognition accuracy of different emotional categories was linked to brain lesions in emotion-related processing circuits, including insula, basal ganglia, IFG, and MFG. In summary, our study provides support for psychosocial and neural factors underlying emotional processing after stroke, contributing to the pathophysiology of PSD.

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.

Neuroanatomy of post-stroke depression: the association between symptom clusters and lesion location

Post-stroke depression affects about 30% of stroke patients and often hampers functional recovery. The diagnosis of depression encompasses heterogeneous symptoms at emotional, motivational, cognitive, behavioural or somatic levels. Evidence indicates that depression is caused by disruption of bio-aminergic fibre tracts between prefrontal and limbic or striatal brain regions comprising different functional networks. Voxel-based lesion-symptom mapping studies reported discrepant findings regarding the association between infarct locations and depression. Inconsistencies may be due to the usage of sum scores, thereby mixing different symptoms of depression. In this cross-sectional study, we used multivariate support vector regression for lesion-symptom mapping to identify regions significantly involved in distinct depressive symptom domains and global depression. MRI lesion data were included from 200 patients with acute first-ever ischaemic stroke (mean 0.9 ± 1.5 days of post-stroke). The Montgomery-Åsberg Depression Rating interview assessed depression severity in five symptom domains encompassing motivational, emotional and cognitive symptoms deficits, anxiety and somatic symptoms and was examined 8.4 days of post-stroke (±4.3). We found that global depression severity, irrespective of individual symptom domains, was primarily linked to right hemispheric lesions in the dorsolateral prefrontal cortex and inferior frontal gyrus. In contrast, when considering distinct symptom domains individually, the analyses yielded much more sensitive results in regions where the correlations with the global depression score yielded no effects. Accordingly, motivational deficits were associated with lesions in orbitofrontal cortex, dorsolateral prefrontal cortex, pre- and post-central gyri and basal ganglia, including putamen and pallidum. Lesions affecting the dorsal thalamus, anterior insula and somatosensory cortex were significantly associated with emotional symptoms such as sadness. Damage to the dorsolateral prefrontal cortex was associated with concentration deficits, cognitive symptoms of guilt and self-reproach. Furthermore, somatic symptoms, including loss of appetite and sleep disturbances, were linked to the insula, parietal operculum and amygdala lesions. Likewise, anxiety was associated with lesions impacting the central operculum, insula and inferior frontal gyrus. Interestingly, symptoms of anxiety were exclusively left hemispheric, whereas the lesion-symptom associations of the other domains were lateralized to the right hemisphere. In conclusion, this large-scale study shows that in acute stroke patients, differential post-stroke depression symptom domains are associated with specific structural correlates. Our findings extend existing concepts on the neural underpinnings of depressive symptoms, indicating that differential lesion patterns lead to distinct depressive symptoms in the first weeks of post-stroke. These findings may facilitate the development of personalized treatments to improve post-stroke rehabilitation.

Brain Topological Reorganization Associated with Visual Neglect After Stroke

Background/Purpose: To identify brain hubs that are behaviorally relevant for neglect after stroke as well as to characterize their functional architecture of communication. Methods: Twenty acute right hemisphere damaged patients underwent neuropsychological and resting-state functional magnetic resonance imaging sessions. Spatial neglect was assessed by means of the Center of Cancellation on the Bells Cancellation Test. For each patient, resting-state functional connectivity matrices were derived by adopting a brain parcellation scheme consisting of 153 nodes. For every node, we extracted its betweenness centrality (BC) defined as the portion of all shortest paths in the connectome involving such node. Then, neglect hubs were identified as those regions showing a high correlation between their BC and neglect scores. Results: A first set of neglect hubs was identified in multiple systems including dorsal attention and ventral attention, default mode, and frontoparietal executive-control networks within the damaged hemisphere as well as in the posterior and anterior cingulate cortex. Such cortical regions exhibited a loss of BC and increased (i.e., less efficient) weighted shortest path length (WSPL) related to severe neglect. Conversely, a second group of neglect hubs found in visual and motor networks, in the undamaged hemisphere, exhibited a pathological increase of BC and reduction of WSPL associated with severe neglect. Conclusion: The topological reorganization of the brain in neglect patients might reflect a maladaptive shift in processing spatial information from higher level associative-control systems to lower level visual and sensory-motor processing areas after a right hemisphere lesion.

DEEP LEARNING PREDICTION OF MOTOR PERFORMANCE IN STROKE INDIVIDUALS USING NEUROIMAGING DATA

The degree of motor impairment and profile of recovery after stroke are difficult to predict for each individual. Measures obtained from clinical assessments, as well as neurophysiological and neuroimaging techniques have been used as potential biomarkers of motor recovery, with limited accuracy up to date. To address this, the present study aimed to develop a deep learning model based on structural brain images obtained from stroke participants and healthy volunteers. The following inputs were used in a multi-channel 3D convolutional neural network (CNN) model: fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity maps obtained from Diffusion Tensor Imaging (DTI) images, white and gray matter intensity values obtained from Magnetic Resonance Imaging, as well as demographic data (e.g., age, gender). Upper limb motor function was classified into "Poor" and "Good" categories. To assess the performance of the DL model, we compared it to more standard machine learning (ML) classifiers including k-nearest neighbor, support vector machines (SVM), Decision Trees, Random Forests, Ada Boosting, and Naïve Bayes, whereby the inputs of these classifiers were the features taken from the fully connected layer of the CNN model. The highest accuracy and area under the curve values were 0.92 and 0.92 for the 3D-CNN and 0.91 and 0.91 for the SVM, respectively. The multi-channel 3D-CNN with residual blocks and SVM supported by DL was more accurate than traditional ML methods to classify upper limb motor impairment in the stroke population. These results suggest that combining volumetric DTI maps and measures of white and gray matter integrity can improve the prediction of the degree of motor impairment after stroke. Identifying the potential of recovery early on after a stroke could promote the allocation of resources to optimize the functional independence of these individuals and their quality of life.

Predicting poststroke dyskinesia with resting-state functional connectivity in the motor network

SIGNIFICANCE

Motor function evaluation is essential for poststroke dyskinesia rehabilitation. Neuroimaging techniques combined with machine learning help decode a patient's functional status. However, more research is needed to investigate how individual brain function information predicts the dyskinesia degree of stroke patients.

AIM

We investigated stroke patients' motor network reorganization and proposed a machine learning-based method to predict the patients' motor dysfunction.

APPROACH

Near-infrared spectroscopy (NIRS) was used to measure hemodynamic signals of the motor cortex in the resting state (RS) from 11 healthy subjects and 31 stroke patients, 15 with mild dyskinesia (Mild), and 16 with moderate-to-severe dyskinesia (MtS). The graph theory was used to analyze the motor network characteristics.

RESULTS

The small-world properties of the motor network were significantly different between groups: (1) clustering coefficient, local efficiency, and transitivity: MtS > Mild > Healthy and (2) global efficiency: MtS < Mild < Healthy. These four properties linearly correlated with patients' Fugl-Meyer Assessment scores. Using the small-world properties as features, we constructed support vector machine (SVM) models that classified the three groups of subjects with an accuracy of 85.7%.

CONCLUSIONS

Our results show that NIRS, RS functional connectivity, and SVM together constitute an effective method for assessing the poststroke dyskinesia degree at the individual level.

Identifying and distinguishing of essential tremor and Parkinson's disease with grouped stability analysis based on searchlight-based MVPA

BACKGROUND

Since both essential tremor (ET) and Parkinson's disease (PD) are movement disorders and share similar clinical symptoms, it is very difficult to recognize the differences in the presentation, course, and treatment of ET and PD, which leads to misdiagnosed commonly.

PURPOSE

Although neuroimaging biomarker of ET and PD has been investigated based on statistical analysis, it is unable to assist the clinical diagnosis of ET and PD and ensure the efficiency of these biomarkers. The aim of the study was to identify the neuroimaging biomarkers of ET and PD based on structural magnetic resonance imaging (MRI). Moreover, the study also distinguished ET from PD via these biomarkers to validate their classification performance.

METHODS

This study has developed and implemented a three-level machine learning framework to identify and distinguish ET and PD. First of all, at the model-level assessment, the searchlight-based machine learning method has been used to identify the group differences of patients (ET/PD) with normal controls (NCs). And then, at the feature-level assessment, the stability of group differences has been tested based on structural brain atlas separately using the permutation test to identify the robust neuroimaging biomarkers. Furthermore, the identified biomarkers of ET and PD have been applied to classify ET from PD based on machine learning techniques. Finally, the identified biomarkers have been compared with the previous findings of the biology-level assessment.

RESULTS

According to the biomarkers identified by machine learning, this study has found widespread alterations of gray matter (GM) for ET and large overlap between ET and PD and achieved superior classification performance (PCA + SVM, accuracy = 100%).

CONCLUSIONS

This study has demonstrated the significance of a machine learning framework to identify and distinguish ET and PD. Future studies using a large data set are needed to confirm the potential clinical application of machine learning techniques to discern between PD and ET.

Resting-state functional connectivity for determining outcomes in upper extremity function after stroke: A functional near-infrared spectroscopy study

OBJECTIVE

Functional near-infrared spectroscopy (fNIRS) is a non-invasive and promising tool to map the brain functional networks in stroke recovery. Our study mainly aimed to use fNIRS to detect the different patterns of resting-state functional connectivity (RSFC) in subacute stroke patients with different degrees of upper extremity motor impairment defined by Fugl-Meyer motor assessment of upper extremity (FMA-UE). The second aim was to investigate the association between FMA-UE scores and fNIRS-RSFC among different regions of interest (ROIs) in stroke patients.

METHODS

Forty-nine subacute (2 weeks-6 months) stroke patients with subcortical lesions were enrolled and were classified into three groups based on FMA-UE scores: mild impairment (n = 17), moderate impairment (n = 13), and severe impairment (n = 19). All patients received FMA-UE assessment and 10-min resting-state fNIRS monitoring. The fNIRS signals were recorded over seven ROIs: bilateral dorsolateral prefrontal cortex (DLPFC), middle prefrontal cortex (MPFC), bilateral primary motor cortex (M1), and bilateral primary somatosensory cortex (S1). Functional connectivity (FC) was calculated by correlation coefficients between each channel and each ROI pair. To reveal the comprehensive differences in FC among three groups, we compared FC on the group level and ROI level. In addition, to determine the associations between FMA-UE scores and RSFC among different ROIs, Spearman's correlation analyses were performed with a significance threshold of p < 0.05. For easy comparison, we defined the left hemisphere as the ipsilesional hemisphere and flipped the lesional right hemisphere in MATLAB R2013b.

RESULTS

For the group-level comparison, the one-way ANOVA and post-hoc t-tests (mild vs. moderate; mild vs. severe; moderate vs. severe) showed that there was a significant difference among three groups (F = 3.42, p = 0.04) and the group-averaged FC in the mild group (0.64 ± 0.14) was significantly higher than that in the severe group (0.53 ± 0.14, p = 0.013). However, there were no significant differences between the mild and moderate group (MD ± SE = 0.05 ± 0.05, p = 0.35) and between the moderate and severe group (MD ± SE = 0.07 ± 0.05, p = 0.16). For the ROI-level comparison, the severe group had significantly lower FC of ipsilesional DLPFC-ipsilesional M1 [p = 0.015, false discovery rate (FDR)-corrected] and ipsilesional DLPFC-contralesional M1 (p = 0.035, FDR-corrected) than those in the mild group. Moreover, the result of Spearman's correlation analyses showed that there were significant correlations between FMA-UE scores and FC of the ipsilesional DLPFC-ipsilesional M1 (r = 0.430, p = 0.002), ipsilesional DLPFC-contralesional M1 (r = 0.388, p = 0.006), ipsilesional DLPFC-MPFC (r = 0.365, p = 0.01), and ipsilesional DLPFC-contralesional DLPFC (r = 0.330, p = 0.021).

CONCLUSION

Our findings indicate that different degrees of post-stroke upper extremity impairment reflect different RSFC patterns, mainly in the connection between DLPFC and bilateral M1. The association between FMA-UE scores and the FC of ipsilesional DLPFC-associated ROIs suggests that the ipsilesional DLPFC may play an important role in motor-related plasticity. These findings can help us better understand the neurophysiological mechanisms of upper extremity motor impairment and recovery in subacute stroke patients from different perspectives. Furthermore, it sheds light on the ipsilesional DLPFC-bilateral M1 as a possible neuromodulation target.

Advancing brain network models to reconcile functional neuroimaging and clinical research

Functional magnetic resonance imaging (fMRI) captures information on brain function beyond the anatomical alterations that are traditionally visually examined by neuroradiologists. However, the fMRI signals are complex in addition to being noisy, so fMRI still faces limitations for clinical applications. Here we review methods that have been proposed as potential solutions so far, namely statistical, biophysical and decoding models, with their strengths and weaknesses. We especially evaluate the ability of these models to directly predict clinical variables from their parameters (predictability) and to extract clinically relevant information regarding biological mechanisms and relevant features for classification and prediction (interpretability). We then provide guidelines for useful applications and pitfalls of such fMRI-based models in a clinical research context, looking beyond the current state of the art. In particular, we argue that the clinical relevance of fMRI calls for a new generation of models for fMRI data, which combine the strengths of both biophysical and decoding models. This leads to reliable and biologically meaningful model parameters, which thus fulfills the need for simultaneous interpretability and predictability. In our view, this synergy is fundamental for the discovery of new pharmacological and interventional targets, as well as the use of models as biomarkers in neurology and psychiatry.

Specific subsystems of the inferior parietal lobule are associated with hand dysfunction following stroke: A cross-sectional resting-state fMRI study

AIM

The inferior parietal lobule (IPL) plays important roles in reaching and grasping during hand movements, but how reorganizations of IPL subsystems underlie the paretic hand remains unclear. We aimed to explore whether specific IPL subsystems were disrupted and associated with hand performance after chronic stroke.

METHODS

In this cross-sectional study, we recruited 65 patients who had chronic subcortical strokes and 40 healthy controls from China. Each participant underwent the Fugl-Meyer Assessment of Hand and Wrist and resting-state fMRI at baseline. We mainly explored the group differences in resting-state effective connectivity (EC) patterns for six IPL subregions in each hemisphere, and we correlated these EC patterns with paretic hand performance across the whole stroke group and stroke subgroups. Moreover, we used receiver operating characteristic curve analysis to distinguish the stroke subgroups with partially (PPH) and completely (CPH) paretic hands.

RESULTS

Stroke patients exhibited abnormal EC patterns with ipsilesional PFt and bilateral PGa, and five sensorimotor-parietal/two parietal-temporal subsystems were positively or negatively correlated with hand performance. Compared with CPH patients, PPH patients exhibited abnormal EC patterns with the contralesional PFop. The PPH patients had one motor-parietal subsystem, while the CPH patients had one sensorimotor-parietal and three parietal-occipital subsystems that were associated with hand performance. Notably, the EC strength from the contralesional PFop to the ipsilesional superior frontal gyrus could distinguish patients with PPH from patients with CPH.

CONCLUSIONS

The IPL subsystems manifest specific functional reorganization and are associated with hand dysfunction following chronic stroke.

Somatosensory Deficits After Stroke: Insights From MRI Studies

Somatosensory deficits after stroke are a major health problem, which can impair patients' health status and quality of life. With the developments in human brain mapping techniques, particularly magnetic resonance imaging (MRI), many studies have applied those techniques to unravel neural substrates linked to apoplexy sequelae. Multi-parametric MRI is a vital method for the measurement of stroke and has been applied to diagnose stroke severity, predict outcome and visualize changes in activation patterns during stroke recovery. However, relatively little is known about the somatosensory deficits after stroke and their recovery. This review aims to highlight the utility and importance of MRI techniques in the field of somatosensory deficits and synthesizes corresponding articles to elucidate the mechanisms underlying the occurrence and recovery of somatosensory symptoms. Here, we start by reviewing the anatomic and functional features of the somatosensory system. And then, we provide a discussion of MRI techniques and analysis methods. Meanwhile, we present the application of those techniques and methods in clinical studies, focusing on recent research advances and the potential for clinical translation. Finally, we identify some limitations and open questions of current imaging studies that need to be addressed in future research.

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.

Is it left or is it right? A classification approach for investigating hemispheric differences in low and high dimensionality

Hemispheric asymmetries, i.e., differences between the two halves of the brain, have extensively been studied with respect to both structure and function. Commonly employed pairwise comparisons between left and right are suitable for finding differences between the hemispheres, but they come with several caveats when assessing multiple asymmetries. What is more, they are not designed for identifying the characterizing features of each hemisphere. Here, we present a novel data-driven framework-based on machine learning-based classification-for identifying the characterizing features that underlie hemispheric differences. Using voxel-based morphometry data from two different samples (n = 226, n = 216), we separated the hemispheres along the midline and used two different pipelines: First, for investigating global differences, we embedded the hemispheres into a two-dimensional space and applied a classifier to assess if the hemispheres are distinguishable in their low-dimensional representation. Second, to investigate which voxels show systematic hemispheric differences, we employed two classification approaches promoting feature selection in high dimensions. The two hemispheres were accurately classifiable in both their low-dimensional (accuracies: dataset 1 = 0.838; dataset 2 = 0.850) and high-dimensional (accuracies: dataset 1 = 0.966; dataset 2 = 0.959) representations. In low dimensions, classification of the right hemisphere showed higher precision (dataset 1 = 0.862; dataset 2 = 0.894) compared to the left hemisphere (dataset 1 = 0.818; dataset 2 = 0.816). A feature selection algorithm in the high-dimensional analysis identified voxels that most contribute to accurate classification. In addition, the map of contributing voxels showed a better overlap with moderate to highly lateralized voxels, whereas conventional t test with threshold-free cluster enhancement best resembled the LQ map at lower thresholds. Both the low- and high-dimensional classifiers were capable of identifying the hemispheres in subsamples of the datasets, such as males, females, right-handed, or non-right-handed participants. Our study indicates that hemisphere classification is capable of identifying the hemisphere in their low- and high-dimensional representation as well as delineating brain asymmetries. The concept of hemisphere classifiability thus allows a change in perspective, from asking what differs between the hemispheres towards focusing on the features needed to identify the left and right hemispheres. Taking this perspective on hemispheric differences may contribute to our understanding of what makes each hemisphere special.

Selectively disrupted sensorimotor circuits in chronic stroke with hand dysfunction

Aim

To investigate the directional and selective disconnection of the sensorimotor cortex (SMC) subregions in chronic stroke patients with hand dysfunction.

Methods

We mapped the resting‐state fMRI effective connectivity (EC) patterns for seven SMC subregions in each hemisphere of 65 chronic stroke patients and 40 healthy participants and correlated these patterns with paretic hand performance.

Results

Compared with controls, patients demonstrated disrupted EC in the ipsilesional primary motor cortex_4p, ipsilesional primary somatosensory cortex_2 (PSC_2), and contralesional PSC_3a. Moreover, we found that EC values of the contralesional PSC_1 to contralesional precuneus, the ipsilesional inferior temporal gyrus to ipsilesional PSC_1, and the ipsilesional PSC_1 to contralesional postcentral gyrus were correlated with paretic hand performance across all patients. We further divided patients into partially (PPH) and completely (CPH) paretic hand subgroups. Compared with CPH patients, PPH patients demonstrated decreased EC in the ipsilesional premotor_6 and ipsilesional PSC_1. Interestingly, we found that paretic hand performance was positively correlated with seven sensorimotor circuits in PPH patients, while it was negatively correlated with five sensorimotor circuits in CPH patients.

Conclusion

SMC neurocircuitry was selectively disrupted after chronic stroke and associated with diverse hand outcomes, which deepens the understanding of SMC reorganization.

MRI radiomic features-based machine learning approach to classify ischemic stroke onset time

PURPOSE

We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options.

METHODS

This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts.

RESULTS

Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ .

CONCLUSIONS

A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.

Functional connectivity drives stroke recovery: shifting the paradigm from correlation to causation

Stroke is a leading cause of disability, with deficits encompassing multiple functional domains. The heterogeneity underlying stroke poses significant challenges in the prediction of post-stroke recovery, prompting the development of neuroimaging-based biomarkers. Structural neuroimaging measurements, particularly those reflecting corticospinal tract injury, are well-documented in the literature as potential biomarker candidates of post-stroke motor recovery. Consistent with the view of stroke as a 'circuitopathy', functional neuroimaging measures probing functional connectivity may also prove informative in post-stroke recovery. An important step in the development of biomarkers based on functional neural network connectivity is the establishment of causality between connectivity and post-stroke recovery. Current evidence predominantly involves statistical correlations between connectivity measures and post-stroke behavioral status, either cross-sectionally or serially over time. However, the advancement of functional connectivity application in stroke depends on devising experiments that infer causality. In 1965, Sir Austin Bradford Hill introduced nine viewpoints to consider when determining the causality of an association: [1] Strength, [2] Consistency [3] Specificity, [4] Temporality, [5] Biological gradient, [6] Plausibility, [7] Coherence, [8] Experiment, and [9] Analogy. Collectively referred to as the Bradford Hill Criteria, these points have been widely adopted in epidemiology. In this review, we assert the value of implementing Bradford Hill's framework to stroke rehabilitation and neuroimaging. We focus on the role of neural network connectivity measurements acquired from task-oriented and resting-state functional magnetic resonance imaging, electroencephalography, magnetoencephalography, and functional near-infrared spectroscopy in describing and predicting post-stroke behavioral status and recovery. We also identify research opportunities within each Bradford Hill tenet to shift the experimental paradigm from correlation to causation.

Dynamic connectivity predicts acute motor impairment and recovery post-stroke

Thorough assessment of cerebral dysfunction after acute lesions is paramount to optimize predicting clinical outcomes. We here built random forest classifier-based prediction models of acute motor impairment and recovery post-stroke. Predictions relied on structural and resting-state fMRI data from 54 stroke patients scanned within the first days of symptom onset. Functional connectivity was estimated via static and dynamic approaches. Motor performance was phenotyped in the acute phase and 6 months later. A 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, 95% confidence interval: 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 (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 (0.89 ± 0.01) in combination with the initial impairment. Here, better recovery was linked to a shorter time spent in a functionally integrated configuration. Dynamic connectivity-derived parameters constitute potent predictors of acute impairment and recovery, which, in the future, might inform personalized therapy regimens to promote stroke recovery.

The structural connectome and motor recovery after stroke: predicting natural recovery

Stroke patients vary considerably in terms of outcomes: some patients present 'natural' recovery proportional to their initial impairment (fitters), while others do not (non-fitters). Thus, a key challenge in stroke rehabilitation is to identify individual recovery potential to make personalized decisions for neuro-rehabilitation, obviating the 'one-size-fits-all' approach. This goal requires (i) the prediction of individual courses of recovery in the acute stage; and (ii) an understanding of underlying neuronal network mechanisms. 'Natural' recovery is especially variable in severely impaired patients, underscoring the special clinical importance of prediction for this subgroup. Fractional anisotropy connectomes based on individual tractography of 92 patients were analysed 2 weeks after stroke (TA) and their changes to 3 months after stroke (TC - TA). Motor impairment was assessed using the Fugl-Meyer Upper Extremity (FMUE) scale. Support vector machine classifiers were trained to separate patients with natural recovery from patients without natural recovery based on their whole-brain structural connectomes and to define their respective underlying network patterns, focusing on severely impaired patients (FMUE < 20). Prediction accuracies were cross-validated internally, in one independent dataset and generalized in two independent datasets. The initial connectome 2 weeks after stroke was capable of segregating fitters from non-fitters, most importantly among severely impaired patients (TA: accuracy = 0.92, precision = 0.93). Secondary analyses studying recovery-relevant network characteristics based on the selected features revealed (i) relevant differences between networks contributing to recovery at 2 weeks and network changes over time (TC - TA); and (ii) network properties specific to severely impaired patients. Important features included the parietofrontal motor network including the intraparietal sulcus, premotor and primary motor cortices and beyond them also attentional, somatosensory or multimodal areas (e.g. the insula), strongly underscoring the importance of whole-brain connectome analyses for better predicting and understanding recovery from stroke. Computational approaches based on structural connectomes allowed the individual prediction of natural recovery 2 weeks after stroke onset, especially in the difficult to predict group of severely impaired patients, and identified the relevant underlying neuronal networks. This information will permit patients to be stratified into different recovery groups in clinical settings and will pave the way towards personalized precision neurorehabilitative treatment.

Early motor network connectivity after stroke: An interplay of general reorganization and state-specific compensation

Motor recovery after stroke relies on functional reorganization of the motor network, which is commonly assessed via functional magnetic resonance imaging (fMRI)-based resting-state functional connectivity (rsFC) or task-related effective connectivity (trEC). Measures of either connectivity mode have been shown to successfully explain motor impairment post-stroke, posing the question whether motor impairment is more closely reflected by rsFC or trEC. Moreover, highly similar changes in ipsilesional and interhemispheric motor network connectivity have been reported for both rsFC and trEC after stroke, suggesting that altered rsFC and trEC may capture similar aspects of information integration in the motor network reflecting principle, state-independent mechanisms of network reorganization rather than state-specific compensation strategies. To address this question, we conducted the first direct comparison of rsFC and trEC in a sample of early subacute stroke patients (n = 26, included on average 7.3 days post-stroke). We found that both rsFC and trEC explained motor impairment across patients, stressing the clinical potential of fMRI-based connectivity. Importantly, intrahemispheric connectivity between ipsilesional M1 and premotor areas depended on the activation state, whereas interhemispheric connectivity between homologs was state-independent. From a mechanistic perspective, our results may thus arise from two distinct aspects of motor network plasticity: task-specific compensation within the ipsilesional hemisphere and a more fundamental form of reorganization between hemispheres.

Cortical propagation tracks functional recovery after stroke

Stroke is a debilitating condition affecting millions of people worldwide. The development of improved rehabilitation therapies rests on finding biomarkers suitable for tracking functional damage and recovery. To achieve this goal, we perform a spatiotemporal analysis of cortical activity obtained by wide-field calcium images in mice before and after stroke. We compare spontaneous recovery with three different post-stroke rehabilitation paradigms, motor training alone, pharmacological contralesional inactivation and both combined. We identify three novel indicators that are able to track how movement-evoked global activation patterns are impaired by stroke and evolve during rehabilitation: the duration, the smoothness, and the angle of individual propagation events. Results show that, compared to pre-stroke conditions, propagation of cortical activity in the subacute phase right after stroke is slowed down and more irregular. When comparing rehabilitation paradigms, we find that mice treated with both motor training and pharmacological intervention, the only group associated with generalized recovery, manifest new propagation patterns, that are even faster and smoother than before the stroke. In conclusion, our new spatiotemporal propagation indicators could represent promising biomarkers that are able to uncover neural correlates not only of motor deficits caused by stroke but also of functional recovery during rehabilitation. In turn, these insights could pave the way towards more targeted post-stroke therapies.

Millions of people worldwide suffer from long-lasting motor deficits caused by stroke. Very recently, the two basic therapeutic approaches, motor training and pharmacological intervention, have been combined in order to achieve a more efficient functional recovery. In this study, we analyze the neurophysiological activity in the brain of mice observed with in vivo calcium imaging before and after the induction of a stroke. We use a newly developed universal approach based on the temporal sequence of local activation in different brain regions to quantify three properties of global propagation patterns: duration, smoothness and angle. These innovative spatiotemporal propagation indicators allow us to track damage and functional recovery following stroke and to quantify the relative success of motor training, pharmacological inactivation, and a combination of both, compared to spontaneous recovery. We show that all three treatments reverse the alterations observed during the subacute phase right after stroke. We also find that combining motor training and pharmacological intervention does not restore pre-stroke features but rather leads to the emergence of new propagation patterns that, surprisingly, are even faster and smoother than the pre-stroke patterns.

Leveraging artificial intelligence in ischemic stroke imaging

Artificial intelligence (AI) is having a disruptive and transformative effect on clinical medicine. Prompt clinical diagnosis and imaging are critical for minimizing the morbidity and mortality associated with ischemic strokes. Clinicians must understand the current strengths and limitations of AI to provide optimal patient care. Ischemic stroke is one of the medical fields that have been extensively evaluated by artificial intelligence. Presented herein is a review of artificial intelligence applied to clinical management of stroke, geared toward clinicians. In this review, we explain the basic concept of AI and machine learning. This review is without coding and mathematical details and targets the clinicians involved in stroke management without any computer or mathematics' background. Here the AI application in ischemic stroke is summarized and classified into stroke imaging (automated diagnosis of brain infarction, automated ASPECT score calculation, infarction segmentation), prognosis prediction, and patients' selection for treatment.

Calhoun V, Grefkes C, Rost NS. Abnormal dynamic functional connectivity is linked to recovery after acute ischemic stroke

The aim of the current study was to explore the whole-brain dynamic functional connectivity patterns in acute ischemic stroke (AIS) patients and their relation to short and long-term stroke severity. We investigated resting-state functional MRI-based dynamic functional 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 built Bayesian hierarchical models to evaluate the predictive capacity of dynamic connectivity and examine the interrelation with clinical measures, such as white matter hyperintensity lesions. Finally, we established correlation analyses between dynamic connectivity and AIS severity as well as 90-day neurological recovery (ΔNIHSS). We identified three distinct dynamic connectivity configurations acutely post-stroke. More severely affected patients spent significantly more time in a configuration that was characterized by particularly strong connectivity and isolated processing of functional brain domains (three-level ANOVA: p < .05, post hoc t tests: p < .05, FDR-corrected). Configuration-specific time estimates possessed predictive capacity of stroke severity in addition to the one of clinical measures. Recovery, as indexed by the realized change of the NIHSS over time, was significantly linked to the dynamic connectivity between bilateral intraparietal lobule and left angular gyrus (Pearson's r = -.68, p = .003, FDR-corrected). Our findings demonstrate transiently increased isolated information processing in multiple functional domains in case of severe AIS. Dynamic connectivity involving default mode network components significantly correlated with recovery in the first 3 months poststroke.

Automated Assessment of Peristomal Skin Discoloration and Leakage Area Using Artificial Intelligence

For people living with an ostomy, development of peristomal skin complications (PSCs) is the most common post-operative challenge. A visual sign of PSCs is discoloration (redness) of the peristomal skin often resulting from leakage of ostomy output under the baseplate. If left unattended, a mild skin condition may progress into a severe disorder; consequently, it is important to monitor discoloration and leakage patterns closely. The Ostomy Skin Tool is current state-of-the-art for evaluation of peristomal skin, but it relies on patients visiting their healthcare professional regularly. To enable close monitoring of peristomal skin over time, an automated strategy not relying on scheduled consultations is required. Several medical fields have implemented automated image analysis based on artificial intelligence, and these deep learning algorithms have become increasingly recognized as a valuable tool in healthcare. Therefore, the main objective of this study was to develop deep learning algorithms which could provide automated, consistent, and objective assessments of changes in peristomal skin discoloration and leakage patterns. A total of 614 peristomal skin images were used for development of the discoloration model, which predicted the area of the discolored peristomal skin with an accuracy of 95% alongside precision and recall scores of 79.6 and 75.0%, respectively. The algorithm predicting leakage patterns was developed based on 954 product images, and leakage area was determined with 98.8% accuracy, 75.0% precision, and 71.5% recall. Combined, these data for the first time demonstrate implementation of artificial intelligence for automated assessment of changes in peristomal skin discoloration and leakage patterns.

Decoding with confidence: Statistical control on decoder maps

In brain imaging, decoding is widely used to infer relationships between brain and cognition, or to craft brain-imaging biomarkers of pathologies. Yet, standard decoding procedures do not come with statistical guarantees, and thus do not give confidence bounds to interpret the pattern maps that they produce. Indeed, in whole-brain decoding settings, the number of explanatory variables is much greater than the number of samples, hence classical statistical inference methodology cannot be applied. Specifically, the standard practice that consists in thresholding decoding maps is not a correct inference procedure. We contribute a new statistical-testing framework for this type of inference. To overcome the statistical inefficiency of voxel-level control, we generalize the Family Wise Error Rate (FWER) to account for a spatial tolerance δ, introducing the δ-Family Wise Error Rate (δ-FWER). Then, we present a decoding procedure that can control the δ-FWER: the Ensemble of Clustered Desparsified Lasso (EnCluDL), a procedure for multivariate statistical inference on high-dimensional structured data. We evaluate the statistical properties of EnCluDL with a thorough empirical study, along with three alternative procedures including decoder map thresholding. We show that EnCluDL exhibits the best recovery properties while ensuring the expected statistical control.

Functional connectivity and upper limb function in patients after pediatric arterial ischemic stroke with contralateral corticospinal tract wiring

To develop individualized motor rehabilitation, knowledge of the relationship between neuroplastic reorganization and motor recovery after pediatric arterial ischemic stroke (AIS) is crucial. Thus, we investigated functional connectivity in patients after AIS with good motor outcome and in patients with hemiparesis compared with typically developing peers. We included 18 patients (n = 9 with hemiparesis, n = 9 with good motor outcome) with pediatric AIS in the chronic phase (≥ 2 years after diagnosis, diagnosed > 16 years) and 18 peers matched by age and gender. Participants underwent a standardized motor assessment, single-pulse transcranial magnetic stimulation to determine the type of corticospinal tract wiring, and resting-state functional magnetic resonance imaging to examine motor network connectivity. Corticospinal tract wiring was contralateral in all participants. Patients with hemiparesis had lower interhemispheric connectivity strength compared with patients with good clinical outcome and peers. Patients with good clinical outcome had higher intrahemispheric connectivity strength compared with peers. Further, higher intrahemispheric connectivity was related to better motor outcome in patients. Our findings suggest that better motor outcome after pediatric AIS is related to higher motor network connectivity strength. Thus, resting-state functional connectivity might be predictive for motor recovery after pediatric AIS.

Fronto-parietal involvement in chronic stroke motor performance when corticospinal tract integrity is compromised

BACKGROUND

Preserved integrity of the corticospinal tract (CST) is a marker of good upper-limb behavior and recovery following stroke. However, there is less understanding of neural mechanisms that might help facilitate upper-limb motor recovery in stroke survivors with extensive CST damage.

OBJECTIVE

The purpose of this study was to investigate resting state functional connectivity in chronic stroke survivors with different levels of CST damage and to explore neural correlates of greater upper-limb motor performance in stroke survivors with compromised ipsilesional CST integrity.

METHODS

Thirty chronic stroke survivors (24 males, aged 64.7 ± 10.8 years) participated in this study. Three experimental sessions were conducted to: 1) obtain anatomical (T1, T2) structural (diffusion) and functional (resting state) MRI sequences, 2) determine CST integrity with transcranial magnetic stimulation (TMS) and conduct assessments of upper-limb behavior, and 3) reconfirm CST integrity status. Participants were divided into groups according to the extent of CST damage. Those in the extensive CST damage group did not show TMS evoked responses and had significantly lower ipsilesional fractional anisotropy.

RESULTS

Of the 30 chronic stroke survivors, 12 were categorized as having extensive CST damage. Stroke survivors with extensive CST damage had weaker functional connectivity in the ipsilesional sensorimotor network and greater functional connectivity in the ipsilesional fronto-parietal network compared to those with preserved CST integrity. For participants with extensive CST damage, improved motor performance was associated with greater functional connectivity of the ipsilesional fronto-parietal network and higher fractional anisotropy of the ipsilesional rostral superior longitudinal fasciculus.

CONCLUSIONS

Stroke survivors with extensive CST damage have greater resting state functional connectivity of an ipsilesional fronto-parietal network that appears to be a behaviorally relevant neural mechanism that improves upper-limb motor performance.

Funktionserholung nach Schlaganfall und die therapeutische Rolle der nicht-invasiven Hirnstimulation

Im Bereich der non-invasiven Hirnstimulation stellen die transkranielle Magnetstimulation (engl. transcranial magnetic stimulation, TMS) sowie die transkranielle Gleichstromstimulation (engl. transcranial direct current stimulation, tDCS) bis heute die wichtigsten Techniken zur Modulation kortikaler Erregbarkeit dar. Beide Verfahren induzieren Nacheffekte, welche die Zeit der reinen Stimulation überdauern, und ebnen damit den Weg für ihren therapeutischen Einsatz beim Schlaganfall. In diesem Übersichtsartikel diskutieren wir die aktuelle Datenlage TMS- und tDCS-vermittelter Therapien für die häufigsten schlaganfallbedingten Defizite wie Hemiparese, Aphasie und Neglect. Darüber hinaus adressieren wir mögliche Einschränkungen der gegenwärtigen Ansätze und zeigen Ansatzpunkte auf, um Neuromodulation nach Schlaganfall effektiver zu gestalten und damit das Outcome der Patienten zu verbessern.

Connectivity-Related Roles of Contralesional Brain Regions for Motor Performance Early after Stroke

Hemiparesis after stroke is associated with increased neural activity not only in the lesioned but also in the contralesional hemisphere. While most studies have focused on the role of contralesional primary motor cortex (M1) activity for motor performance, data on other areas within the unaffected hemisphere are scarce, especially early after stroke. We here combined functional magnetic resonance imaging (fMRI) and transcranial magnetic stimulation (TMS) to elucidate the contribution of contralesional M1, dorsal premotor cortex (dPMC), and anterior intraparietal sulcus (aIPS) for the stroke-affected hand within the first 10 days after stroke. We used “online” TMS to interfere with neural activity at subject-specific fMRI coordinates while recording 3D movement kinematics. Interfering with aIPS activity improved tapping performance in patients, but not healthy controls, suggesting a maladaptive role of this region early poststroke. Analyzing effective connectivity parameters using a Lasso prediction model revealed that behavioral TMS effects were predicted by the coupling of the stimulated aIPS with dPMC and ipsilesional M1. In conclusion, we found a strong link between patterns of frontoparietal connectivity and TMS effects, indicating a detrimental influence of the contralesional aIPS on motor performance early after stroke.

Artificial intelligence in stroke imaging: Current and future perspectives

Artificial intelligence (AI) is a fast-growing research area in computer science that aims to mimic cognitive processes through a number of techniques. Supervised machine learning, a subfield of AI, includes methods that can identify patterns in high-dimensional data using labeled 'ground truth' data and apply these learnt patterns to analyze, interpret, or make predictions on new datasets. Supervised machine learning has become a significant area of interest within the medical community. Radiology and neuroradiology in particular are especially well suited for application of machine learning due to the vast amount of data that is generated. One devastating disease for which neuroimaging plays a significant role in the clinical management is stroke. Within this context, AI techniques can play pivotal roles for image-based diagnosis and management of stroke. This overview focuses on the recent advances of artificial intelligence methods - particularly supervised machine learning and deep learning - with respect to workflow, image acquisition and reconstruction, and image interpretation in patients with acute stroke, while also discussing potential pitfalls and future applications.

Toward a hemorrhagic trauma severity score: fusing five physiological biomarkers

BACKGROUND

To introduce the Hemorrhage Intensive Severity and Survivability (HISS) score, based on the fusion of multi-biomarker data; glucose, lactate, pH, potassium, and oxygen tension, to serve as a patient-specific attribute in hemorrhagic trauma.

MATERIALS AND METHODS

One hundred instances of Sensible Fictitious Rationalized Patient (SFRP) data were synthetically generated and the HISS score assigned by five clinically active physician experts (100 [5]). The HISS score stratifies the criticality of the trauma patient as; low(0), guarded(1), elevated(2), high(3) and severe(4). Standard classifier algorithms; linear support vector machine (SVM-L), multi-class ensemble bagged decision tree (EBDT), artificial neural network with bayesian regularization (ANN:BR) and possibility rule-based using function approximation (PRBF) were evaluated for their potential to similarly classify and predict a HISS score.

RESULTS

SVM-L, EBDT, ANN:BR and PRBF generated score predictions with testing accuracies (majority vote) corresponding to 0.91 ± 0.06, 0.93 ± 0.04, 0.92 ± 0.07, and 0.92 ± 0.03, respectively, with no statistically significant difference (p > 0.05). Targeted accuracies of 0.99 and 0.999 could be achieved with SFRP data size and clinical expert scores of 147[7](0.99) and 154[9](0.999), respectively.

CONCLUSIONS

The predictions of the data-driven model in conjunction with an adjunct multi-analyte biosensor intended for point-of-care continual monitoring of trauma patients, can aid in patient stratification and triage decision-making.

Detecting schizophrenia at the level of the individual: relative diagnostic value of whole-brain images, connectome-wide functional connectivity and graph-based metrics

BACKGROUND

Previous studies using resting-state functional neuroimaging have revealed alterations in whole-brain images, connectome-wide functional connectivity and graph-based metrics in groups of patients with schizophrenia relative to groups of healthy controls. However, it is unclear which of these measures best captures the neural correlates of this disorder at the level of the individual patient.

METHODS

Here we investigated the relative diagnostic value of these measures. A total of 295 patients with schizophrenia and 452 healthy controls were investigated using resting-state functional Magnetic Resonance Imaging at five research centres. Connectome-wide functional networks were constructed by thresholding correlation matrices of 90 brain regions, and their topological properties were analyzed using graph theory-based methods. Single-subject classification was performed using three machine learning (ML) approaches associated with varying degrees of complexity and abstraction, namely logistic regression, support vector machine and deep learning technology.

RESULTS

Connectome-wide functional connectivity allowed single-subject classification of patients and controls with higher accuracy (average: 81%) than both whole-brain images (average: 53%) and graph-based metrics (average: 69%). Classification based on connectome-wide functional connectivity was driven by a distributed bilateral network including the thalamus and temporal regions.

CONCLUSION

These results were replicated across the three employed ML approaches. Connectome-wide functional connectivity permits differentiation of patients with schizophrenia from healthy controls at single-subject level with greater accuracy; this pattern of results is consistent with the 'dysconnectivity hypothesis' of schizophrenia, which states that the neural basis of the disorder is best understood in terms of system-level functional connectivity alterations.

Recovery from stroke: current concepts and future perspectives

Stroke is a leading cause of acquired, permanent disability worldwide. Although the treatment of acute stroke has been improved considerably, the majority of patients to date are left disabled with a considerable impact on functional independence and quality of life. As the absolute number of stroke survivors is likely to further increase due to the demographic changes in our aging societies, new strategies are needed in order to improve neurorehabilitation. The most critical driver of functional recovery post-stroke is neural reorganization. For developing novel, neurobiologically informed strategies to promote recovery of function, an improved understanding of the mechanisms enabling plasticity and recovery is mandatory. This review provides a comprehensive survey of recent developments in the field of stroke recovery using neuroimaging and non-invasive brain stimulation. We discuss current concepts of how the brain reorganizes its functional architecture to overcome stroke-induced deficits, and also present evidence for maladaptive effects interfering with recovery. We demonstrate that the combination of neuroimaging and neurostimulation techniques allows a better understanding of how brain plasticity can be modulated to promote the reorganization of neural networks. Finally, neurotechnology-based treatment strategies allowing patient-tailored interventions to achieve enhanced treatment responses are discussed. The review also highlights important limitations of current models, and finally closes with possible solutions and future directions.

Acute ischaemic stroke alters the brain's preference for distinct dynamic connectivity states

Acute ischaemic stroke disturbs healthy brain organization, prompting subsequent plasticity and reorganization to compensate for the loss of specialized neural tissue and function. Static resting state functional MRI studies have already furthered our understanding of cerebral reorganization by estimating stroke-induced changes in network connectivity aggregated over the duration of several minutes. In this study, we used dynamic resting state functional MRI analyses to increase temporal resolution to seconds and explore transient configurations of motor network connectivity in acute stroke. To this end, we collected resting state functional MRI data of 31 patients with acute ischaemic stroke and 17 age-matched healthy control subjects. Stroke patients presented with moderate to severe hand motor deficits. By estimating dynamic functional connectivity within a sliding window framework, we identified three distinct connectivity configurations of motor-related networks. Motor networks were organized into three regional domains, i.e. a cortical, subcortical and cerebellar domain. The dynamic connectivity patterns of stroke patients diverged from those of healthy controls depending on the severity of the initial motor impairment. Moderately affected patients (n = 18) spent significantly more time in a weakly connected configuration that was characterized by low levels of connectivity, both locally as well as between distant regions. In contrast, severely affected patients (n = 13) showed a significant preference for transitions into a spatially segregated connectivity configuration. This configuration featured particularly high levels of local connectivity within the three regional domains as well as anti-correlated connectivity between distant networks across domains. A third connectivity configuration represented an intermediate connectivity pattern compared to the preceding two, and predominantly encompassed decreased interhemispheric connectivity between cortical motor networks independent of individual deficit severity. Alterations within this third configuration thus closely resembled previously reported ones originating from static resting state functional MRI studies post-stroke. In summary, acute ischaemic stroke not only prompted changes in connectivity between distinct networks, but it also caused characteristic changes in temporal properties of large-scale network interactions depending on the severity of the individual deficit. These findings offer new vistas on the dynamic neural mechanisms underlying acute neurological symptoms, cortical reorganization and treatment effects in stroke patients.

Advanced Neurotechnologies for the Restoration of Motor Function

Stroke is one of the leading causes of long-term disability. Advanced technological solutions ("neurotechnologies") exploiting robotic systems and electrodes that stimulate the nervous system can increase the efficacy of stroke rehabilitation. Recent studies on these approaches have shown promising results. However, a paradigm shift in the development of new approaches must be made to significantly improve the clinical outcomes of neurotechnologies compared with those of traditional therapies. An "evolutionary" change can occur only by understanding in great detail the basic mechanisms of natural stroke recovery and technology-assisted neurorehabilitation. In this review, we first describe the results achieved by existing neurotechnologies and highlight their current limitations. In parallel, we summarize the data available on the mechanisms of recovery from electrophysiological, behavioral, and anatomical studies in humans and rodent models. Finally, we propose new approaches for the effective use of neurotechnologies in stroke survivors, as well as in people with other neurological disorders.

Reporting quality of studies using machine learning models for medical diagnosis: a systematic review

AIMS

We conducted a systematic review assessing the reporting quality of studies validating models based on machine learning (ML) for clinical diagnosis, with a specific focus on the reporting of information concerning the participants on which the diagnostic task was evaluated on.

METHOD

Medline Core Clinical Journals were searched for studies published between July 2015 and July 2018. Two reviewers independently screened the retrieved articles, a third reviewer resolved any discrepancies. An extraction list was developed from the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guideline. Two reviewers independently extracted the data from the eligible articles. Third and fourth reviewers checked, verified the extracted data as well as resolved any discrepancies between the reviewers.

RESULTS

The search results yielded 161 papers, of which 28 conformed to the eligibility criteria. Detail of data source was reported in 24 of the 28 papers. For all of the papers, the set of patients on which the ML-based diagnostic system was evaluated was partitioned from a larger dataset, and the method for deriving such set was always reported. Information on the diagnostic/non-diagnostic classification was reported well (23/28). The least reported items were the use of reporting guideline (0/28), distribution of disease severity (8/28 patient flow diagram (10/28) and distribution of alternative diagnosis (10/28). A large proportion of studies (23/28) had a delay between the conduct of the reference standard and ML tests, while one study did not and four studies were unclear. For 15 studies, it was unclear whether the evaluation group corresponded to the setting in which the ML test will be applied to.

CONCLUSION

All studies in this review failed to use reporting guidelines, and a large proportion of them lacked adequate detail on participants, making it difficult to replicate, assess and interpret study findings.

PROSPERO REGISTRATION NUMBER

CRD42018099167.

Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke

Background. Accurate prediction of clinical impairment in upper-extremity motor function following therapy in chronic stroke patients is a difficult task for clinicians but is key in prescribing appropriate therapeutic strategies. Machine learning is a highly promising avenue with which to improve prediction accuracy in clinical practice. Objectives. The objective was to evaluate the performance of 5 machine learning methods in predicting postintervention upper-extremity motor impairment in chronic stroke patients using demographic, clinical, neurophysiological, and imaging input variables. Methods. A total of 102 patients (female: 31%, age 61 ± 11 years) were included. The upper-extremity Fugl-Meyer Assessment (UE-FMA) was used to assess motor impairment of the upper limb before and after intervention. Elastic net (EN), support vector machines, artificial neural networks, classification and regression trees, and random forest were used to predict postintervention UE-FMA. The performances of methods were compared using cross-validated R². Results. EN performed significantly better than other methods in predicting postintervention UE-FMA using demographic and baseline clinical data (median REN2=0.91,RRF2=0.88,RANN2=0.83,RSVM2=0.79,RCART2=0.70; P < .05). Preintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors. The difference in MT had greater importance than the absence or presence of a motor-evoked potential (MEP) in the affected hemisphere. Conclusion. Machine learning methods may enable clinicians to accurately predict a chronic stroke patient's postintervention UE-FMA. Interhemispheric difference in the MT is an important predictor of chronic stroke patients' response to therapy and, therefore, could be included in prospective studies.

The differential roles of contralesional frontoparietal areas in cortical reorganization after stroke

BACKGROUND

Studies examining the contribution of contralesional brain regions to motor recovery after stroke have revealed conflicting results comprising both supporting and disturbing influences. Especially the relevance of contralesional brain regions beyond primary motor cortex (M1) has rarely been studied, particularly concerning the temporal dynamics post-stroke.

METHODS

We, therefore, used online transcranial magnetic stimulation (TMS) interference to longitudinally assess the role of contralesional (right) frontoparietal areas for recovery of hand motor function after left hemispheric stroke: contralesional M1, contralesional dorsal premotor cortex (dPMC), and contralesional anterior intraparietal sulcus (IPS). Fourteen stroke patients and sixteen age-matched healthy subjects performed motor tasks of varying complexity with their (paretic) right hand. Motor performance was quantified using three-dimensional kinematic data. All patients were assessed twice, (i) in the first week, and (ii) after more than three months post-stroke.

RESULTS

While we did not observe a significant effect of TMS interference on movement kinematics following the stimulation of contralesional M1 and dPMC in the first week post-stroke, we found improvements of motor performance upon interference with contralesional IPS across motor tasks early after stroke, an effect that persisted into the later phase. By contrast, for dPMC, TMS-induced deterioration of motor performance was only evident three months post-stroke, suggesting that a supportive role of contralesional premotor cortex might evolve with reorganization.

CONCLUSION

We here highlight time-sensitive and region-specific effects of contralesional frontoparietal areas after left hemisphere stroke, which may influence on neuromodulation regimes aiming at supporting recovery of motor function post-stroke.

Fighting healthcare rocketing costs with value-based medicine: the case of stroke management

Value-Based Medicine (VBM) is imposing itself as 'a new paradigm in healthcare management and medical practice.In this perspective paper, we discuss the role of VBM in dealing with the large productivity issue of the healthcare industry and examine some of the worldwide industrial and technological trends linked with VBM introduction. To clarify the points, we discuss examples of VBM management of stroke patients.In our conclusions, we support the idea of VBM as a strategic aid to manage rising costs in healthcare, and we explore the idea that VBM, by establishing value-generating networks among different healthcare stakeholders, can serve as the long sought-after redistributive mechanism that compensate patients for the industrial exploitation of their personal medical records.

Intermittent theta burst stimulation applied during early rehabilitation after stroke: study protocol for a randomised controlled trial

INTRODUCTION

Intermittent theta burst stimulation (iTBS) applied to primary motor cortex (M1) has been shown to modulate both the excitability and connectivity of the motor system. A recent proof-of-principle study, based on a small group of hospitalised patients with acute ischemic stroke, suggested that iTBS applied to the ipsilesional M1 combined with physical therapy early after stroke can amplify motor recovery with lasting after effects. A randomised controlled clinical trial using a double-blind design is warranted to justify the implementation of iTBS-assisted motor rehabilitation in neurorehabilitation from an acute ischaemic stroke.

METHODS/DESIGN

We investigate the effects of daily iTBS on early motor rehabilitation after stroke in an investigator-initiated, longitudinal randomised controlled trial. Patients (n=150) with hemiparesis receive either iTBS (600 pulses) applied to the ipsilesional motor cortex (M1) or a control stimulation (ie, coil placement over the parieto-occipital vertex in parallel to the interhemispheric fissure and with a tilt of 45°). On 8 consecutive workdays, a 45 min arm-centred motor training follows the intervention . The relative grip strength, defined as the grip force ratios of the affected and unaffected hands, serves as the primary outcome parameter. Secondary outcome parameters are measures of arm function (Action Research Arm Test, Fugl-Meyer Motor Scale), stroke severity (National Institutes of Health Stroke Scale), stroke-induced disability (modified Rankin Scale, Barthel Index), duration of inpatient rehabilitation, quality of life (EuroQol 5D), motor evoked potentials and the resting motor threshold of the ipsilesional M1.

ETHICS AND DISSEMINATION

The study was approved by the Ethics Commission of the Medical Faculty, University of Cologne, Germany (reference number 15-343). Data will be disseminated through peer-reviewed publications and presentations at conferences. Study title: Theta-Burst Stimulation in Early Rehabilitation after Stroke (acronym: TheSiReS). Study registration at German Registry for Clinical Trials (DRKS00008963) and at ClinicalTrials.gov (NCT02910024).

Can clinical audits be enhanced by pathway simulation and machine learning? An example from the acute stroke pathway

OBJECTIVE

To evaluate the application of clinical pathway simulation in machine learning, using clinical audit data, in order to identify key drivers for improving use and speed of thrombolysis at individual hospitals.

DESIGN

Computer simulation modelling and machine learning.

SETTING

Seven acute stroke units.

PARTICIPANTS

Anonymised clinical audit data for 7864 patients.

RESULTS

Three factors were pivotal in governing thrombolysis use: (1) the proportion of patients with a known stroke onset time (range 44%-73%), (2) pathway speed (for patients arriving within 4 hours of onset: per-hospital median arrival-to-scan ranged from 11 to 56 min; median scan-to-thrombolysis ranged from 21 to 44 min) and (3) predisposition to use thrombolysis (thrombolysis use ranged from 31% to 52% for patients with stroke scanned with 30 min left to administer thrombolysis). A pathway simulation model could predict the potential benefit of improving individual stages of the clinical pathway speed, whereas a machine learning model could predict the benefit of 'exporting' clinical decision making from one hospital to another, while allowing for differences in patient population between hospitals. By applying pathway simulation and machine learning together, we found a realistic ceiling of 15%-25% use of thrombolysis across different hospitals and, in the seven hospitals studied, a realistic opportunity to double the number of patients with no significant disability that may be attributed to thrombolysis.

CONCLUSIONS

National clinical audit may be enhanced by a combination of pathway simulation and machine learning, which best allows for an understanding of key levers for improvement in hyperacute stroke pathways, allowing for differences between local patient populations. These models, based on standard clinical audit data, may be applied at scale while providing results at individual hospital level. The models facilitate understanding of variation and levers for improvement in stroke pathways, and help set realistic targets tailored to local populations.

Predictive analytics and machine learning in stroke and neurovascular medicine

Advances in predictive analytics and machine learning supported by an ever-increasing wealth of data and processing power are transforming almost every industry. Accuracy and precision of predictive analytics have significantly increased over the past few years and are evolving at an exponential pace. There have been significant breakthroughs in using Predictive Analytics in healthcare where it is held as the foundation of precision medicine. Yet, although the research in the field is expanding with the profuse volume of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Regardless of the status of its current contribution, the field of predictive analytics is expected to fundamentally change the way we diagnose and treat diseases, as well as the conduct of biomedical science research. In this review, we describe the main tools and techniques in predictive analytics and will analyze the trends in application of these techniques over the recent years. We will also provide examples of its application in medicine and more specifically in stroke and neurovascular research and outline current limitations.

Brain networks and their relevance for stroke rehabilitation

Stroke has long been regarded as focal disease with circumscribed damage leading to neurological deficits. However, advances in methods for assessing the human brain and in statistics have enabled new tools for the examination of the consequences of stroke on brain structure and function. Thereby, it has become evident that stroke has impact on the entire brain and its network properties and can therefore be considered as a network disease. The present review first gives an overview of current methodological opportunities and pitfalls for assessing stroke-induced changes and reorganization in the human brain. We then summarize principles of plasticity after stroke that have emerged from the assessment of networks. Thereby, it is shown that neurological deficits do not only arise from focal tissue damage but also from local and remote changes in white-matter tracts and in neural interactions among wide-spread networks. Similarly, plasticity and clinical improvements are associated with specific compensatory structural and functional patterns of neural network interactions. Innovative treatment approaches have started to target such network patterns to enhance recovery. Network assessments to predict treatment response and to individualize rehabilitation is a promising way to enhance specific treatment effects and overall outcome after stroke.

Multivariate prediction of functional outcome using lesion topography characterized by acute diffusion tensor imaging

The relationship between stroke topography and functional outcome has largely been studied with binary manual lesion segmentations. However, stroke topography may be better characterized by continuous variables capable of reflecting the severity of ischemia, which may be more pertinent for long-term outcome. Diffusion Tensor Imaging (DTI) constitutes a powerful means of quantifying the degree of acute ischemia and its potential relation to functional outcome. Our aim was to investigate whether using more clinically pertinent imaging parameters with powerful machine learning techniques could improve prediction models and thus provide valuable insight on critical brain areas important for long-term outcome. Eighty-seven thrombolyzed patients underwent a DTI sequence at 24 h post-stroke. Functional outcome was evaluated at 3 months post-stroke with the modified Rankin Score and was dichotomized into good (mRS ≤ 2) and poor (mRS > 2) outcome. We used support vector machines (SVM) to classify patients into good vs. poor outcome and evaluate the accuracy of different models built with fractional anisotropy, mean diffusivity, axial diffusivity, radial diffusivity asymmetry maps, and lesion segmentations in combination with lesion volume, age, recanalization status, and thrombectomy treatment. SVM classifiers built with axial diffusivity maps yielded the best accuracy of all imaging parameters (median [IQR] accuracy = 82.8 [79.3-86.2]%), compared to that of lesion segmentations (76.7 [73.3-82.8]%) when predicting 3-month functional outcome. The analysis revealed a strong contribution of clinical variables, notably - in descending order - lesion volume, thrombectomy treatment, and recanalization status, in addition to the deep white matter at the crossroads of major white matter tracts, represented by brain regions where model weights were highest. Axial diffusivity is a more appropriate imaging marker to characterize stroke topography for predicting long-term outcome than binary lesion segmentations.