Voxel-based lesion symptom mapping analysis for dysphagia in stroke patients with isolated cerebellar lesions

Machine learning models based on location-radiomics enable the accurate prediction of early neurological function deterioration for acute stroke in elderly patients

Background

The timely and accurate identification of elderly stroke patients at risk of early neurological deterioration (END) is crucial for guiding clinical management. The present study aimed to create a comprehensive map of lesion location in elderly stroke, and build a machine learning model integrating location features and radiomics to predict END in elderly stroke patients.

Methods

A cohort of 709 elderly stroke patients from two centers patients were enrolled. Three machine learning models [logistic regression (LR), random forest (RF), and support vector machine (SVM)] based on location features, radiomics, and Loc-Rad were constructed to predict END in elderly stroke patients, respectively. The performance of models was evaluated using the receiver operating characteristic curves (ROC) and decision curve analysis (DCA). The SHapley Additive exPlanations (SHAP) was used to interpret and visualize the impact of the model predictors on the risk of END.

Results

The location maps for elderly stroke patients showed the bilateral cerebellum, left basal ganglia, left corona radiata, and right occipital lobe were significantly associated with END (p < 0.05). For three ML algorithms, the Loc-Rad models based on location features and radiomics demonstrated better performance than the separate location and radiomics-based models in the training cohort (p < 0.05), and the Loc-Rad model constructed with the RF algorithm performed best, with an AUC of 0.883 and accuracy of 0.888, and showed strong prediction performance in the external validation set (AUC of 0.818; accuracy of 0.811). The SHAP plots demonstrated that the most significant contributors to model performance were related to postcentral gyrus left, superior frontal gyrus right, w-HLH_glcm_Correlation, large vessel occlusion and lateral ventricle_body left.

Conclusion

We constructed comprehensive maps of strategic lesion network localizations for predicting END in elderly stroke patients and developed a predictive ML model that incorporates both location and radiomics features. This model could facilitate the rapid and robust prediction of the risk of END, enabling timely interventions and personalized treatment strategies to improve patient outcomes.

Dysphagia in multiple sclerosis: pathophysiology, assessment, and management-an overview

Dysphagia is a frequent and life-threatening complication of multiple sclerosis (MS). Swallowing disturbances may be present at all stages of MS, although their prevalence increases with age, with disease duration, and in progressive phenotypes. The pathophysiology of dysphagia in MS is likely due to a combination of factors, including the involvement of corticobulbar tracts, the cerebellum, and the brainstem. Accurate diagnosis and early management of swallowing disorders improve quality of life and may delay complications or invasive therapeutic interventions. Here we provide an overview of the pathophysiology, the assessment, and the management of MS dysphagia, also examining the possible role of novel therapeutic strategies. Although studies using imaging and neurophysiological techniques have contributed to better characterize swallowing alterations in MS, the treatment of dysphagia is still challenging. Rehabilitation represents the main therapeutic approach for swallowing disorders. Recently, some innovative neurophysiological approaches, such as pharyngeal electrical stimulation (PES), repetitive transcranial magnetic stimulation (rTMS), and transcranial direct current stimulation (tDCS), have been proposed as a supplement to swallowing therapy in different neurological conditions. However, only few studies have explored the role of neuromodulation for MS dysphagia.

Incidence and Risk Factors for Dysphagia Following Cerebellar Stroke: a Retrospective Cohort Study

The cerebellum is known to play a supportive role in swallowing-related functions; however, wide discrepancies about the incidence rate of swallowing disorders following cerebellar strokes exist within the literature. This study aimed to investigate the incidence rate of dysphagia and the factors which may affect the presence of dysphagia and clinical recovery in individuals diagnosed with cerebellar stroke. A retrospective chart audit of 1651 post-stroke patients (1049 males and 602 females) admitted with a cerebellar stroke to a comprehensive tertiary hospital in China was conducted. Data on demographics, medical, along with swallowing function assessment were collected. Differences between dysphagic and non-dysphagic groups were evaluated using t-tests and Pearson's chi-square test. Univariate logistic regression analysis was performed to establish factors associated with the presence of dysphagia. A total of 11.45% of participants were identified with dysphagia during inpatient admission. Individuals with mixed types of stroke, multiple lesions in the cerebellum, and ages older than 85 years old were more likely to develop dysphagia. Moreover, the prognosis of dysphagia following a cerebellar stroke was associated with lesions in different parts of the cerebellum. The cumulative recovery rates from the best to worse were the right hemisphere group, the cerebellum vermis or peduncle group, and both the hemisphere group and the left hemisphere group, respectively.

Prevalence, recovery and phenotype of dysphagia in patients with ischaemic cerebellar stroke

BACKGROUND AND PURPOSE

Swallowing is a complex task, moderated by a sophisticated bilateral network including multiple supratentorial regions, the brainstem and the cerebellum. To date, conflicting data exist about whether focal lesions to the cerebellum are associated with dysphagia. Therefore, the aim of the study was to evaluate dysphagia prevalence, recovery and dysphagia pattern in patients with ischaemic cerebellar stroke.

METHODS

A retrospective analysis of patients consecutively admitted to an academic stroke centre with ischaemic stroke found only in the cerebellum was performed. The presence of dysphagia was the primary end-point and was assessed by a speech-language pathologist, according to defined criteria. Dysphagia pattern was evaluated by analysing the videos of the flexible endoscopic evaluation of swallowing. Brain imaging was used to identify lesion size and location associated with dysphagia.

RESULTS

Between January 2016 and December 2021, 102 patients (35.3% female) with a mean age of 52.8 ± 17.3 years were included. Thirteen (12.7%) patients presented with dysphagia. The most frequently observed flexible endoscopic evaluation of swallowing phenotype was premature spillage (n = 7; 58.3%), whilst significant residues or aspiration did not occur. One patient died (7.7%); the other patients showed improvement of dysphagia and one patient (7.7%) was discharged with dietary restrictions.

CONCLUSIONS

Although the involvement of the cerebellum in deglutition has become increasingly evident, isolated lesions to the cerebellum are less likely to cause clinically relevant and persisting dysphagia compared to other brain regions. The observed dysphagia pattern shows a lack of coordination and control, resulting in premature spillage or fragmented bolus transfer in some patients.

Clinical Features and Voxel-Based-Symptom-Lesion Mapping of Silent Aspiration in Acute Infratentorial Stroke

Post-stroke dysphagia (PSD) is a severe and common complication after ischemic stroke. The role of silent aspiration as an important contributing factor in the development of a dysphagia-associated complications, in particular aspiration-associated pneumonia has been insufficiently understood. The aim of this study was to investigate the characteristics and risk factors of silent aspiration in patients with acute infratentorial stroke by FEES and to identify culprit lesions in stroke patient with a high risk of silent aspiration via voxel-based-symptom-lesion mapping (VBS/ML). This study is a retrospective observational study based on a prospectively collected FEES and stroke database. Consecutive patient cases with acute ischemic infratentorial stroke and FEES examination between 2017 and 2022 were identified. Group allocation was performed based on PAS scores. Imaging analysis was performed by manual assignment and by VBS/ML. Group comparisons were performed to assess silent aspiration characteristics. Binary logistic regression analysis was performed to determine if baseline clinical, demographic, and imaging parameters were helpful in predicting silent aspiration in patients. In this study 84 patient cases with acute infratentorial stroke who underwent FEES examination were included. Patients were moderately affected at admission (mean NIH-SS score at admission 5.7 SD ± 4.7). Most lesions were found pontine. Overall 40.5% of patients suffered from silent aspiration, most frequently in case of bilateral lesions. Patients with silent aspiration had higher NIH-SS scores at admission (p < 0.05), had a more severe swallowing disorder (p < 0.05) and were 4.7 times more likely to develop post-stroke pneumonia. Patients who underwent FEES examination later than 72 h after symptom onset were significantly more likely to suffer from silent aspiration and to develop pneumonia compared to patients who underwent FEES examination within the first 72 h (p < 0.05). A binary logistic regression model identified NIH-SS at admission as a weak predictor of silent aspiration. Neither in manual assignment of the lesions to brain regions nor in voxel-wise statistic regression any specific region was useful in prediction of silent aspiration. Silent aspiration is common in patients with infratentorial stroke and contributes to the risk for pneumonia. Patients with silent aspiration are more severely affected by stroke, but cannot reliably be identified by NIH-SS at admission or lesion location. Patients suffering from acute infratentorial stroke should been screened and examined for PSD and silent aspiration.

Lesion voxels to lesion networks: The enduring value of the Vietnam Head Injury Study

The Vietnam Head Injury Study has been curated by Dr Jordan Grafman since the 1980s in an effort to study patients with penetrating traumatic brain injuries suffered during the Vietnam War. Unlike many datasets of ischemic stroke lesions, the VHIS collected extraordinarily deep phenotyping and was able to sample lesion locations that are not constrained to typical vascular territories. For decades, this dataset has helped researchers draw causal links between neuroanatomical regions and neuropsychiatric symptoms. The value of the VHIS has only increased over time as techniques for analyzing the dataset have developed and evolved. Tools such as voxel lesion symptom mapping allowed one to relate symptoms to individual brain voxels. With the advent of the human connectome, tools such as lesion network mapping allow one to relate symptoms to connected brain networks by combining lesion datasets with new atlases of human brain connectivity. In a series of recent studies, lesion network mapping has been combined with the Vietnam Head Injury dataset to identify brain networks associated with spirituality, religiosity, consciousness, memory, emotion regulation, addiction, depression, and even transdiagnostic mental illness. These findings are enhancing our ability to make diagnoses, identify potential treatment targets for focal brain stimulation, and understand the human brain generally. Our techniques for studying brain lesions will continue to improve, as will our tools for modulating brain circuits. As these advances occur, the value of well characterized lesion datasets such as the Vietnam Head Injury Study will continue to grow. This study aims to review the history of the Vietnam Head Injury Study and contextualize its role in modern-day localization of neurological symptoms.

Dysphagia following cerebellar stroke: analyzing the contribution of the cerebellum to swallowing function

Swallowing is essential for human health, and the cerebellum is crucial for motor movement regulation. Cerebellar strokes may cause dysphagia, but their exact effects remain unexplored in swallowing function. Therefore, the aim of this study was to analyze the precise clinical characteristics of the oral and pharyngeal phases of swallowing after cerebellar stroke and to critically discuss the cerebellum's contribution to swallowing. The study involved 34 participants with cerebellar strokes, gathered through convenience sampling. Neurologists diagnosed isolated strokes, and a speech and language pathologist examined swallowing ability using the Mann Assessment of Swallowing Ability. The study found that 52.9% of people experienced dysphagia after a cerebellar stroke. Dysphagia was significantly associated with a higher risk of aspiration. Age was also significantly correlated with dysphagia. No significant correlation was found between swallowing ability and sex. In conclusion, this study suggests isolated cerebellar stroke can adversely affect the motor and non-motor aspects of swallowing and cause severe dysphagia and aspiration risk. Thus, early diagnosis and timely management of dysphagia following a cerebellar stroke can help prevent serious consequences.

The assessment of dysphagia after stroke: state of the art and future directions

Dysphagia is a major complication following an acute stroke that affects the majority of patients. Clinically, dysphagia after stroke is associated with increased risk of aspiration pneumonia, malnutrition, mortality, and other adverse functional outcomes. Pathophysiologically, dysphagia after stroke is caused by disruption of an extensive cortical and subcortical swallowing network. The screening of patients for dysphagia after stroke should be provided as soon as possible, starting with simple water-swallowing tests at the bedside or more elaborate multi-consistency protocols. Subsequently, a more detailed examination, ideally with instrumental diagnostics such as flexible endoscopic evaluation of swallowing or video fluoroscopy is indicated in some patients. Emerging diagnostic procedures, technical innovations in assessment tools, and digitalisation will improve diagnostic accuracy in the future. Advances in the diagnosis of dysphagia after stroke will enable management based on individual patterns of dysfunction and predisposing risk factors for complications. Progess in dysphagia rehabilitation are essential to reduce mortality and improve patients' quality of life after a stroke.

Neural basis of dysphagia in stroke: A systematic review and meta-analysis

Objectives

Dysphagia is a major cause of stroke infection and death, and identification of structural and functional brain area changes associated with post-stroke dysphagia (PSD) can help in early screening and clinical intervention. Studies on PSD have reported numerous structural lesions and functional abnormalities in brain regions, and a systematic review is lacking. We aimed to integrate several neuroimaging studies to summarize the empirical evidence of neurological changes leading to PSD.

Methods

We conducted a systematic review of studies that used structural neuroimaging and functional neuroimaging approaches to explore structural and functional brain regions associated with swallowing after stroke, with additional evidence using a live activation likelihood estimation (ALE) approach.

Results

A total of 35 studies were included, including 20 studies with structural neuroimaging analysis, 14 studies with functional neuroimaging analysis and one study reporting results for both. The overall results suggest that structural lesions and functional abnormalities in the sensorimotor cortex, insula, cerebellum, cingulate gyrus, thalamus, basal ganglia, and associated white matter connections in individuals with stroke may contribute to dysphagia, and the ALE analysis provides additional evidence for structural lesions in the right lentiform nucleus and right thalamus and functional abnormalities in the left thalamus.

Conclusion

Our findings suggest that PSD is associated with neurological changes in brain regions such as sensorimotor cortex, insula, cerebellum, cingulate gyrus, thalamus, basal ganglia, and associated white matter connections. Adequate understanding of the mechanisms of neural changes in the post-stroke swallowing network may assist in clinical diagnosis and provide ideas for the development of new interventions in clinical practice.

Effects of Insular Cortex on Post-Stroke Dysphagia: A Systematic Review and Meta Analysis

Objective: To investigate the relationship of lobar and deep brain regions with post-stroke dysphagia (PSD). Method: The databases of Medline, Embase, Web of Science, and Cochrane Library were searched from the establishment to May 2022. Studies that investigated the effects of lesions in lobar and deep brain regions on swallowing function after stroke were screened. The primary outcomes were PSD-related brain regions (including aspiration-related and oral transit time-related brain regions). The secondary outcomes were the incidence rate of PSD. The brain regions with the most overlap in the included studies were considered to be most relevant to PSD, and were presented as percentages. Data were compared utilizing the t-tests for continuous variables and χ2 for frequency-based variables. Result: A total of 24 studies and 2306 patients were included. The PSD-related lobar and deep brain regions included the insular cortex, frontal lobe, temporal gyrus, basal ganglia, postcentral, precentral, precuneus, corona radiate, etc. Among these brain regions, the insular cortex was most frequently reported (taking up 54.2%) in the included studies. Furthermore, the total incidence rate of PSD was around 40.4%, and the incidence of male was nearly 2.57 times as much as that of female (χ2 = 196.17, p < 0.001). Conclusions: In lobar and deep brain regions, the insular cortex may be most relevant to PSD and aspiration, which may be a potentially promising target in the treatment of PSD.