Stroke Characteristics Research Articles

Prevalence and characteristics of comorbid stroke and traumatic brain injury in a real-world population: findings from a nationally representative cross-sectional survey in China

BackgroundIn China, data on the prevalence and characteristics of comorbid stroke and traumatic brain injury (TBI) in real-world populations are still lacking but of paramount importance for the evidence-based prevention and control of the comorbidity of the two diseases. This study aimed to investigate the prevalence and characteristics of comorbid stroke and TBI in a real-world population.MethodsIn 2013, a nationally representative, door-to-door survey on stroke and TBI using a complex, multistage, probability sampling design was conducted among approximately 600,000 participants from 155 urban and rural areas in China (Ethic ID: KY2013-006-01). The weighted prevalence of comorbid stroke and TBI was estimated using individuals’ final weight. A Poisson regression analysis was used to compare the rate ratio of the comorbidity prevalence among different subgroups of the population, including age, sex, place of residence, and geographic location subgroups. For analyses of associations between the comorbidities and predictors of interest, all other variables were adjusted for in a multinomial logistic regression model.ResultsAmong the 596,536 people, 219 patients with comorbid stroke and TBI were identified. The point prevalence of comorbid stroke and TBI weighted to the China 2010 census population was 29.30 (95% CI: 22.69–37.84) per 100,000 population in China. The adjusted prevalence of post-TBI stroke in patients with previous TBI was significantly higher than that of post-stroke TBI in patients with previous stroke (6021.3 vs. 811.1 per 100,000 people; rate ratio: 11.001; 95% CI: 8.069–14.998). Patients with nonconcussion had significantly higher rates of both pre-stroke TBI (odds ratio: 4.694; 95% CI: 3.296–6.687) and post-stroke TBI (odds ratio: 6.735; 95% CI: 3.719–12.194) than patients with concussion. Compared to patients with ischaemic stroke, patients with subarachnoid haemorrhage (odds ratio: 2.044; 95% CI: 1.097–3.809) and intracerebral haemorrhage (odds ratio: 1.903; 95% CI: 1.296–2.795) had significantly higher rates of post-TBI stroke.ConclusionsThe high prevalence of stroke among TBI patients is becoming a new public health issue. TBI patients, especially those with nonconcussion TBI, are more likely to develop comorbid stroke and TBI than stroke patients, especially ischaemic stroke patients.

Ischemic patterns and their angiographic risk factors in adult patients with moyamoya disease.

The present study aims to determine whether angiographic differences increase the risk of ischemic pattern among adult patients with moyamoya disease (MMD). From January 2020 to December 2021, we retrospectively enrolled 123 ischemic or asymptomatic adult patients diagnosed as MMD. Angiographic changes including Suzuki stage, moyamoya vessels, anterior choroidal artery (AChoA) dilatation, lenticulostriate artery (LSA) dilatation, posterior communicating artery (PcomA) dilatation, and posterior cerebral artery (PCA) involvement were evaluated for all patients. Among the 123 participants, 35 ischemic patients and 88 asymptomatic patients were analyzed. There was no significant difference of Suzuki stage, AChoA dilatation, LSA dilatation, and PcomA dilatation between ischemic group and asymptomatic group. The grading of moyamoya vessels differed significantly but was not a factor associated with ischemic pattern after adjusting multiple related confounders. However, the frequency of PCA steno-occlusive changes in ischemic patients was statistically higher than that in asymptomatic patients (54.3% vs 34.1%, p = 0.039). Furthermore, PCA involvement was a risk factor associated with ischemic form and remained statistically significant after the multivariate adjustment (p = 0.033, 95% CI 1.092-8.310). PCA involvement is closely related to the presentation of ischemic stroke but other angiographic features had no association with ischemic pattern in adult MMD.

Research on the characteristics of the exhaust energy splitting method for the two-stroke low speed marine diesel engine

Efficient waste heat recovery (WHR) is the key to improve the thermal efficiency of the marine diesel engine and reduce the cost. According to the characteristics of long stroke of low-speed marine diesel engine, the exhaust energy splitting (EES) method based on exhaust energy distribution is proposed in this paper. EES is a new method of improving waste heat grade by separating high temperature exhaust gas and low temperature scavenging air. Compared with other studies on increasing exhaust temperature, EES significantly increases exhaust temperature and improves waste heat recovery efficiency without negatively affecting engine performance. Moreover, due to the adjustable EES valve, the optimal performance of engine and WHR system can be achieved under various operating conditions by adjusting the exhaust splitting phase (ESP). The One-Dimension and Three-Dimension simulation models for a two-stroke low speed marine diesel engine with waste heat recovery system are established. The exhaust energy distribution and the splitting phase to be optimized are also explored synchronously. The results show that by using the exhaust energy splitting method, temperature after turbine can be increased by more than 100 K compared with the baseline of the original engine system. Using Organic Rankine cycle (ORC) as WHR system, the waste heat recovery efficiency can reach over 17 %. Compared with the original engine, the total output power of the optimized EES low-speed engine and ORC system Increase by 100.90 kW under 75 % load and 154.72 kW under 100 % load, and the NOx emissions can be reduced by 5 %.

OC 26.3 Main Features of Ischemic Stroke in Patients with Acute Immune-Mediated Thrombotic Thrombocytopenic Purpura

OC 26.3 Main Features of Ischemic Stroke in Patients with Acute Immune-Mediated Thrombotic Thrombocytopenic Purpura

Unsupervised Domain Adaptation via Class Aggregation for Text Recognition

Cross-domain text recognition is a very challenging task due to the domain drift problem. One solution is aligning feature distributions between domains through Unsupervised Domain Adaptation (UDA). All existing methods perform feature alignment based on the whole image or semantic character features. However, visual character features without contextual semantics also contain much valuable information, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., stroke features of individual characters, which also benefits domain transfer. To this end, we propose a dual intra-Class Aggregation based unsupervised Domain Adaptation method (CADA) for text recognition, which aligns both visual and semantic character feature distributions. To our knowledge, CADA is the first to consider visual character features without contextual semantics in cross-domain text recognition tasks. Accordingly, a Single-head Self-Attention (SSA) mechanism is introduced for extracting visual character features. Thereafter, a dual intra-class aggregation strategy is designed, which performs class aggregations in both visual and semantic spaces. We test the proposed method on widely-used datasets by combining it with representative text recognition models with various decoding methods. Extensive experimental results demonstrate the superiority and generality. Moreover, there is no additional inference time introduced compared to the baselines.

GDB: Gated Convolutions-based Document Binarization

Document binarization is a crucial pre-processing step for various document analysis tasks. However, existing methods fail to accurately capture stroke edges, primarily due to the inherent limitations of vanilla convolutions and the absence of adequate boundary-related supervision during stroke edge extraction. In this paper, we formulate text extraction as the learning of gating values and propose an end-to-end network architecture based on gated convolutions, named GDB, to address the problem of imprecise stroke edge extraction. The gated convolutions enable the selective extraction of stroke feature with different attention. Our proposed framework comprises two stages. Firstly, a coarse sub-network with an extra edge branch is trained to enhance the precision of feature maps by incorporating a priori mask and edge information. Secondly, a refinement sub-network is cascaded to enhance the output of the first stage using gated convolutions based on the sharp edges. To effectively incorporate global information, GDB also integrates a parallelized multi-scale operation that combines local and global features. We conduct comprehensive experiments on ten Document Image Binarization Contest (DIBCO) datasets from 2009 to 2019 and Document Deblurring Datasets. Experimental results show that our proposed methods outperform the state-of-the-art methods across all metrics on average. Extensive ablation studys demonstrate the efficacy of key components. Available codes: https://github.com/Royalvice/GDB.

Hemorrhagic transformation in patients with large-artery atherosclerotic stroke is associated with the gut microbiota and lipopolysaccharide.

Abstract JOURNAL/nrgr/04.03/01300535-202407000-00032/figure1/v/2023-11-20T171125Z/r/image-tiff Hemorrhagic transformation is a major complication of large-artery atherosclerotic stroke (a major ischemic stroke subtype) that worsens outcomes and increases mortality. Disruption of the gut microbiota is an important feature of stroke, and some specific bacteria and bacterial metabolites may contribute to hemorrhagic transformation pathogenesis. We aimed to investigate the relationship between the gut microbiota and hemorrhagic transformation in large-artery atherosclerotic stroke. An observational retrospective study was conducted. From May 2020 to September 2021, blood and fecal samples were obtained upon admission from 32 patients with first-ever acute ischemic stroke and not undergoing intravenous thrombolysis or endovascular thrombectomy, as well as 16 healthy controls. Patients with stroke who developed hemorrhagic transformation (n = 15) were compared to those who did not develop hemorrhagic transformation (n = 17) and with healthy controls. The gut microbiota was assessed through 16S ribosomal ribonucleic acid sequencing. We also examined key components of the lipopolysaccharide pathway: lipopolysaccharide, lipopolysaccharide-binding protein, and soluble CD14. We observed that bacterial diversity was decreased in both the hemorrhagic transformation and non-hemorrhagic transformation group compared with the healthy controls. The patients with ischemic stroke who developed hemorrhagic transformation exhibited altered gut microbiota composition, in particular an increase in the relative abundance and diversity of members belonging to the Enterobacteriaceae family. Plasma lipopolysaccharide and lipopolysaccharide-binding protein levels were higher in the hemorrhagic transformation group compared with the non-hemorrhagic transformation group. lipopolysaccharide, lipopolysaccharide-binding protein, and soluble CD14 concentrations were associated with increased abundance of Enterobacteriaceae. Next, the role of the gut microbiota in hemorrhagic transformation was evaluated using an experimental stroke rat model. In this model, transplantation of the gut microbiota from hemorrhagic transformation rats into the recipient rats triggered higher plasma levels of lipopolysaccharide, lipopolysaccharide-binding protein, and soluble CD14. Taken together, our findings demonstrate a noticeable change in the gut microbiota and lipopolysaccharide-related inflammatory response in stroke patients with hemorrhagic transformation. This suggests that maintaining a balanced gut microbiota may be an important factor in preventing hemorrhagic transformation after stroke.

Do stroke services still show sex differences? A multicenter study

BackgroundThe issue of sex differences in stroke has gained concern in the past few years. However, multicenter studies are still required in this field. This study explores sex variation in a large number of patients and compares stroke characteristics among women in different age groups and across different countries.MethodsThis multicenter retrospective cross-sectional study aimed to compare sexes regarding risk factors, stroke severity, quality of services, and stroke outcome. Moreover, conventional risk factors in women according to age groups and among different countries were studied.ResultsEighteen thousand six hundred fifty-nine patients from 9 countries spanning 4 continents were studied. The number of women was significantly lower than men, with older age, more prevalence of AF, hypertension, and dyslipidemia. Ischemic stroke was more severe in women, with worse outcomes among women (p: < 0.0001), although the time to treatment was shorter. Bridging that was more frequent in women (p:0.002). Analyzing only women: ischemic stroke was more frequent among the older, while hemorrhage and TIA prevailed in the younger and stroke of undetermined etiology. Comparison between countries showed differences in age, risk factors, type of stroke, and management.ConclusionWe observed sex differences in risk factors, stroke severity, and outcome in our population. However, access to revascularization was in favor of women.

Prevalence of Thromboembolic Events in Patients With Non–Small Cell Lung Cancer and RET Fusions

This cohort study examines the incidence, risks, and characteristics of deep vein thrombosis, pulmonary embolism, arterial thrombosis, and stroke among patients with non–small cell lung cancer (NSCLC) and RET fusions.

Predictors of manual dexterity at 3 and 6 months after stroke: integration of clinical, neurophysiological, and neuroimaging factors.

This retrospective study aimed to predict dexterity at 3 and 6 months post-stroke by integrating clinical, neurophysiological, and neuroimaging factors. We included 126 patients with first-ever, unilateral, and supratentorial stroke. Demographic, stroke characteristics, and initial clinical assessment variables [Mini-mental state examination and Fugl-Meyer Assessment Upper Extremity (FMA-UE)] were evaluated 2 weeks after stroke. Dexterity, measured using the Manual Function Test (MFT) hand subscore, was the primary outcome. The neurophysiological variables, upper limb somatosensory evoked potential (SEP) and motor evoked potential (MEP), were assessed 2 weeks post-stroke. The neuroimaging variable, fractional anisotropy (FA) of the corticospinal tract (CST), was assessed 3 weeks post-stroke. Multiple regression analysis revealed significant predictors for improved dexterity at 3 and 6 months post-stroke, including younger age, higher FMA-UE score, presence of waveforms in the SEP and MEP, and higher FA values in the CST (adjusted R 2 = 0.776, P < 0.001 at 3 months; adjusted R 2 = 0.668, P < 0.001 at 6 months; where MEP, SEP, and FA accounted together for an additional 0.079 and 0.166 of variance beyond age and FMA-UE, respectively). Subgroup analysis was conducted by categorizing the participants based on their initial hand function: those with no hand function (MFT hand subscore = 0) (N = 60) and those with a score >0 (N = 51). Initial FMA-UE was a primary predictive factor regardless of the time point or initial severity, whereas the presence of MEP was a significant predictor only in the group with no initial hand dexterity.

Imaging features of cardioembolic stroke on 4-dimensional computed tomography angiography.

Identifying cardioembolic stroke is important for the decision-making of endovascular treatment and anticoagulation therapy. We aimed to explore the features of cardioembolic stroke on 4-dimensional (4D) computed tomography angiography (4D-CTA) and assess whether these features can assist in classifying stroke etiology. In this retrospective study, we analyzed the images of 294 patients with acute ischemic stroke (AIS) from July 2020 to February 2022 at the First Affiliated Hospital of Chongqing Medical University, which had been consecutively collected. The data of 110 patients with occlusion of the M1/M2 segment of the middle cerebral artery (MCA) with/without intracranial internal carotid artery (ICA) occlusion were analyzed to calculate the clot burden score (CBS) and collateral score (CS), and the data of 88 patients with a clear origin and distal part were analyzed to measure clot length. Maximum intensity projection (MIP) and time MIP (tMIP) post-processing were used to assess the clot features. The Mann-Whitney U test was used to compare the clot characteristics between the 2 groups. Binary logistic regression was performed to assess the association between the image characteristics and cardioembolic stroke. Moreover, the receiver operating characteristic (ROC) curve was used to test the diagnostic efficacy of MIP/tMIP clot features in classifying cardioembolic stroke. Age, high-risk factors for cerebrovascular disease, high/medium-risk sources of cardioembolic stroke, clot length, CBS, and CS were significantly different between the cardioembolic stroke group and non-cardioembolic stroke group (P<0.05). In the cardioembolic stroke group, the median MIP and tMIP clot length was 12 mm [interquartile range (IQR), 8.3-17.4 mm] and 9.3 mm (IQR, 6.8-14.3 mm), respectively. In the non-cardioembolic stroke group, the median MIP and tMIP clot length was 6.5 mm (IQR, 4.7-11.5 mm) and 5.8 mm (IQR, 3.9-10.6 mm), respectively. Binary logistic regression showed that cardioembolic stroke was significantly associated with MIP-clot length [odds ratio (OR), 1.15; 95% confidence interval (CI): 1.02-1.29; P<0.05], tMIP-clot length (OR, 1.18; 95% CI: 1.02-1.36; P<0.05), and tMIP-CBS (OR, 3.96; 95% CI: 1.08-14.58; P<0.05). The area under the ROC curve (AUC) values of MIP clot length for identifying cardioembolic stroke were 0.75 (95% CI: 0.65-0.84, P<0.05), with a cut-off value of >7.4 mm [sensitivity: 84.62% (95% CI: 69.50-94.10%); specificity: 59.18% (95% CI: 44.20-73.00%)]. The AUC value of tMIP clot length was 0.72 (95% CI: 0.61-0.81, P<0.05), with a cut-off value of >5.4 mm [sensitivity: 92.31% (95% CI: 79.10-98.40%); specificity: 48.98% (95% CI: 34.40-63.70%)]. Clot length and CBS were overestimated on MIP images. Among the clot characteristics, clot length could identify cardioembolic stroke.

Clinical characteristics and intracranial arterial lesions of non-young adult ischemic stroke patients with RNF213 p.R4810K variant

BackgroundAlthough RNF213 p.R4810K, a genetic susceptibility variant for moyamoya disease (MMD), is associated with intracranial artery stenosis/occlusion (ICASO), the impact of this variant on ischemic stroke patients in non-young adults is unclear. We aimed to determine the characteristics of non-young adult stroke patients with RNF213 p.R4810K. MethodsWe retrospectively identified acute ischemic stroke patients ≥50 years who were admitted to our hospital and underwent intracranial vascular imaging. We reviewed the patients with RNF213 p.R4810K and compared stroke characteristics and the frequency and location of ICASO between patients with and without the variant. ResultsAmong 341 patients, RNF213 p.R4810K was identified in 7 patients (2.1%). Five of the 7 patients with the variant (71%) had multiple ICASO without any finding of MMD and remaining 2 patients had no ICASO. The presumed etiologies of ICASO were atherosclerosis in 3 cases, vasculitis in 1, and undetermined vasculopathy in 1. ICASO in the anterior circulation was more common in patients with the variant than in those without (71% vs. 25%). The internal carotid artery, the M1 segment of the middle cerebral artery, the A1 segment of the anterior cerebral artery, and the P1 segment of the posterior cerebral artery, which were the most frequently affected arteries in MMD, were more often affected in the variant group. ConclusionsNon-young adult stroke patients with RNF213 p.R4810K are more likely to have ICASO in arterial segments commonly affected in MMD. The etiology of their ICASO exhibited diverse mechanisms, possibly depending on vascular risk and other environmental factors.

Lesion location and serum levels of homocysteine are associated with early-onset post-stroke depression in acute ischemic stroke.

It is well known that post-stroke depression (PSD) is a psychiatric complication after stroke which leads to worse functional outcome and poorer quality of life. Some risk factors including gender, stroke severity, lesion location, homocysteine (HCY), and so on are associated with PSD. This study aims to further explore the possible relationship between serum levels of HCY and early-onset PSD and the predictive value of HCY combined with stroke characteristics for early-onset PSD. Two hundred forty-five patients with acute ischemic stroke who met the criteria were included in this study from March 2015 to March 2017. PSD was diagnosed at 2weeks after stroke. The severity of depressive symptoms was evaluated with the Hamilton depression scale 17 items (HAMD-17), and patients with HAMD scores ≥7 were included in the PSD group. The demographic data, clinical characteristics, serum levels of HCY, and detailed radiological variables (e.g., lesion location and quantity of the brain infarct) were also examined. In total, 97 (39.6%) patients of the 245 patients were diagnosed with depression. The univariate analyses suggested that patients in PSD group had a higher NIHSS score, modified Rankin Scale score, and HCY levels than patients in non-PSD group (p < .001). The patients with PSD had higher proportion of multiple-site acute infarcts and frontal lobe lesion (p < .05). In multivariate logistic regression analysis, NIHSS score at admission, serum levels of HCY, and multiple-site lesions were independently related to early-onset PSD. Based on receiver operating characteristic curves analysis, the combination of HCY, NIHSS scores, multiple-site lesions, and lesion location revealed a highest area under the curve of 0.807 (95% confidence interval [CI]: 0.748-0.865, p < .001). Furthermore, there was a significantly increased risk of early-onset PSD associated with serum levels of HCY ≥16.98μmol/L (odds ratio [OR]=10.976, 95% CI: 5.585-21.573, p < .001). Our study indicated that higher NIHSS score, elevated serum levels of HCY, and multiple-site lesions may be independent risk factors of early-onset PSD. The combination of HCY, NIHSS scores, multiple-site lesions, and lesion location may provide greater predictive value than HCY alone for early-onset PSD. Early intervention for elevated serum levels of HCY may be a potential target for the intervention and prevention of PSD.

Characteristics, management and outcome of stroke: Observations from the Sri Lanka Stroke Clinical Registry

BackgroundStroke registries are pivotal to the monitoring and improvement of the quality of stroke care. We report data from the initial phase of a nationally representative hospital-based stroke registry in Sri Lanka. MethodsBased on an observational cohort design, all consecutive patients aged ≥18 years with a diagnosis of stroke or transient ischemic attack (TIA) presenting to six tertiary-care hospitals in the Western, Eastern, Southern, Northern and Central provinces of Sri Lanka within 14 days of onset were recruited. ResultsDuring a period of 14 months, 5893 patients with a stroke/TIA (58.8% men; mean age 65.22 years, SD=13.28) were entered into the database; 69.8% (n=4111) had an ischaemic stroke (IS); 20.9% (n=1233) had a haemorrhagic stroke (HS); 7.2% (424) had a TIA; and 2.1% (125) had a venous stroke. While IS were more common among women (71.7% vs 68.4%; p=0.006), HS were more common among men (22.3% vs 19.0%; p=0.003). Hemiparesis (86.2% vs 83.2%; p=0.011), headache (29% vs 11.6%; p<0.001), seizures (5.9% vs 4.2%; p=0.013), sphincter dysfunction (11.8% vs 7.7%; p<0.001) and hypertension (72% vs 67.3%, p=0.002) were more common in HS while dysphasia (63.2% vs 50.0%; p<0.001), ataxia (9.6% vs 7.3%; p=0.014), sensory disturbances (10.8% vs 6.0%; p<0.001) and diabetes mellitus (37.9% vs 28.1%; p<0.001) were more common in IS. Thrombolysis was administered in only 2.1% while only 14.6% had access to stroke units. The mean door-to-needle time was 100.2 (SD=46.0) minutes. The hospital mortality rate was 8.3%. Recurrent strokes within three months were more common in HS than IS (3.2% vs 1.6%; p=0.007). ConclusionsWhile stroke characteristics in Sri Lanka are similar to that of other populations, the rate of thrombolysis and access to stroke units are inadequate. The stroke registry provides useful data for the appraisal and improvement of stroke services.

A Method for Intelligent Road Network Selection Based on Graph Neural Network

As an essential role in cartographic generalization, road network selection produces basic geographic information across map scales. However, the previous selection methods could not simultaneously consider both attribute characteristics and spatial structure. In light of this, an intelligent road network selection method based on a graph neural network (GNN) is proposed in this paper. Firstly, the selection case is designed to construct a sample library. Secondly, some neighbor sampling and aggregation rules are developed to update road features. Then, a GNN-based selection model is designed to calculate classification labels, thus completing road network selection. Finally, a few comparative analyses with different selection methods are conducted, verifying that most of the accuracy values of the GNN model are stable over 90%. The experiments indicate that this method could aggregate stroke nodes and their neighbors together to synchronously preserve semantic, geometric, and topological features of road strokes, and the selection result is closer to the reference map. Therefore, this paper could bridge the distance between deep learning and cartographic generalization, thus facilitating a more intelligent road network selection method.

Early Epileptic Seizures after Ischemic Stroke: Their Association with Stroke Risk Factors and Stroke Characteristics.

Background and Objectives: A growing number of stroke survivors face various stroke complications, including new-onset epileptic seizures (ESs). Post-stroke ESs are divided into early and late ESs based on the time of onset after stroke. Early ESs are associated with worse stroke outcomes, longer hospitalization and an increased risk of late ESs. A variety of risk factors for early ESs are being studied in order to prevent their occurrence. Therefore, we aim to determine the association of early ESs with ischemic stroke risk factors and characteristics. Materials and Methods: A total of 166 patients, treated for ischemic stroke in the Hospital of Lithuanian University of Health Sciences Kaunas Clinics, were enrolled in a prospective cohort study. Initially, data about stroke risk factors, localization, severity and treatment were collected, followed by an observation period of 14 days for early ESs. Results: Early ESs occurred in 11 (6.6%) participants. The probability of early ESs after ischemic stroke among males and females (LogRank = 1.281; p > 0.05), younger (≤65 y) and older (>65 y) participants (LogRank = 0.129; p > 0.05) was the same. The presence of ischemic stroke risk factors, such as atrial fibrillation (LogRank = 0.004; p > 0.05), diabetes mellitus (LogRank = 1.168; p > 0.05) and dyslipidemia (LogRank = 0.092; p > 0.05), did not increase the probability of early ESs. However, participants without a prior history of arterial hypertension (LogRank = 4.453; p < 0.05) were more likely to develop early ESs. Stroke localization (anterior versus posterior) (LogRank = 0.011; p > 0.05), stroke severity (LogRank = 0.395; p > 0.05) and type of treatment (specific versus non-specific) (LogRank = 1.783; p > 0.05) did not affect the probability of early ESs.

Medical Named Entity Recognition Fusing Part-of-Speech and Stroke Features

It is highly significant from a research standpoint and a valuable practice to identify diseases, symptoms, drugs, examinations, and other medical entities in medical text data to support knowledge maps, question and answer systems, and other downstream tasks that can provide the public with knowledgeable answers. However, when contrasted with other languages like English, Chinese words lack a distinct dividing line, and medical entities have problems such as long length and multiple entity types nesting. Therefore, to address these issues, this study suggests a medical named entity recognition (NER) approach that combines part-of-speech and stroke features. First, the text is fed into the BERT pre-training model to get the semantic representation of the text, while the part-of-speech feature vector is obtained using the part-of-speech dictionary, and the stroke feature of the text is extracted through a convolution neural network (CNN). The word vector is then joined with the part-of-speech and stroke feature vectors, respectively, and input into the BiLSTM and CRF layer for training. Additionally, to balance the disparity in data volume across several types of entities, the class-weighted loss function is included in the loss function. According to the experimental findings, our model’s F1 score on the CCKS2019 dataset reaches 78.65%, and the recognition performance exceeds many existing algorithms.

SocialBit: protocol for a prospective observational study to validate a wearable social sensor for stroke survivors with diverse neurological abilities

IntroductionSocial isolation has been found to be a significant risk factor for health outcomes, on par with traditional risk factors. This isolation is characterised by reduced social interactions, which can...

Wearable Microwave Medical Sensing for Stroke Classification and Localization: A Space-Division-Based Decision-Tree Learning Method

Microwave medical imaging systems have shown a competitive advantage in stroke detection due to their cost-effectiveness, non-ionization, and portability. However, these systems often rely on time-consuming image reconstruction techniques, which are disadvantageous for timely stroke treatment. In this paper, a novel microwave medical sensing (MMS) method is proposed for fast stroke classification and localization, which utilizes space division of the region under examination (i.e., the head). The space division is enabled by the generalized scattering matrix theory and incorporates the brain anatomy. Then a novel decision tree learning method is proposed, which facilitates efficient stroke feature identification for classification. The spatial information acquired from the decision tree also results in rapid stroke localization. In order to verify the proposed method, we investigate the feasibility of classifying brain strokes between an intracranial haemorrhage stroke and an ischemic stroke with a wearable MMS system. Both numerical and experimental results are obtained. Compared to the traditional method, the classification rates for simulation and experimental results are improved by 14.1% and 19.2%, respectively. Furthermore, by utilizing the a priori information, the localization time is reduced by 21.1%. Finally, the localization accuracy is higher than 0.90 in both simulation and experimental studies. The classification accuracy and localization efficiency are shown to be greatly improved compared to the traditional method, which has great significance for wearable devices. This study proposes an efficient space-division-based detection method to localize the brain stroke without imaging.

Stroke Characteristics in a Cohort of Hmong American Patients.

Background Prior studies have indicated high rates of vascular risk factors, but little is known about stroke in Hmong. Methods and Results The institutional Get With The Guidelines (GWTG) database was used to identify patients discharged with acute ischemic stroke, intracerebral hemorrhage, or subarachnoid hemorrhage between 2010 and 2019. Hmong patients were identified using clan names and primary language. Univariate analysis was used to compare Hmong and White patients. A subarachnoid hemorrhage comparison was not conducted because of the small sample size. We identified 128 Hmong patients and 3084 White patients. Hmong patients had more prevalent hemorrhagic stroke (31% versus 15%; P<0.0016). In the acute ischemic stroke cohort, compared with White patients, Hmong patients were younger (60±13 versus 71±15 years; P<0.0001), presented to the emergency department almost 4 hours later; and had a lower thrombolysis usage rate (6% versus 14%; P=0.03496), worse lipid profile, higher hemoglobin A1C, similar stroke severity, and less frequent discharge to rehabilitation facilities. The most common ischemic stroke mechanism for Hmong patients was small-vessel disease. In the intracerebral hemorrhage cohort, Hmong patients were younger (55±13 versus 70±15 years; P<0.0001), had higher blood pressure, and had a lower rate of independent ambulation on discharge (9% versus 30%; P=0.0041). Conclusions Hmong patients with stroke were younger and had poorer risk factor control compared with White patients. There was a significant delay in emergency department arrival and low use of acute therapies among the Hmong acute ischemic stroke cohort. Larger studies are needed to confirm these observations, but action is urgently needed to close gaps in primary care and stroke health literacy.