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

Prediction of cerebral hemorrhagic transformation after thrombectomy using a deep learning of dual-energy CT

OBJECTIVES

To develop and validate a deep learning model for predicting hemorrhagic transformation after endovascular thrombectomy using dual-energy computed tomography (CT).

MATERIALS AND METHODS

This was a retrospective study from a prospective registry of acute ischemic stroke. Patients admitted between May 2019 and February 2023 who underwent endovascular thrombectomy for acute anterior circulation occlusions were enrolled. Hemorrhagic transformation was defined using follow-up magnetic resonance imaging or CT. The deep learning model was developed using post-thrombectomy dual-energy CT to predict hemorrhagic transformation within 72 h. Temporal validation was performed with patients who were admitted after July 2022. The deep learning model's performance was compared with a logistic regression model developed from clinical variables using the area under the receiver operating characteristic curve (AUC).

RESULTS

Total of 202 patients (mean age 71.4 years ± 14.5 [standard deviation], 92 men) were included, with 109 (54.0%) patients having hemorrhagic transformation. The deep learning model performed consistently well, showing an average AUC of 0.867 (95% confidence interval [CI], 0.815-0.902) upon five-fold cross validation and AUC of 0.911 (95% CI, 0.774-1.000) with the test dataset. The clinical variable model showed an AUC of 0.775 (95% CI, 0.709-0.842) on the training dataset (p < 0.01) and AUC of 0.634 (95% CI, 0.385-0.883) on the test dataset (p = 0.06).

CONCLUSION

A deep learning model was developed and validated for prediction of hemorrhagic transformation after endovascular thrombectomy in patients with acute stroke using dual-energy computed tomography.

CLINICAL RELEVANCE STATEMENT

This study demonstrates that a convolutional neural network (CNN) can be utilized on dual-energy computed tomography (DECT) for the accurate prediction of hemorrhagic transformation after thrombectomy. The CNN achieves high performance without the need for region of interest drawing.

KEY POINTS

• Iodine leakage on dual-energy CT after thrombectomy may be from blood-brain barrier disruption. • A convolutional neural network on post-thrombectomy dual-energy CT enables individualized prediction of hemorrhagic transformation. • Iodine leakage is an important predictor of hemorrhagic transformation following thrombectomy for ischemic stroke.

Severity-Dependent Interhemispheric White Matter Connectivity Predicts Poststroke Neglect Recovery

Left-sided spatial neglect is a very common and challenging issue after right-hemispheric stroke, which strongly and negatively affects daily living behavior and recovery of stroke survivors. The mechanisms underlying recovery of spatial neglect remain controversial, particularly regarding the involvement of the intact, contralesional hemisphere, with potential contributions ranging from maladaptive to compensatory. In the present prospective, observational study, we assessed neglect severity in 54 right-hemispheric stroke patients (32 male; 22 female) at admission to and discharge from inpatient neurorehabilitation. We demonstrate that the interaction of initial neglect severity and spared white matter (dis)connectivity resulting from individual lesions (as assessed by diffusion tensor imaging, DTI) explains a significant portion of the variability of poststroke neglect recovery. In mildly impaired patients, spared structural connectivity within the lesioned hemisphere is sufficient to attain good recovery. Conversely, in patients with severe impairment, successful recovery critically depends on structural connectivity within the intact hemisphere and between hemispheres. These distinct patterns, mediated by their respective white matter connections, may help to reconcile the dichotomous perspectives regarding the role of the contralesional hemisphere as exclusively compensatory or not. Instead, they suggest a unified viewpoint wherein the contralesional hemisphere can - but must not necessarily - assume a compensatory role. This would depend on initial impairment severity and on the available, spared structural connectivity. In the future, our findings could serve as a prognostic biomarker for neglect recovery and guide patient-tailored therapeutic approaches.

Predictive modelling and identification of key risk factors for stroke using machine learning

Strokes are a leading global cause of mortality, underscoring the need for early detection and prevention strategies. However, addressing hidden risk factors and achieving accurate prediction become particularly challenging in the presence of imbalanced and missing data. This study encompasses three imputation techniques to deal with missing data. To tackle data imbalance, it employs the synthetic minority oversampling technique (SMOTE). The study initiates with a baseline model and subsequently employs an extensive range of advanced models. This study thoroughly evaluates the performance of these models by employing k-fold cross-validation on various imbalanced and balanced datasets. The findings reveal that age, body mass index (BMI), average glucose level, heart disease, hypertension, and marital status are the most influential features in predicting strokes. Furthermore, a Dense Stacking Ensemble (DSE) model is built upon previous advanced models after fine-tuning, with the best-performing model as a meta-classifier. The DSE model demonstrated over 96% accuracy across diverse datasets, with an AUC score of 83.94% on imbalanced imputed dataset and 98.92% on balanced one. This research underscores the remarkable performance of the DSE model, compared to the previous research on the same dataset. It highlights the model's potential for early stroke detection to improve patient outcomes.

CBF Profile in Computed Tomography Perfusion-Based AutoMIStar Software Predicts Futile Recanalization After Basilar Artery Thrombectomy

Background

Futile recanalization (FR) remains a significant challenge in patients with acute basilar artery occlusion (BAO) following successful endovascular treatment (EVT). This study aimed to investigate the predictive value of computed tomography perfusion (CTP)-based software (AutoMIStar; Apollo) for FR among BAO patients undergoing EVT.

Methods

We analyzed a prospectively maintained database to identify consecutive BAO patients who achieved successful recanalization (modified Thrombolysis in Cerebral Infarction grade ≥ 2b) after EVT between January 2020 and September 2022. Clinical characteristics and imaging parameters from non-contrast CT, CT angiography, and CTP-AutoMIStar were collected for analysis. FR was defined as an unfavorable outcome (modified Rankin Scale score > 3) at 90 days despite successful recanalization. Multivariable stepwise logistic regression analysis was performed to identify independent predictors of FR.

Results

Of the 54 patients included in this study, 24 (44.4%) experienced FR. In the univariate analysis, admission National Institutes of Health Stroke Scale score, posterior circulation Acute Stroke Prognosis Early CT Score, Basilar Artery on Computed Tomography Angiography (BATMAN) score, hypoperfusion intensity ratio, and perfusion deficit volume in delay time (DT) > 4 s, DT > 6 s, DT > 8 s, and all cerebral blood flow (CBF) thresholds were associated with FR (all P < 0.05). In the multivariate analysis, perfusion deficit volume in CBF < 35% (adjusted odds ratio [aOR] = 1.105, 95% confidence interval [CI]: 1.004-1.215; P = 0.040) and BATMAN score (aOR = 0.662, 95% CI: 0.455-0.964; P = 0.031) remained independent predictors of FR.

Conclusion

Perfusion deficit volume in CBF < 35% on CTP-AutoMIStar imaging maps and BATMAN score are independent predictors of FR after EVT in BAO patients. There is a significant positive correlation between perfusion deficit volume in CBF < 35% and the occurrence of FR.

Developing machine learning models to predict multi-class functional outcomes and death three months after stroke in Sweden

Globally, stroke is the third-leading cause of mortality and disability combined, and one of the costliest diseases in society. More accurate predictions of stroke outcomes can guide healthcare organizations in allocating appropriate resources to improve care and reduce both the economic and social burden of the disease. We aim to develop and evaluate the performance and explainability of three supervised machine learning models and the traditional multinomial logistic regression (mLR) in predicting functional dependence and death three months after stroke, using routinely-collected data. This prognostic study included adult patients, registered in the Swedish Stroke Registry (Riksstroke) from 2015 to 2020. Riksstroke contains information on stroke care and outcomes among patients treated in hospitals in Sweden. Prognostic factors (features) included demographic characteristics, pre-stroke functional status, cardiovascular risk factors, medications, acute care, stroke type, and severity. The outcome was measured using the modified Rankin Scale at three months after stroke (a scale of 0-2 indicates independent, 3-5 dependent, and 6 dead). Outcome prediction models included support vector machines, artificial neural networks (ANN), eXtreme Gradient Boosting (XGBoost), and mLR. The models were trained and evaluated on 75% and 25% of the dataset, respectively. Model predictions were explained using SHAP values. The study included 102,135 patients (85.8% ischemic stroke, 53.3% male, mean age 75.8 years, and median NIHSS of 3). All models demonstrated similar overall accuracy (69%-70%). The ANN and XGBoost models performed significantly better than the mLR in classifying dependence with F1-scores of 0.603 (95% CI; 0.594-0.611) and 0.577 (95% CI; 0.568-0.586), versus 0.544 (95% CI; 0.545-0.563) for the mLR model. The factors that contributed most to the predictions were expectedly similar in the models, based on clinical knowledge. Our ANN and XGBoost models showed a modest improvement in prediction performance and explainability compared to mLR using routinely-collected data. Their improved ability to predict functional dependence may be of particular importance for the planning and organization of acute stroke care and rehabilitation.

Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network

Objectives

This study proposed an outcome prediction method to improve the accuracy and efficacy of ischemic stroke outcome prediction based on the diversity of whole brain features, without using basic information about patients and image features in lesions.

Design

In this study, we directly extracted dynamic radiomics features (DRFs) from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) and further extracted static radiomics features (SRFs) and static encoding features (SEFs) from the minimum intensity projection (MinIP) map, which was generated from the time dimension of DSC-PWI images. After selecting whole brain features Ffuse from the combinations of DRFs, SRFs, and SEFs by the Lasso algorithm, various machine and deep learning models were used to evaluate the role of Ffuse in predicting stroke outcomes.

Results

The experimental results show that the feature Ffuse generated from DRFs, SRFs, and SEFs (Resnet 18) outperformed other single and combination features and achieved the best mean score of 0.971 both on machine learning models and deep learning models and the 95% CI were (0.703, 0.877) and (0.92, 0.983), respectively. Besides, the deep learning models generally performed better than the machine learning models.

Conclusion

The method used in our study can achieve an accurate assessment of stroke outcomes without segmentation of ischemic lesions, which is of great significance for rapid, efficient, and accurate clinical stroke treatment.

Predicting Recovery of Independent Walking After Stroke: A Systematic Review

ABSTRACT

Patients recovering from a stroke experience reduced participation, especially when they are limited in daily activities involving walking. Understanding the recovery of independent walking, can be used by clinicians in the decision-making process during rehabilitation, resulting in more personalized stroke rehabilitation. Therefore, it is necessary to gain insight in predicting the recovery of independent walking in patients after stroke. This systematic review provided an overview of current evidence about prognostic models and its performance to predict recovery of independent walking after stroke. Therefore, MEDLINE, CINAHL, and Embase were searched for all relevant studies in English and Dutch. Descriptive statistics, study methods, and model performance were extracted and divided into two categories: subacute phase and chronic phase. This resulted in 16 articles that fulfilled all the search criteria, which included 30 prognostic models. Six prognostic models showed an excellent performance (area under the curve value and/or overall accuracy ≥0.90). The model of Smith et al. (2017) showed highest overall accuracy (100%) in predicting independent walking in the subacute phase after stroke ( Neurorehabil Neural Repair 2017;31(10-11):955-64.). Recovery of independent walking can be predicted in the subacute and chronic phase after stroke. However, proper external validation and the applicability in clinical practice of identified prognostic models are still lacking.

Unveiling the Influence of AI Predictive Analytics on Patient Outcomes: A Comprehensive Narrative Review

This comprehensive literature review explores the transformative impact of artificial intelligence (AI) predictive analytics on healthcare, particularly in improving patient outcomes regarding disease progression, treatment response, and recovery rates. AI, encompassing capabilities such as learning, problem-solving, and decision-making, is leveraged to predict disease progression, optimize treatment plans, and enhance recovery rates through the analysis of vast datasets, including electronic health records (EHRs), imaging, and genetic data. The utilization of machine learning (ML) and deep learning (DL) techniques in predictive analytics enables personalized medicine by facilitating the early detection of conditions, precision in drug discovery, and the tailoring of treatment to individual patient profiles. Ethical considerations, including data privacy, bias, and accountability, emerge as vital in the responsible implementation of AI in healthcare. The findings underscore the potential of AI predictive analytics in revolutionizing clinical decision-making and healthcare delivery, emphasizing the necessity of ethical guidelines and continuous model validation to ensure its safe and effective use in augmenting human judgment in medical practice.

Artificial intelligence in neurology: opportunities, challenges, and policy implications

Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.

Cognitive functioning in untreated glioma patients: The limited predictive value of clinical variables

BACKGROUND

Previous research identified many clinical variables that are significantly related to cognitive functioning before surgery. It is not clear whether such variables enable accurate prediction for individual patients' cognitive functioning because statistical significance does not guarantee predictive value. Previous studies did not test how well cognitive functioning can be predicted for (yet) untested patients. Furthermore, previous research is limited in that only linear or rank-based methods with small numbers of variables were used.

METHODS

We used various machine learning models to predict preoperative cognitive functioning for 340 patients with glioma across 18 outcome measures. Predictions were made using a comprehensive set of clinical variables as identified from the literature. Model performances and optimized hyperparameters were interpreted. Moreover, Shapley additive explanations were calculated to determine variable importance and explore interaction effects.

RESULTS

Best-performing models generally demonstrated above-random performance. Performance, however, was unreliable for 14 out of 18 outcome measures with predictions worse than baseline models for a substantial number of train-test splits. Best-performing models were relatively simple and used most variables for prediction while not relying strongly on any variable.

CONCLUSIONS

Preoperative cognitive functioning could not be reliably predicted across cognitive tests using the comprehensive set of clinical variables included in the current study. Our results show that a holistic view of an individual patient likely is necessary to explain differences in cognitive functioning. Moreover, they emphasize the need to collect larger cross-center and multimodal data sets.

Exploring the use of ChatGPT in predicting anterior circulation stroke functional outcomes after mechanical thrombectomy: a pilot study

BACKGROUND

Accurate prediction of functional outcomes is crucial in stroke management, but this remains challenging.

OBJECTIVE

To evaluate the performance of the generative language model ChatGPT in predicting the functional outcome of patients with acute ischemic stroke (AIS) 3 months after mechanical thrombectomy (MT) in order to assess whether ChatGPT can used to be accurately predict the modified Rankin Scale (mRS) score at 3 months post-thrombectomy.

METHODS

We conducted a retrospective analysis of clinical, neuroimaging, and procedure-related data from 163 patients with AIS undergoing MT. The agreement between ChatGPT's exact and dichotomized predictions and actual mRS scores was assessed using Cohen's κ. The added value of ChatGPT was measured by evaluating the agreement of predicted dichotomized outcomes using an existing validated score, the MT-DRAGON.

RESULTS

ChatGPT demonstrated fair (κ=0.354, 95% CI 0.260 to 0.448) and good (κ=0.727, 95% CI 0.620 to 0.833) agreement with the true exact and dichotomized mRS scores at 3 months, respectively, outperforming MT-DRAGON in overall and subgroup predictions. ChatGPT agreement was higher for patients with shorter last-time-seen-well-to-door delay, distal occlusions, and better modified Thrombolysis in Cerebral Infarction scores.

CONCLUSIONS

ChatGPT adequately predicted short-term functional outcomes in post-thrombectomy patients with AIS and was better than the existing risk score. Integrating AI models into clinical practice holds promise for patient care, yet refining these models is crucial for enhanced accuracy in stroke management.

Neurological Consequences of Cardiac Arrhythmias: Relationship Between Stroke, Cognitive Decline, and Heart Rhythm Disorders

Cardiac arrhythmias are one of the most common disorders with high morbidity and mortality. The effect of cardiac arrhythmias on the brain is very pronounced due to the high sensitivity of the brain to oxygen and blood supply. This mortality is preventable by early diagnosis and treatment which improves the patient's quality of life. Intervening at the right time, post arrhythmia is significant in preventing deaths and improving patient outcomes. Multiple pathophysiological mechanisms are studied for the brain-axis implications, that have the potential to be targeted by novel therapies. In this review, we describe the pathophysiological mechanisms and recent advances in detail to understand the functional aspects of the brain-heart axis and neurological implications post-stroke, caused by cardiac disorders.  This paper aims to discuss the current literature on the neurological consequences of cardiac arrhythmias and delve into a deeper understanding of the brain-heart axis, imbalances, and decline, with the aim of summarizing everything and all about the neurological consequences of cardiac arrhythmias.

Adaptation of the Concept of Brain Reserve for the Prediction of Stroke Outcome: Proxies, Neural Mechanisms, and Significance for Research

The prediction of stroke outcome is challenging due to the high inter-individual variability in stroke patients. We recently suggested the adaptation of the concept of brain reserve (BR) to improve the prediction of stroke outcome. This concept was initially developed alongside the one for the cognitive reserve for neurodegeneration and forms a valuable theoretical framework to capture high inter-individual variability in stroke patients. In the present work, we suggest and discuss (i) BR-proxies-quantitative brain characteristics at the time stroke occurs (e.g., brain volume, hippocampus volume), and (ii) proxies of brain pathology reducing BR (e.g., brain atrophy, severity of white matter hyperintensities), parameters easily available from a routine MRI examination that might improve the prediction of stroke outcome. Though the influence of these parameters on stroke outcome has been partly reported individually, their independent and combined impact is yet to be determined. Conceptually, BR is a continuous measure determining the amount of brain structure available to mitigate and compensate for stroke damage, thus reflecting individual differences in neural resources and a capacity to maintain performance and recover after stroke. We suggest that stroke outcome might be defined as an interaction between BR at the time stroke occurs and lesion load. BR in stroke can potentially be influenced, e.g., by modifying cardiovascular risk factors. In addition to the potential power of the BR concept in a mechanistic understanding of inter-individual variability in stroke outcome and establishing individualized therapeutic approaches, it might help to strengthen the synergy of preventive measures in stroke, neurodegeneration, and healthy aging.

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.

Non-contrast ultrasound image analysis for spatial and temporal distribution of blood flow after spinal cord injury

Ultrasound technology can provide high-resolution imaging of blood flow following spinal cord injury (SCI). Blood flow imaging may improve critical care management of SCI, yet its duration is limited clinically by the amount of contrast agent injection required for high-resolution, continuous monitoring. In this study, we aim to establish non-contrast ultrasound as a clinically translatable imaging technique for spinal cord blood flow via comparison to contrast-based methods and by measuring the spatial distribution of blood flow after SCI. A rodent model of contusion SCI at the T12 spinal level was carried out using three different impact forces. We compared images of spinal cord blood flow taken using both non-contrast and contrast-enhanced ultrasound. Subsequently, we processed the images as a function of distance from injury, yielding the distribution of blood flow through space after SCI, and found the following. (1) Both non-contrast and contrast-enhanced imaging methods resulted in similar blood flow distributions (Spearman's ρ = 0.55, p < 0.0001). (2) We found an area of decreased flow at the injury epicenter, or umbra (p < 0.0001). Unexpectedly, we found increased flow at the periphery, or penumbra (rostral, p < 0.05; caudal, p < 0.01), following SCI. However, distal flow remained unchanged, in what is presumably unaffected tissue. (3) Finally, tracking blood flow in the injury zones over time revealed interesting dynamic changes. After an initial decrease, blood flow in the penumbra increased during the first 10 min after injury, while blood flow in the umbra and distal tissue remained constant over time. These results demonstrate the viability of non-contrast ultrasound as a clinical monitoring tool. Furthermore, our surprising observations of increased flow in the injury periphery pose interesting new questions about how the spinal cord vasculature reacts to SCI, with potentially increased significance of the penumbra.

Stratified predictions of upper limb motor outcomes after stroke

Introduction

Longitudinal observations of upper limb motor recovery after stroke have suggested that certain subgroups may exhibit distinct recovery patterns. Here we sought to examine whether the predictive ability for post-stroke upper limb motor outcomes could be enhanced by applying conventional stratification strategies.

Method

For 60 individuals who suffered the first stroke, upper limb motor impairment was assessed with the upper extremity Fugl-Meyer assessment (UE-FMA) at 2 weeks as a baseline and then 3 months post-stroke. Brain structural damage at baseline was assessed by MRI data-derived markers ranging from traditional lesion size to the lesion load and to the disconnectome. Linear regression models for predicting upper limb motor outcomes (UE-FMA score at 3 months post-stroke) based on baseline upper limb motor impairment (UE-FMA score at 2 weeks post-stroke), brain structural damage, and their combinations were generated, and those with the best predictive performance were determined for individual subgroups stratified according to initial impairment (severe and non-severe), lesion location (cortical and non-cortical), and neurophysiological status (motor evoked potential-positive and motor evoked potential-negative).

Results

The best predictions were made by baseline upper limb motor impairment alone for subgroups with less functional impairment (non-severe) or less structural involvement (non-cortical), but by the combination of baseline upper limb motor impairment and brain structural damage for the other subgroups. The predictive models tailored for subgroups determined according to initial impairment and neurophysiological status yielded a smaller overall error than that for the whole group in upper limb motor outcome predictions.

Discussion

The predictive ability for upper limb motor outcomes could be enhanced beyond the one-size-fits-all model for all individuals with stroke by applying specific stratification strategies, with stratification according to initial impairment being the most promising. We expect that predictive models tailored for individual subgroups could lead closer to the personalized prognosis of upper limb motor outcomes after stroke.

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

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

Rat Model of Middle Cerebral Artery Occlusion

Stroke is the third-leading cause of death and the leading cause of acquired adult disability worldwide. Several ischemic stroke models are currently available. However, mimicking focal cerebral ischemia (FCI) is the most common. The formation of an embolic or thrombotic occlusion at or near the middle cerebral artery causes most events in FCI. The current protocol closely mimics the etiology of human stroke and ensures that the results obtained are highly relevant. The method described in this protocol yields reproducible results. The success of this model in ischemic research can be examined through the utilization of Doppler blood flow imaging equipment.

Artificial intelligence applied in acute ischemic stroke: from child to elderly

This review will summarize artificial intelligence developments in acute ischemic stroke in recent years and forecasts for the future. Stroke is a major healthcare concern due to its effects on the patient's quality of life and its dependence on the timing of the identification as well as the treatment. In recent years, attention increased on the use of artificial intelligence (AI) systems to help categorize, prognosis, and to channel these patients toward the right therapeutic procedure. Machine learning (ML) and in particular deep learning (DL) systems using convoluted neural networks (CNN) are becoming increasingly popular. Various studies over the years evaluated the use of these methods of analysis and prediction in the assessment of stroke patients, and at the same time, several applications and software have been developed to support the neuroradiologists and the stroke team to improve patient outcomes.

Genomic insights and advanced machine learning: characterizing autism spectrum disorder biomarkers and genetic interactions

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by altered brain connectivity and function. In this study, we employed advanced bioinformatics and explainable AI to analyze gene expression associated with ASD, using data from five GEO datasets. Among 351 neurotypical controls and 358 individuals with autism, we identified 3,339 Differentially Expressed Genes (DEGs) with an adjusted p-value (≤ 0.05). A subsequent meta-analysis pinpointed 342 DEGs (adjusted p-value ≤ 0.001), including 19 upregulated and 10 down-regulated genes across all datasets. Shared genes, pathogenic single nucleotide polymorphisms (SNPs), chromosomal positions, and their impact on biological pathways were examined. We identified potential biomarkers (HOXB3, NR2F2, MAPK8IP3, PIGT, SEMA4D, and SSH1) through text mining, meriting further investigation. Additionally, ‎we shed light on the roles of RPS4Y1 and KDM5D genes in neurogenesis and neurodevelopment. Our analysis detected 1,286 SNPs linked to ASD-related conditions, of which 14 high-risk SNPs were located on chromosomes 10 and X. We highlighted potential missense SNPs associated with FGFR inhibitors, suggesting that it may serve as a promising biomarker for responsiveness to targeted therapies. Our explainable AI model identified the MID2 gene as a potential ASD biomarker. This research unveils vital genes and potential biomarkers, providing a foundation for novel gene discovery in complex diseases.

Unlocking the Medicinal Mysteries: Preventing Lacunar Stroke with Drug Repurposing

Currently, only the general control of the risk factors is known to prevent lacunar cerebral infarction, but it is unknown which type of medication for controlling the risk factors has a causal relationship with reducing the risk of lacunar infarction. To unlock this medical mystery, drug-target Mendelian randomization analysis was applied to estimate the effect of common antihypertensive agents, hypolipidemic agents, and hypoglycemic agents on lacunar stroke. Lacunar stroke data for the transethnic analysis were derived from meta-analyses comprising 7338 cases and 254,798 controls. We have confirmed that genetic variants mimicking calcium channel blockers were found to most stably prevent lacunar stroke. The genetic variants at or near HMGCR, NPC1L1, and APOC3 were predicted to decrease lacunar stroke incidence in drug-target MR analysis. These variants mimic the effects of statins, ezetimibe, and antisense anti-apoC3 agents, respectively. Genetically proxied GLP1R agonism had a marginal effect on lacunar stroke, while a genetically proxied improvement in overall glycemic control was associated with reduced lacunar stroke risk. Here, we show that certain categories of drugs currently used in clinical practice can more effectively reduce the risk of stroke. Repurposing several drugs with well-established safety and low costs for lacunar stroke prevention should be given high priority when doctors are making decisions in clinical practice. This may contribute to healthier brain aging.

Post-Stroke Brain Health Monitoring and Optimization: A Narrative Review

Significant advancements have been made in recent years in the acute treatment and secondary prevention of stroke. However, a large proportion of stroke survivors will go on to have enduring physical, cognitive, and psychological disabilities from suboptimal post-stroke brain health. Impaired brain health following stroke thus warrants increased attention from clinicians and researchers alike. In this narrative review based on an open timeframe search of the PubMed, Scopus, and Web of Science databases, we define post-stroke brain health and appraise the body of research focused on modifiable vascular, lifestyle, and psychosocial factors for optimizing post-stroke brain health. In addition, we make clinical recommendations for the monitoring and management of post-stroke brain health at major post-stroke transition points centered on four key intertwined domains: cognition, psychosocial health, physical functioning, and global vascular health. Finally, we discuss potential future work in the field of post-stroke brain health, including the use of remote monitoring and interventions, neuromodulation, multi-morbidity interventions, enriched environments, and the need to address inequities in post-stroke brain health. As post-stroke brain health is a relatively new, rapidly evolving, and broad clinical and research field, this narrative review aims to identify and summarize the evidence base to help clinicians and researchers tailor their own approach to integrating post-stroke brain health into their practices.

Utilizing deep learning via the 3D U-net neural network for the delineation of brain stroke lesions in MRI image

The segmentation of acute stroke lesions plays a vital role in healthcare by assisting doctors in making prompt and well-informed treatment choices. Although Magnetic Resonance Imaging (MRI) is a time-intensive procedure, it produces high-fidelity images widely regarded as the most reliable diagnostic tool available. Employing deep learning techniques for automated stroke lesion segmentation can offer valuable insights into the precise location and extent of affected tissue, enabling medical professionals to effectively evaluate treatment risks and make informed assessments. In this research, a deep learning approach is introduced for segmenting acute and sub-acute stroke lesions from MRI images. To enhance feature learning through brain hemisphere symmetry, pre-processing techniques are applied to the data. To tackle the class imbalance challenge, we employed a strategy of using small patches with balanced sampling during training, along with a dynamically weighted loss function that incorporates f1-score and IOU-score (Intersection over Union). Furthermore, the 3D U-Net architecture is used to generate predictions for complete patches, employing a high degree of overlap between patches to minimize the requirement for subsequent post-processing steps. The 3D U-Net model, utilizing ResnetV2 as the pre-trained encoder for IOU-score and Seresnext101 for f1-score, stands as the leading state-of-the-art (SOTA) model for segmentation tasks. However, recent research has introduced a novel model that surpasses these metrics and demonstrates superior performance compared to other backbone architectures. The f1-score and IOU-score were computed for various backbones, with Seresnext101 achieving the highest f1-score and ResnetV2 performing the highest IOU-score. These calculations were conducted using a threshold value of 0.5. This research proposes a valuable model based on transfer learning for the classification of brain diseases in MRI scans. The achieved f1-score using the recommended classifiers demonstrates the effectiveness of the approach employed in this study. The findings indicate that Seresnext101 attains the highest f1-score of 0.94226, while ResnetV2 achieves the best IOU-score of 0.88342, making it the preferred architecture for segmentation methods. Furthermore, the study presents experimental results of the 3D U-Net model applied to brain stroke lesion segmentation, suggesting prospects for researchers interested in segmenting brain strokes and enhancing 3D U-Net models.

Understanding stroke survivors' preferences regarding wearable sensor feedback on functional movement: a mixed-methods study

BACKGROUND

In stroke rehabilitation, wearable technology can be used as an intervention modality by providing timely, meaningful feedback on motor performance. Stroke survivors' preferences may offer a unique perspective on what metrics are intuitive, actionable, and meaningful to change behavior. However, few studies have identified feedback preferences from stroke survivors. This project aims to determine the ease of understanding and movement encouragement of feedback based on wearable sensor data (both arm/hand use and mobility) for stroke survivors and to identify preferences for feedback metrics (mode, content, frequency, and timing).

METHODS

A sample of 30 chronic stroke survivors wore a multi-sensor system in the natural environment over a 1-week monitoring period. The sensor system captured time in active movement of each arm, arm use ratio, step counts and stance time symmetry. Using the data from the monitoring period, participants were presented with a movement report with visual displays of feedback about arm/hand use, step counts and gait symmetry. A survey and qualitative interview were used to assess ease of understanding, actionability and components of feedback that users found most meaningful to drive lasting behavior change.

RESULTS

Arm/hand use and mobility sensor-derived feedback metrics were easy to understand and actionable. The preferred metric to encourage arm/hand use was the hourly arm use bar plot, and similarly the preferred metric to encourage mobility was the hourly steps bar plot, which were each ranked as top choice by 40% of participants. Participants perceived that quantitative (i.e., step counts) and qualitative (i.e., stance time symmetry) mobility metrics provided complementary information. Three main themes emerged from the qualitative analysis: (1) Motivation for behavior change, (2) Real-time feedback based on individual goals, and (3) Value of experienced clinicians for prescription and accountability. Participants stressed the importance of having feedback tailored to their own personalized goals and receiving guidance from clinicians on strategies to progress and increase functional movement behavior in the unsupervised home and community setting.

CONCLUSION

The resulting technology has the potential to integrate engineering and personalized rehabilitation to maximize participation in meaningful life activities outside clinical settings in a less structured environment.

Factors associated with the effectiveness of immersive virtual therapy in alleviating depressive symptoms during sub-acute post-stroke rehabilitation: a gender comparison

BACKGROUND

The large-scale digitalization of healthcare has induced shifts in patient preferences, prompting the introduction of therapies utilizing novel technologies. In this context, the targeted application of these interventions is deemed as crucial as assessing their overall effectiveness. The aim of this study was to characterize the patient profile who benefited most from immersive virtual reality (VR) therapy.

METHODS

Based on the results from the previous randomized controlled trial study, we employed an exploratory study design to determine the factors associated with the most significant mental health improvement. A secondary analysis was conducted on a sample of 83 participants, with further analysis of participants with elevated depression symptoms, as indicated by a score of > 10 on the 30-item Geriatric Depression Scale (GDS-30). Both groups participated in a similar post-stroke rehabilitation program; however, the experimental group also received additional VR therapy through an immersive VR garden intervention. The GDS-30 was used to assess mood and depressive symptoms, and sociodemographic, cognitive status as well as stroke-related variables were considered as potential factors.

RESULTS

In both the experimental (mean change 5.3) and control groups (mean change 2.8), interventions significantly reduced depressive symptoms, with a more pronounced difference in the experimental group (p < 0.05). When examining gender differences, women exhibited greater improvement in the GDS, with mean between-group differences of 5.0 for the total sample and 6.0 for those with elevated depressive symptoms. Sociodemographic factors, cognitive status, and time from stroke were not found to be factors that alter the effectiveness of VR therapy.

CONCLUSIONS

While VR therapy as an adjunctive treatment for post-stroke rehabilitation seems especially effective for women with elevated depressive symptoms, the results should be interpreted with caution due to the study's small experimental group size. Traditional methods showed reduced effectiveness in women compared to men; thus, developing technologically advanced and gender-specific approaches can lead to more tailored therapy.

TRIAL REGISTRATION

NCT03830372 (February 5, 2019).

Interhemispheric Structural Connectivity Underlies Motor Recovery after Stroke

OBJECTIVE

Although ample evidence highlights that the ipsilesional corticospinal tract (CST) plays a crucial role in motor recovery after stroke, studies on cortico-cortical motor connections remain scarce and provide inconclusive results. Given their unique potential to serve as structural reserve enabling motor network reorganization, the question arises whether cortico-cortical connections may facilitate motor control depending on CST damage.

METHODS

Diffusion spectrum imaging (DSI) and a novel compartment-wise analysis approach were used to quantify structural connectivity between bilateral cortical core motor regions in chronic stroke patients. Basal and complex motor control were differentially assessed.

RESULTS

Both basal and complex motor performance were correlated with structural connectivity between bilateral premotor areas and ipsilesional primary motor cortex (M1) as well as interhemispheric M1 to M1 connectivity. Whereas complex motor skills depended on CST integrity, a strong association between M1 to M1 connectivity and basal motor control was observed independent of CST integrity especially in patients who underwent substantial motor recovery. Harnessing the informational wealth of cortico-cortical connectivity facilitated the explanation of both basal and complex motor control.

INTERPRETATION

We demonstrate for the first time that distinct aspects of cortical structural reserve enable basal and complex motor control after stroke. In particular, recovery of basal motor control may be supported via an alternative route through contralesional M1 and non-crossing fibers of the contralesional CST. Our findings help to explain previous conflicting interpretations regarding the functional role of the contralesional M1 and highlight the potential of cortico-cortical structural connectivity as a future biomarker for motor recovery post-stroke. ANN NEUROL 2023;94:785-797.

The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis

Objectives

This study aimed to assess the accuracy of artificial intelligence (AI) models in predicting the prognosis of stroke.

Methods

We searched PubMed, Embase, and Web of Science databases to identify studies using AI for acute stroke prognosis prediction from the database inception to February 2023. Selected studies were designed cohorts and had complete data. We used the Quality Assessment of Diagnostic Accuracy Studies tool to assess the qualities and bias of included studies and used a random-effects model to summarize and analyze the data. We used the area under curve (AUC) as an indicator of the predictive accuracy of AI models.

Results

We retrieved a total of 1,241 publications and finally included seven studies. There was a low risk of bias and no significant heterogeneity in the final seven studies. The total pooled AUC under the fixed-effects model was 0.872 with a 95% CI of (0.862-0.881). The DL subgroup showed its AUC of 0.888 (95%CI 0.872-0.904). The LR subgroup showed its AUC 0.852 (95%CI 0.835-0.869). The RF subgroup showed its AUC 0.863 (95%CI 0.845-0.882). The SVM subgroup showed its AUC 0.905 (95%CI 0.857-0.952). The Xgboost subgroup showed its AUC 0.905 (95%CI 0.805-1.000).

Conclusion

The accuracy of AI models in predicting the outcomes of ischemic stroke is good from our study. It could be an assisting tool for physicians in judging the outcomes of stroke patients. With the update of AI algorithms and the use of big data, further AI predictive models will perform better.

Cerebrovascular disease case identification in inpatient electronic medical record data using natural language processing

BACKGROUND

Abstracting cerebrovascular disease (CeVD) from inpatient electronic medical records (EMRs) through natural language processing (NLP) is pivotal for automated disease surveillance and improving patient outcomes. Existing methods rely on coders' abstraction, which has time delays and under-coding issues. This study sought to develop an NLP-based method to detect CeVD using EMR clinical notes.

METHODS

CeVD status was confirmed through a chart review on randomly selected hospitalized patients who were 18 years or older and discharged from 3 hospitals in Calgary, Alberta, Canada, between January 1 and June 30, 2015. These patients' chart data were linked to administrative discharge abstract database (DAD) and Sunrise™ Clinical Manager (SCM) EMR database records by Personal Health Number (a unique lifetime identifier) and admission date. We trained multiple natural language processing (NLP) predictive models by combining two clinical concept extraction methods and two supervised machine learning (ML) methods: random forest and XGBoost. Using chart review as the reference standard, we compared the model performances with those of the commonly applied International Classification of Diseases (ICD-10-CA) codes, on the metrics of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULT

Of the study sample (n = 3036), the prevalence of CeVD was 11.8% (n = 360); the median patient age was 63; and females accounted for 50.3% (n = 1528) based on chart data. Among 49 extracted clinical documents from the EMR, four document types were identified as the most influential text sources for identifying CeVD disease ("nursing transfer report," "discharge summary," "nursing notes," and "inpatient consultation."). The best performing NLP model was XGBoost, combining the Unified Medical Language System concepts extracted by cTAKES (e.g., top-ranked concepts, "Cerebrovascular accident" and "Transient ischemic attack"), and the term frequency-inverse document frequency vectorizer. Compared with ICD codes, the model achieved higher validity overall, such as sensitivity (25.0% vs 70.0%), specificity (99.3% vs 99.1%), PPV (82.6 vs. 87.8%), and NPV (90.8% vs 97.1%).

CONCLUSION

The NLP algorithm developed in this study performed better than the ICD code algorithm in detecting CeVD. The NLP models could result in an automated EMR tool for identifying CeVD cases and be applied for future studies such as surveillance, and longitudinal studies.

Data-driven biomarkers outperform theory-based biomarkers in predicting stroke motor outcomes

Chronic motor impairments are a leading cause of disability after stroke. Previous studies have predicted motor outcomes based on the degree of damage to predefined structures in the motor system, such as the corticospinal tract. However, such theory-based approaches may not take full advantage of the information contained in clinical imaging data. The present study uses data-driven approaches to predict chronic motor outcomes after stroke and compares the accuracy of these predictions to previously-identified theory-based biomarkers. Using a cross-validation framework, regression models were trained using lesion masks and motor outcomes data from 789 stroke patients (293 female/496 male) from the ENIGMA Stroke Recovery Working Group (age 64.9±18.0 years; time since stroke 12.2±0.2 months; normalised motor score 0.7±0.5 (range [0,1]). The out-of-sample prediction accuracy of two theory-based biomarkers was assessed: lesion load of the corticospinal tract, and lesion load of multiple descending motor tracts. These theory-based prediction accuracies were compared to the prediction accuracy from three data-driven biomarkers: lesion load of lesion-behaviour maps, lesion load of structural networks associated with lesion-behaviour maps, and measures of regional structural disconnection. In general, data-driven biomarkers had better prediction accuracy - as measured by higher explained variance in chronic motor outcomes - than theory-based biomarkers. Data-driven models of regional structural disconnection performed the best of all models tested (R2 = 0.210, p < 0.001), performing significantly better than predictions using the theory-based biomarkers of lesion load of the corticospinal tract (R2 = 0.132, p< 0.001) and of multiple descending motor tracts (R2 = 0.180, p < 0.001). They also performed slightly, but significantly, better than other data-driven biomarkers including lesion load of lesion-behaviour maps (R2 =0.200, p < 0.001) and lesion load of structural networks associated with lesion-behaviour maps (R2 =0.167, p < 0.001). Ensemble models - combining basic demographic variables like age, sex, and time since stroke - improved prediction accuracy for theory-based and data-driven biomarkers. Finally, combining both theory-based and data-driven biomarkers with demographic variables improved predictions, and the best ensemble model achieved R2 = 0.241, p < 0.001. Overall, these results demonstrate that models that predict chronic motor outcomes using data-driven features, particularly when lesion data is represented in terms of structural disconnection, perform better than models that predict chronic motor outcomes using theory-based features from the motor system. However, combining both theory-based and data-driven models provides the best predictions.

Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine

Depression is a common mental disorder that seriously affects patients' social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole brain EEG signals and forehead hemodynamic signals from 25 depression patients and 30 healthy subjects during the resting state. On one hand, we explored the EEG brain functional network properties, and found that the clustering coefficient and local efficiency of the delta and theta bands in patients were significantly higher than those in normal subjects. On the other hand, we extracted brain network properties, asymmetry, and brain oxygen entropy as alternative features, used a data-driven automated method to select features, and established a support vector machine model for automatic depression classification. The results showed the classification accuracy was 81.8% when using EEG features alone and increased to 92.7% when using hybrid EEG and fNIRS features. The brain network local efficiency in the delta band, hemispheric asymmetry in the theta band and brain oxygen sample entropy features differed significantly between the two groups (p < 0.05) and showed high depression distinguishing ability indicating that they may be effective biological markers for identifying depression. EEG, fNIRS and machine learning constitute an effective method for classifying depression at the individual level.

Precision Medicine 2.0: How Digital Health and AI Are Changing the Game

In the era of rapid IT developments, the health domain is undergoing a considerable transformation [...].

Machine learning in predicting outcomes for stroke patients following rehabilitation treatment: A systematic review

OBJECTIVE

This review aimed to summarize the use of machine learning for predicting the potential benefits of stroke rehabilitation treatments, to evaluate the risk of bias of predictive models, and to provide recommendations for future models.

MATERIALS AND METHODS

This systematic review was conducted in accordance with the PRISMA statement and the CHARMS checklist. The PubMed, Embase, Cochrane Library, Scopus, and CNKI databases were searched up to April 08, 2023. The PROBAST tool was used to assess the risk of bias of the included models.

RESULTS

Ten studies within 32 models met our inclusion criteria. The optimal AUC value of the included models ranged from 0.63 to 0.91, and the optimal R2 value ranged from 0.64 to 0.91. All of the included models were rated as having a high or unclear risk of bias, and most of them were downgraded due to inappropriate data sources or analysis processes.

DISCUSSION AND CONCLUSION

There remains much room for improvement in future modeling studies, such as high-quality data sources and model analysis. Reliable predictive models should be developed to improve the efficacy of rehabilitation treatment by clinicians.

Clinical, Neuroimaging and Robotic Measures Predict Long-Term Proprioceptive Impairments following Stroke

Proprioceptive impairments occur in ~50% of stroke survivors, with 20-40% still impaired six months post-stroke. Early identification of those likely to have persistent impairments is key to personalizing rehabilitation strategies and reducing long-term proprioceptive impairments. In this study, clinical, neuroimaging and robotic measures were used to predict proprioceptive impairments at six months post-stroke on a robotic assessment of proprioception. Clinical assessments, neuroimaging, and a robotic arm position matching (APM) task were performed for 133 stroke participants two weeks post-stroke (12.4 ± 8.4 days). The APM task was also performed six months post-stroke (191.2 ± 18.0 days). Robotics allow more precise measurements of proprioception than clinical assessments. Consequently, an overall APM Task Score was used as ground truth to classify proprioceptive impairments at six months post-stroke. Other APM performance parameters from the two-week assessment were used as predictive features. Clinical assessments included the Thumb Localisation Test (TLT), Behavioural Inattention Test (BIT), Functional Independence Measure (FIM) and demographic information (age, sex and affected arm). Logistic regression classifiers were trained to predict proprioceptive impairments at six months post-stroke using data collected two weeks post-stroke. Models containing robotic features, either alone or in conjunction with clinical and neuroimaging features, had a greater area under the curve (AUC) and lower Akaike Information Criterion (AIC) than models which only contained clinical or neuroimaging features. All models performed similarly with regard to accuracy and F1-score (>70% accuracy). Robotic features were also among the most important when all features were combined into a single model. Predicting long-term proprioceptive impairments, using data collected as early as two weeks post-stroke, is feasible. Identifying those at risk of long-term impairments is an important step towards improving proprioceptive rehabilitation after a stroke.

Physics-informed neural networks for modeling physiological time series for cuffless blood pressure estimation

The bold vision of AI-driven pervasive physiological monitoring, through the proliferation of off-the-shelf wearables that began a decade ago, has created immense opportunities to extract actionable information for precision medicine. These AI algorithms model input-output relationships of a system that, in many cases, exhibits complex nature and personalization requirements. A particular example is cuffless blood pressure estimation using wearable bioimpedance. However, these algorithms need training over significant amount of ground truth data. In the context of biomedical applications, collecting ground truth data, particularly at the personalized level is challenging, burdensome, and in some cases infeasible. Our objective is to establish physics-informed neural network (PINN) models for physiological time series data that would use minimal ground truth information to extract complex cardiovascular information. We achieve this by building Taylor's approximation for gradually changing known cardiovascular relationships between input and output (e.g., sensor measurements to blood pressure) and incorporating this approximation into our proposed neural network training. The effectiveness of the framework is demonstrated through a case study: continuous cuffless BP estimation from time series bioimpedance data. We show that by using PINNs over the state-of-the-art time series models tested on the same datasets, we retain high correlations (systolic: 0.90, diastolic: 0.89) and low error (systolic: 1.3 ± 7.6 mmHg, diastolic: 0.6 ± 6.4 mmHg) while reducing the amount of ground truth training data on average by a factor of 15. This could be helpful in developing future AI algorithms to help interpret pervasive physiologic data using minimal amount of training data.

Precision Medicine for Brain Disorders: New and Emerging Approaches

The brain is the most complex organ in the human body, making it susceptible to many abnormalities [...].

Understanding preferences of stroke survivors for feedback provision about functional movement behavior from wearable sensors: a mixed-methods study

Background

In stroke rehabilitation, wearable technology can be used as an intervention modality by providing timely, meaningful feedback on motor performance. Stroke survivors' preferences may offer a unique perspective on what metrics are intuitive, actionable, and meaningful to change behavior. However, few studies have identified feedback preferences from stroke survivors. This project aims to determine stroke survivors' satisfaction with feedback from wearable sensors (both mobility and arm/hand use) and to identify preferences for feedback type and delivery schedule.

Methods

A sample of 30 chronic stroke survivors wore a multi-sensor system in the natural environment over a 1-week monitoring period. The sensor system captured time in active movement of each arm, arm use ratio, step counts and stance time symmetry. Using the data from the monitoring period, participants were presented with a movement report with visual displays of quantitative and qualitative feedback. A survey and qualitative interview were used to assess ease of understanding, actionability and components of feedback that users found most meaningful to drive lasting behavior change.

Results

Arm/hand use and mobility sensor-derived feedback metrics were easy to understand and actionable. The preferred metric to encourage arm/hand use was the hourly arm use bar plot, and similarly the preferred metric to encourage mobility was the hourly steps bar plot, which were each ranked as top choice by 40% of participants. Participants perceived that quantitative (i.e., step counts) and qualitative (i.e., stance time symmetry) mobility metrics provided complementary information. Three main themes emerged from the qualitative analysis: 1) Motivation for behavior change, 2) Real-time feedback based on individual goals, and 3) Value of experienced clinicians for prescription and accountability. Participants stressed the importance of having feedback tailored to their own personalized goals and receiving guidance from clinicians on strategies to progress and increase functional movement behavior in the unsupervised home and community setting.

Conclusion

The resulting technology has the potential to integrate engineering and personalized rehabilitation to maximize participation in meaningful life activities outside clinical settings in a less structured environment-one where stroke survivors live their lives.

What's the Future of Vascular Neurology?

The field of vascular neurology has made tremendous advances over the last several decades, with major shifts in diagnosis, treatment, prevention, and rehabilitation of patients with stroke. Furthermore, the individuals who are providing the care represent a different cohort than those who were caring for stroke patients 30 years ago, with the increasing need for rapid decision-making for acute interventions and a larger workforce being needed to provide the many complicated aspects of care of stroke patients. Understanding the history of the field is critical before one can speculate about its future directions. In summarizing some of the past massive shifts in the past few decades, this review will discuss future opportunities and future challenges and will introduce the rest of this special issue focusing on vascular neurology in a post-thrombectomy era. Although thrombolysis and thrombectomy remain a major part of ischemic stroke management and care, in the coming years, there will likely be further modifications in how we provide the care, who provides it, how we train those individuals who provide it, where it is provided, and what data inform early management decisions.

Artificial Intelligence in Medicine and Dentistry

INTRODUCTION

Artificial intelligence has been applied in various fields throughout history, but its integration into daily life is more recent. The first applications of AI were primarily in academia and government research institutions, but as technology has advanced, AI has also been applied in industry, commerce, medicine and dentistry.

OBJECTIVE

Considering that the possibilities of applying artificial intelligence are developing rapidly and that this field is one of the areas with the greatest increase in the number of newly published articles, the aim of this paper was to provide an overview of the literature and to give an insight into the possibilities of applying artificial intelligence in medicine and dentistry. In addition, the aim was to discuss its advantages and disadvantages.

CONCLUSION

The possibilities of applying artificial intelligence to medicine and dentistry are just being discovered. Artificial intelligence will greatly contribute to developments in medicine and dentistry, as it is a tool that enables development and progress, especially in terms of personalized healthcare that will lead to much better treatment outcomes.

Impact of Virtual Reality Cognitive and Motor Exercises on Brain Health

Innovative technologies of the 21st century have an extremely significant impact on all activities of modern humans. Among them, virtual reality (VR) offers great opportunities for scientific research and public health. The results of research to date both demonstrate the beneficial effects of using virtual worlds, and indicate undesirable effects on bodily functions. This review presents interesting recent findings related to training/exercise in virtual environments and its impact on cognitive and motor functions. It also highlights the importance of VR as an effective tool for assessing and diagnosing these functions both in research and modern medical practice. The findings point to the enormous future potential of these rapidly developing innovative technologies. Of particular importance are applications of virtual reality in basic and clinical neuroscience.

Psychometric Properties of a New Measure of Upper Limb Performance in Post-Stroke Individuals: Trunk-Based Index of Performance

BACKGROUND

Several measures of upper limb (UL) motor tasks have been developed to characterize recovery. However, UL performance and movement quality measures in isolation may not provide a true profile of functional recovery.

OBJECTIVE

To investigate the measurement properties of a new trunk-based Index of Performance (IPt) of the UL combining endpoint performance (accuracy and speed) and movement quality (trunk displacement) in stroke.

METHODS

Participants with stroke (n = 25, mean time since stroke: 18.7 ± 17.2 months) performed a reaching task over 3 evaluation sessions. The IPt was computed based on Fitts' Law that incorporated endpoint accuracy and speed corrected by the amount of trunk displacement. Test-retest reliability was analyzed using intraclass correlation coefficient (ICC) and Bland-Altman plots. Standard error of measurement (SEM) and Minimal Detectable Change (MDC) were determined. Validity was investigated through the relationship between IPt, Fugl-Meyer Assessment (FMA-UE), and Action Research Arm Test (ARAT), as well as the ability of IPt to distinguish between levels of UL motor impairment severity.

RESULTS

Test-retest reliability was excellent (ICC = .908, 95% CI: 0.807-0.96). Bland-Altman did not show systematic differences. SEM and MDC₉₅ were 14% and 39%, respectively. Construct validity was satisfactory. The IPt showed low-to-moderate relationships with FMA-UE (R² ranged from .236 to .428) and ARAT (R² ranged from .277 to .306). IPt scores distinguished between different levels of UL severity.

CONCLUSIONS

The IPt showed evidence of good reliability, and initial validity. The IPt may be a promising tool for research and clinical settings. Further research is warranted to investigate its validity with additional comparator instruments.

Prediction of post-stroke motor recovery benefits from measures of sub-acute widespread network damages

Following a stroke in regions of the brain responsible for motor activity, patients can lose their ability to control parts of their body. Over time, some patients recover almost completely, while others barely recover at all. It is known that lesion volume, initial motor impairment and cortico-spinal tract asymmetry significantly impact motor changes over time. Recent work suggested that disabilities arise not only from focal structural changes but also from widespread alterations in inter-regional connectivity. Models that consider damage to the entire network instead of only local structural alterations lead to a more accurate prediction of patients' recovery. However, assessing white matter connections in stroke patients is challenging and time-consuming. Here, we evaluated in a data set of 37 patients whether we could predict upper extremity motor recovery from brain connectivity measures obtained by using the patient's lesion mask to introduce virtual lesions in 60 healthy streamline tractography connectomes. This indirect estimation of the stroke impact on the whole brain connectome is more readily available than direct measures of structural connectivity obtained with magnetic resonance imaging. We added these measures to benchmark structural features, and we used a ridge regression regularization to predict motor recovery at 3 months post-injury. As hypothesized, accuracy in prediction significantly increased (R ² = 0.68) as compared to benchmark features (R ² = 0.38). This improved prediction of recovery could be beneficial to clinical care and might allow for a better choice of intervention.

Toward individualized medicine in stroke—The TiMeS project: Protocol of longitudinal, multi-modal, multi-domain study in stroke

Despite recent improvements, complete motor recovery occurs in <15% of stroke patients. To improve the therapeutic outcomes, there is a strong need to tailor treatments to each individual patient. However, there is a lack of knowledge concerning the precise neuronal mechanisms underlying the degree and course of motor recovery and its individual differences, especially in the view of brain network properties despite the fact that it became more and more clear that stroke is a network disorder. The TiMeS project is a longitudinal exploratory study aiming at characterizing stroke phenotypes of a large, representative stroke cohort through an extensive, multi-modal and multi-domain evaluation. The ultimate goal of the study is to identify prognostic biomarkers allowing to predict the individual degree and course of motor recovery and its underlying neuronal mechanisms paving the way for novel interventions and treatment stratification for the individual patients. A total of up to 100 patients will be assessed at 4 timepoints over the first year after the stroke: during the first (T1) and third (T2) week, then three (T3) and twelve (T4) months after stroke onset. To assess underlying mechanisms of recovery with a focus on network analyses and brain connectivity, we will apply synergistic state-of-the-art systems neuroscience methods including functional, diffusion, and structural magnetic resonance imaging (MRI), and electrophysiological evaluation based on transcranial magnetic stimulation (TMS) coupled with electroencephalography (EEG) and electromyography (EMG). In addition, an extensive, multi-domain neuropsychological evaluation will be performed at each timepoint, covering all sensorimotor and cognitive domains. This project will significantly add to the understanding of underlying mechanisms of motor recovery with a strong focus on the interactions between the motor and other cognitive domains and multimodal network analyses. The population-based, multi-dimensional dataset will serve as a basis to develop biomarkers to predict outcome and promote personalized stratification toward individually tailored treatment concepts using neuro-technologies, thus paving the way toward personalized precision medicine approaches in stroke rehabilitation.

Personalized Approaches to Stroke: One Step Forward for Functional Recovery of Stroke Patients

Recent advances in diagnoses, management, and rehabilitation have had a significant impact to reduce mortality and functional recovery in stroke patients. In spite of these medical advances, many stroke survivors still suffer from significant disabilities. Stroke is a complex disease caused by a combination of multiple risk factors. Therefore, personalized medicine is more important than any other field to overcome the limitations of current stroke management and rehabilitation. It is necessary to apply accurate evaluation for functions and a personalized approach in consideration of various characteristics of each stroke patient to improve function. The objective of this Special Issue is to inform the recent scientific knowledge, current limitations, and challenges for an individually tailored strategy in the areas of diagnosis, treatment, and rehabilitation of stroke. A multidisciplinary approach and research will be strongly encouraged for personalized medicine in the field of stroke treatment and rehabilitation.

Development and Validation of Prediction Models for Severe Complications After Acute Ischemic Stroke: A Study Based on the Stroke Registry of Northwestern Germany

Background

The treatment of stroke has been undergoing rapid changes. As treatment options progress, prediction of those under risk for complications becomes more important. Available models have, however, frequently been built based on data no longer representative of today’s care, in particular with respect to acute stroke management. Our aim was to build and validate prediction models for 4 clinically important, severe outcomes after stroke.

Methods and Results

We used German registry data from 152 710 patients with acute ischemic stroke obtained in 2016 (development) and 2017 (validation). We took into account potential predictors that were available at admission and focused on in‐hospital mortality, intracranial mass effect, secondary intracerebral hemorrhage, and deep vein thrombosis as outcomes. Validation cohort prediction and calibration performances were assessed using the following 4 statistical approaches: logistic regression with backward selection, l1‐regularized logistic regression, k‐nearest neighbor, and gradient boosting classifier. In‐hospital mortality and intracranial mass effects could be predicted with high accuracy (both areas under the curve, 0.90 [95% CI, 0.90–0.90]), whereas the areas under the curve for intracerebral hemorrhage (0.80 [95% CI, 0.80–0.80]) and deep vein thrombosis (0.73 [95% CI, 0.73–0.73]) were considerably lower. Stroke severity was the overall most important predictor. Models based on gradient boosting achieved better performances than those based on logistic regression for all outcomes. However, area under the curve estimates differed by a maximum of 0.02.

Conclusions

We validated prediction models for 4 severe outcomes after acute ischemic stroke based on routinely collected, recent clinical data. Model performance was superior to previously proposed approaches. These predictions may help to identify patients at risk early after stroke and thus facilitate an individualized level of care.