Cognitive syndromes after the first stroke

Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementia

Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia. Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew's correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system's efficiency. Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535. Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.

European Stroke Organisation and European Academy of Neurology joint guidelines on post-stroke cognitive impairment

BACKGROUND AND PURPOSE

The optimal management of post-stroke cognitive impairment (PSCI) remains controversial. These joint European Stroke Organisation (ESO) and European Academy of Neurology (EAN) guidelines provide evidence-based recommendations to assist clinicians in decision making regarding prevention, diagnosis, treatment and prognosis.

METHODS

Guidelines were developed according to the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) methodology. The working group identified relevant clinical questions, performed systematic reviews, assessed the quality of the available evidence, and made specific recommendations. Expert consensus statements were provided where insufficient evidence was available to provide recommendations.

RESULTS

There was limited randomized controlled trial (RCT) evidence regarding single or multicomponent interventions to prevent post-stroke cognitive decline. Lifestyle interventions and treating vascular risk factors have many health benefits, but a cognitive effect is not proven. We found no evidence regarding routine cognitive screening following stroke, but recognize the importance of targeted cognitive assessment. We describe the accuracy of various cognitive screening tests, but found no clearly superior approach to testing. There was insufficient evidence to make a recommendation for use of cholinesterase inhibitors, memantine nootropics or cognitive rehabilitation. There was limited evidence on the use of prediction tools for post-stroke cognition. The association between PSCI and acute structural brain imaging features was unclear, although the presence of substantial white matter hyperintensities of presumed vascular origin on brain magnetic resonance imaging may help predict cognitive outcomes.

CONCLUSIONS

These guidelines highlight fundamental areas where robust evidence is lacking. Further definitive RCTs are needed, and we suggest priority areas for future research.

European Stroke Organisation and European Academy of Neurology joint guidelines on post-stroke cognitive impairment

The optimal management of post-stroke cognitive impairment remains controversial. These joint European Stroke Organisation (ESO) and European Academy of Neurology (EAN) guidelines provide evidence-based recommendations to assist clinicians in decision making around prevention, diagnosis, treatment and prognosis. These guidelines were developed according to ESO standard operating procedure and the Grading of Recommendations, Assessment, Development and Evaluation (GRADE) methodology. The working group identified relevant clinical questions, performed systematic reviews and, where possible, meta-analyses of the literature, assessed the quality of the available evidence and made specific recommendations. Expert consensus statements were provided where insufficient evidence was available to provide recommendations based on the GRADE approach. There was limited randomised controlled trial evidence regarding single or multicomponent interventions to prevent post-stroke cognitive decline. Interventions to improve lifestyle and treat vascular risk factors may have many health benefits but a beneficial effect on cognition is not proven. We found no evidence around routine cognitive screening following stroke but recognise the importance of targeted cognitive assessment. We described the accuracy of various cognitive screening tests but found no clearly superior approach to testing. There was insufficient evidence to make a recommendation for use of cholinesterase inhibitors, memantine nootropics or cognitive rehabilitation. There was limited evidence on the use of prediction tools for post-stroke cognitive syndromes (cognitive impairment, dementia and delirium). The association between post-stroke cognitive impairment and most acute structural brain imaging features was unclear, although the presence of substantial white matter hyperintensities of presumed vascular origin on acute MRI brain may help predict cognitive outcomes. These guidelines have highlighted fundamental areas where robust evidence is lacking. Further, definitive randomised controlled trials are needed, and we suggest priority areas for future research.

Prognostic rules for predicting cognitive syndromes following stroke: A systematic review

Purpose

Stroke survivors are at high risk of developing cognitive syndromes, such as delirium and dementia. Accurate prediction of future cognitive outcomes may aid timely diagnosis, intervention planning, and stratification in clinical trials. We aimed to identify, describe and appraise existing multivariable prognostic rules for prediction of post-stroke cognitive status.

Method

We systematically searched four electronic databases from inception to November 2019 for publications describing a method to estimate individual probability of developing a cognitive syndrome following stroke. We extracted data from selected studies using a pre-specified proforma and applied the Prediction model Risk Of Bias Assessment Tool (PROBAST) for critical appraisal.

Findings

Of 17,390 titles, we included 10 studies (3143 participants), presenting the development of 11 prognostic rules – 7 for post-stroke cognitive impairment and 4 for delirium. Most commonly incorporated predictors were: demographics, imaging findings, stroke type and symptom severity. Among studies assessing predictive discrimination, the area under the receiver operating characteristic (AUROC) in apparent validation ranged from 0.80 to 0.91. The overall risk of bias for each study was high. Only one prognostic rule had been externally validated.

Discussion/conclusion: Research into the prognosis of cognitive outcomes following stroke is an expanding field, still at its early stages. Recommending use of specific prognostic rules is limited by the high risk of bias in all identified studies, and lack of supporting evidence from external validation. To ensure the quality of future research, investigators should adhere to current, endorsed best practice guidelines for conduct of prediction model studies.

Imaging of vascular cognitive impairment

Vascular cognitive impairment (VCI) is a major health challenge and represents the second most common cause of dementia. We review the updated imaging classification and imaging findings of different subtypes of VCI. We will focus on the magnetic resonance imaging (MRI) markers of each subtype and highlight the role of advanced MR imaging sequences in the evaluation of these patients. Small vessel dementia appears as white matter hyperintensity, lacunae, microinfarcts, and microbleeds. Large vessel dementia includes strategic infarction and multi-infarction dementias. Hypoperfusion dementia can be seen as watershed infarcts and cortical laminar necrosis. Hemorrhagic dementia results from cerebral amyloid angiopathy and cortical superficial siderosis. Hereditary forms of VCI, caused by gene mutations such as CADASIL, should be suspected when dementia presents in young patients. Mixed dementia is seen in patients with Alzheimer's disease and the coexistence of cerebrovascular disease.

Self-perceptions on cognitive versus motor disability among neurologists

OBJECTIVE

The modified Rankin Scale is a functional outcome measure that disproportionately represents motor deficits. We hypothesize that among physicians who most commonly use the modified Rankin Scale to counsel patients on neurological treatment options, personal perception of acceptable or optimal outcome may be discordant with those described in clinical trials.

METHODS

A three-question anonymous voluntary survey was emailed to academic and community practicing neurologists and board-eligible or board-certified neurology fellows inquiring about their personal perception of a better quality of life between two choices featuring clinical scenarios that would qualify as modified Rankin Scale 2 and 4 disability outcome scores.

RESULTS

Sixty-nine percent of participants were 30-45 years old, 24% were 45-60 years old, and 7% were over 60 years old. Most responders were general neurologists (31.3%). The remaining responders represented multiple subspecialties including neurocritical care, vascular neurology, neurohospitalist medicine, neuromuscular neurology, neurophysiology, child neurology, neuro-oncology, headache, neuroimmunology, movement disorders, and palliative care medicine. Forty-four of 45 neurologists (97.7%) stated they would choose needing a wheelchair if still able to function at their cognitive baseline at work (p < 0.000001). One responder preferred to get around without assistance, despite new cognitive symptoms that would preclude them from working as a physician.

CONCLUSIONS

The modified Rankin Scale may not adequately represent preferred outcomes among neurology specialists, particularly with respect to cognitive symptoms. Future studies are needed to characterize long-term cognitive outcomes in patients with acute stroke-related conditions.