Search

Abstract Stroke has a negative impact on people’s lives and is one of the leading causes of death and disability worldwide. Early detection of symptoms can significantly help predict stroke and promote a healthy lifestyle. Researchers have developed several methods to predict strokes using machine learning (ML) techniques. However, the proposed systems have suffered from the following two main problems. The first problem is that the machine learning models are biased due to the uneven distribution of classes in the dataset. Recent research has not adequately addressed this problem, and no preventive measures have been taken. Synthetic Minority Oversampling (SMOTE) has been used to remove bias and balance the training of the proposed ML model. The second problem is to solve the problem of lower classification accuracy of machine learning models. We proposed a learning system that combines an autoencoder with a linear discriminant analysis (LDA) model to increase the accuracy of the proposed ML model for stroke prediction. Relevant features are extracted from the feature space using the autoencoder, and the extracted subset is then fed into the LDA model for stroke classification. The hyperparameters of the LDA model are found using a grid search strategy. However, the conventional accuracy metric does not truly reflect the performance of ML models. Therefore, we employed several evaluation metrics to validate the efficiency of the proposed model. Consequently, we evaluated the proposed model’s accuracy, sensitivity, specificity, area under the curve (AUC), and receiver operator characteristic (ROC). The experimental results show that the proposed model achieves a sensitivity and specificity of 98.51% and 97.56%, respectively, with an accuracy of 99.24% and a balanced accuracy of 98.00%.

Introduction: Moyamoya disease (MMD) and non-MMD intracranial cerebral artery stenosis (ICAS) have been linked to the RNF213 rs112735431 gene in Korean and Japanese populations. This cross-sectional study investigates the prevalence of the RNF213 rs112735431 gene in non-cardioembolic ischemic stroke (NCIS) among Thai patients. Methods: A cross-sectional investigation was conducted on patients aged 18 years or older admitted to King Chulalongkorn Memorial Hospital between June 2015 and March 2016 with acute NCIS. ICAS and extracranial carotid artery stenosis (ECAS) were assessed through computer tomography angiography or magnetic resonance angiography. Blood samples were collected, and Sanger sequencing was performed. Results: Among 234 acute NCIS cases, 113 exhibited ICAS, 12 had ECAS, 20 had both, and 89 had neither. The RNF213 rs112735431 gene variant was detected in 2 patients, both heterozygous A/G. The frequency of the RNF213 rs112735431 variant was 0.9% (2/234; 95% CI: 0–2.1%) in acute NCIS patients and 1.8% (2/113; 95% CI: 0–4.2%) in ICAS. All individuals with the RNF213 variant were males with hypertension, diabetes mellitus, dyslipidemia, and ICAS, without a family history of ischemic stroke. Conclusion: This study reveals that the RNF213 rs112735431 gene variant is uncommon among Thai NCIS patients, suggesting a discrepancy in the prevalence of this genetic variation between Thai and other Eastern Asian populations.

Abstract Background Ischemic stroke (IS) is one of the leading causes of death among non-communicable diseases in Thailand. Patients who have survived an IS are at an increased risk of developing recurrent IS, which can result in worse outcomes and post-stroke complications. Objectives The study aimed to investigate the incidence of recurrent IS among patients with first-ever IS during a one-year follow-up period and to determine its associated risk factors. Methods Adult patients (aged ≥ 18 years) who were hospitalized at the Stroke Center, King Chulalongkorn Memorial Hospital (KCMH) in Bangkok, Thailand, due to first-ever IS between January and December 2019 and had at least one follow-up visit during the one-year follow-up period were included in this retrospective cohort study. IS diagnosis was confirmed by neurologists and imaging. The log-rank test was used to determine the event-free survival probabilities of recurrent IS in each risk factor. Results Of 418 patients hospitalized due to first-ever IS in 2019, 366 (87.6%) were included in the analysis. During a total of 327.2 person-years of follow-up, 25 (6.8%) patients developed recurrent IS, accounting for an incidence rate of 7.7 per 100 person-year (95% confidence interval [CI] 5.2–11.3). The median (interquartile range) time of recurrence was 35 (16–73) days. None of the 47 patients with atrial fibrillation developed recurrent IS. The highest incidence rate of recurrent IS occurred within 1 month after the first episode (34 per 100 person-years) compared to other follow-up periods. Patients with small vessel occlusion and large-artery atherosclerosis (LAA) constituted the majority of patients in the recurrent IS episode (48% and 40%, respectively), with LAA exhibiting a higher recurrence rate (13.5%). Additionally, smoking status was found to be associated with an increased risk of recurrence. Conclusion The incidence rate of the recurrence was moderate in our tertiary care setting, with a decreasing trend over time after the first episode. The various subtypes of IS and smoking status can lead to differences in event-free survival probabilities.

Cerebrovascular diseases such as stroke are among the most common causes of death and disability worldwide and are preventable and treatable. Early detection of strokes and their rapid intervention play an important role in reducing the burden of disease and improving clinical outcomes. In recent years, machine learning methods have attracted a lot of attention as they can be used to detect strokes. The aim of this study is to identify reliable methods, algorithms, and features that help medical professionals make informed decisions about stroke treatment and prevention. To achieve this goal, we have developed an early stroke detection system based on CT images of the brain coupled with a genetic algorithm and a bidirectional long short-term Memory (BiLSTM) to detect strokes at a very early stage. For image classification, a genetic approach based on neural networks is used to select the most relevant features for classification. The BiLSTM model is then fed with these features. Cross-validation was used to evaluate the accuracy of the diagnostic system, precision, recall, F1 score, ROC (Receiver Operating Characteristic Curve), and AUC (Area Under The Curve). All of these metrics were used to determine the system’s overall effectiveness. The proposed diagnostic system achieved an accuracy of 96.5%. We also compared the performance of the proposed model with Logistic Regression, Decision Trees, Random Forests, Naive Bayes, and Support Vector Machines. With the proposed diagnosis system, physicians can make an informed decision about stroke.

Presents corrections to the paper, Innovations in Stroke Identification: A Machine Learning-Based Diagnostic Model Using Neuroimages.

Abstract Background After the initiation of the COVID-19 vaccination program in Thailand, thousands of patients have experienced unusual focal neurological symptoms. We report 8 patients with focal neurological symptoms after receiving inactivated virus vaccine, CoronaVac. Case series Patients were aged 24–48 years and 75% were female. Acute onset of focal neurological symptoms occurred within the first 24 h after vaccination in 75% and between 1-7d in 25%. All presented with lateralized sensory deficits, motor deficits, or both, of 2–14 day duration. Migraine headache occurred in half of the patients. Magnetic resonance imaging of the brain during and after the attacks did not demonstrate any abnormalities suggesting ischemic stroke. All patients showed moderately large regions of hypoperfusion and concurrent smaller regions of hyperperfusion on SPECT imaging while symptomatic. None developed permanent deficits or structural brain injury. Discussions Here, we present a case series of transient focal neurological syndrome following Coronavac vaccination. The characteristic sensory symptoms, history of migraine, female predominant, and abnormal functional brain imaging without structural changes suggest migraine aura as pathophysiology. We propose that pain related to vaccine injection, component of vaccine, such as aluminum, or inflammation related to vaccination might trigger migraine aura in susceptible patients.

Abstract Background We report the first case of a patient who suffered transient focal neurological deficit mimicking stroke following CoronaVac vaccination. However, instead of an ischemic stroke, motor aura was suspected. Case presentations A 24 year-old Thai female presented with left hemiparesis fifteen minutes after receiving CoronaVac. She also had numbness of her left arm and legs, flashing lights, and headaches. On physical examination, her BMI was 32.8. Her vital signs were normal. She had moderate left hemiparesis (MRC grade III), numbness on her left face, arms, and legs. Her weakness continued for 5 days. A brain CT scan was done showing no evidence of acute infarction. Acute treatment with aspirin was given. MRI in conjunction with MRA was performed in which no restricted diffusion was seen. A SPECT was performed to evaluate the function of the brain showing significant hypoperfusion of the right hemisphere. The patient gradually improved and was discharged. Discussions In this study, we present the first case of stroke mimic after CoronaVac vaccination. After negative imaging studies had been performed repeatedly, we reach a conclusion that stroke is unlikely to be the cause. Presumably, this phenomenon could possibly have abnormal functional imaging study. Therefore, we believed that it might be due to cortical spreading depression, like migraine aura, which we had conducted a literature review.

Background We sought to determine recurrent stroke predictors among patients with embolic strokes of undetermined source (ESUS). Methods and Results We applied Cox proportional hazards models to identify clinical features associated with recurrent stroke among participants enrolled in RE‐SPECT ESUS (Randomized, Double‐Blind, Evaluation in Secondary Stroke Prevention Comparing the Efficacy and Safety of the Oral Thrombin Inhibitor Dabigatran Etexilate Versus Acetylsalicylic Acid in Patients With Embolic Stroke of Undetermined Source) trial, an international clinical trial evaluating dabigatran versus aspirin for patients with ESUS. During a median follow‐up of 19 months, 384 of 5390 participants had recurrent stroke (annual rate, 4.5%). Multivariable models revealed that stroke or transient ischemic attack before the index event (hazard ratio [HR], 2.27 [95% CI, 1.83–2.82]), creatinine clearance

We report a 66-year-old female patient who presented with acute onset of visual loss with relative afferent pupillary defect, hemineglect, hemihypesthesia, and apraxia. Magnetic resonance imaging of the brain demonstrated different stages of ischemic stroke in different vascular territories, suggesting cardiogenic embolism. Past history was significant for advanced-stage adenocarcinoma of the uterine cervix under chemoradiation treatment. On echocardiogram, vegetation at the aortic valve was observed. With the absence of evidence of infectious endocarditis, diagnosis of nonbacterial thrombotic endocarditis was made, and the patient was treated by long-term anticoagulant. This case is unique in terms of the adenocarcinoma cell type of cervical cancer, which is uncommon and has been rarely reported to be related to nonbacterial thrombotic endocarditis.

Abstract Background Acute vertigo is a common presentation of inner ear disease. However, it can also be caused by more serious conditions, especially posterior circulation stroke. Differentiating between these two conditions by clinical presentations and imaging studies during the acute phase can be challenging. This study aimed to identify serum microRNA (miRNA) candidates that could differentiate between posterior circulation stroke and peripheral vertigo, among patients presenting with acute vertigo. Methods Serum levels of six miRNAs including miR-125a-5p, miR-125b-5p, miR-143-3p, miR-342-3p, miR-376a-3p, and miR-433-5p were evaluated. Using quantitative reverse-transcription polymerase chain reaction (RT-qPCR), the serum miRNAs were assessed in the acute phase and at a 90 day follow-up visit. Results A total of 58 patients with posterior circulation stroke (n = 23) and peripheral vertigo (n = 35) were included in the study. Serum miR-125a-5p (P = 0.001), miR-125b-5p (P

Abstract Background Chulalongkorn Stroke Center is a comprehensive stroke center (CSC) located in Bangkok, Thailand. Our stroke network consists of different levels of spoke hospitals, ranging from community hospitals where thrombolytic treatment is not available, to those capable of onsite thrombolytic therapy. This study aimed to assess the time to treatment and outcomes among acute ischemic stroke patients who received thrombolytic treatment in the Chulalongkorn Stroke Network by 1.) Direct arrival at the CSC (mothership) 2.) Telestroke-assisted thrombolytic treatment with secondary transfer to the CSC (drip-and-ship) 3.) Referral from community hospital to the CSC for thrombolytic treatment (ship-and-drip). Methods Acute ischemic stroke patients who received thrombolytic treatment during January 2016–December 2017 in the Chulalongkorn Stroke Network were studied. Time to treatment and clinical outcomes were compared among treatment groups. Results There were 273 patients in the study including 147, 87, and 39 patients in mothership, drip-and-ship, and ship-and-drip paradigms, respectively. The door-to-needle-time (DTN) and onset-to-needle-time (OTN) times were significantly longest in ship-and-drip group (146.5 ± 62/205.03 ± 44.88 mins) compared to mothership (38 ± 23/155.2 ± 60.54 mins) and drip-and-ship (63.0 ± 44/166.09 ± 87 mins), P

This work studies the features of a proposed automated stroke self-screening application that utilizes the gyroscope and accelerometer devices in smartphones to determine the possible onset of a stroke by assessing arm muscle weakness. The application requires users to perform two arm movements to evaluate arm weakness and pronation: Curl-up and Raise-up. For the purpose of the study, 68 subjects, consisting of 36 stroke patients with symptoms of arm weakness and 32 healthy subjects, consented to participate. A total of 78 handcrafted features were proposed, 26 of which were extracted from Curl-up and Raise-up for each arm. Then, the differences between corresponding features for each arm were calculated. These features were then tested on 63 combinations of three classical feature selection methods, three feature sets (i.e., Curl-up-only features, Raise-up-only features, and both-exercises combined features) and seven well-known classification methods. The results from ten runs of 10-fold cross-validation showed that Curl-up-only features achieved an average sensitivity of 83.3%, significantly higher than those of the Raise-up-only features or both-exercises features. From all possible combinations, the random forest classification based on information gain feature selection from Curl-up-only features achieved the most efficient results for arm-weakness-stroke screening. It achieved an average sensitivity of 94.8%, an average specificity of 75.2%, an average accuracy of 84.1%, and an average area under the receiver operating characteristic curve of 85.0%. Our work proposes a novel accessible method to screen symptoms of arm weakness that may indicate the onset of a stroke using a single mobile device. In the future, we can combine this method with other methods of evaluating facial drooping and slurred speech to create a complete Face, Arm, Speech, Time (FAST) assessment application.

This phase 4 study evaluated the efficacy and safety of azilsartan medoxomil (AZL-M) in patients with essential hypertension and type 2 diabetes mellitus (T2DM) in Hong Kong, Taiwan, and Thailand. This was a prospective, multicenter, single-arm, open-label study with patients aged 18–75 years with T2DM and essential hypertension and on stable treatment for T2DM. Patients with uncontrolled hypertension were treated with AZL-M 40 mg daily, with the option to uptitrate to 80 mg at 6 weeks. In all, 380 of the 478 patients screened in Hong Kong, Taiwan, and Thailand were enrolled. At week 6, 97 patients (25.5%) were titrated up to AZL-M 80 mg based on BP readings. At 12 weeks, 54.8% of patients reached the blood pressure (BP) goal of

Purpose Dabigatran is a direct thrombin inhibitor approved for stroke prophylaxis in patients with non-valvular atrial fibrillation (NVAF). Real-world data about patient preference, satisfaction and convenience in patients in Asia are not available. The study aimed to explore the perception of patients with newly diagnosed NVAF regarding dabigatran versus vitamin K antagonists (VKAs), when used for stroke prevention.Patients and methods This was a multinational, multicentre, non-interventional study involving 49 sites across 5 countries in South East Asia and South Korea where 934 patients newly diagnosed with NVAF were initiated on either dabigatran (N=591) or VKA (N=343). Data were collected at baseline and over two follow-up visits across 6 months. Treatment satisfaction and patient convenience were evaluated using the Perception on Anticoagulant Treatment Questionnaire-2 (PACT-Q2).Results The mean age of the patients was 65.9±10.4 years, and 64.2% were male. Mean CHA2DS2-VASc score was 2.4±1.5, and mean HAS-BLED score was 1.2±0.9. At baseline, patients initiated on dabigatran had higher stroke risk, bleeding risk, creatinine clearance and proportion of patients with concomitant illnesses compared with patients initiated on VKAs. Treatment convenience was perceived to be significantly better with dabigatran versus VKAs at visits 2 and 3 (p=0.0423 and 0.0287, respectively). Treatment satisfaction was significantly better with dabigatran compared with VKAs at visit 3 (p=0.0300).Conclusion In this study, dabigatran is associated with better patient perception in terms of treatment convenience and satisfaction compared with VKAs when used for stroke prevention in newly diagnosed NVAF patients from South East Asia and South Korea.Trial registration number NCT02849509.Plain language summary Patient satisfaction with dabigatran versus VKAs in South East Asia. Patients with atrial fibrillation are at high risk of stroke and require anticoagulants for stroke prevention. Two such anticoagulants are dabigatran and VKAs. We wanted to compare the extent of satisfaction and treatment convenience among newly diagnosed patients with atrial fibrillation from the South East Asian region when they were given either dabigatran or VKAs. Consenting patients filled out a standardised questionnaire called the PACT-Q2 over three visits after they were started on either dabigatran (591 patients) or VKAs (343 patients). We found that satisfaction and convenience were significantly higher when patients received dabigatran than when they received VKAs.

N/a.

Background: In Thailand, almost one-quarter of strokes are related to atrial fibrillation (AF), and many could be prevented if AF were diagnosed and treated prior to the stroke. Therefore, we tested a novel strategy to screen large numbers of community residents using village health volunteers and primary care nurses. Methods: Local primary care nurses and village health volunteers in Phetchaburi and Lopburi provinces, Thailand were trained to perform AF screening using a blood pressure device with AF algorithm (Microlife A200 AFib). 10% of residents aged ≥ 65 years were randomly selected for screening during home-visits. Participants with possible AF were given follow-up appointments for further testing, including 12-lead ECG and echocardiogram. Results: Over two-months, 9.7% (13,864/143,478) of the target population were screened: mean age 73.2 ± 6.4 years, 32.4% male. The estimated AF prevalence (detected by Microlife A200 AFib) was 2.8% (95% CI, 2.6–3.1%) for age ≥ 65 years (i.e. 393/13,864 participants). Prevalence increased with age from 1.9% (65–69 years) to 5.0% (≥85 years) (p

Background and purpose Real-world data about treatment convenience and satisfaction in Asian non-valvular atrial fibrillation (NVAF) patients after switching from vitamin K antagonists (VKAs) to non-VKA oral anticoagulants were evaluated.Methods In this non-interventional study involving 49 sites across five countries in Southeast Asia and South Korea, 379 stable NVAF patients who switched from VKA therapy to dabigatran during routine clinical practice were recruited and followed up for 6 months. Treatment convenience and satisfaction were evaluated using Perception on Anticoagulant Treatment Questionnaire-2 (PACT-Q2). Through post hoc analysis, factors associated with improved treatment convenience scores at visit 2 were described.Results Treatment convenience and satisfaction significantly improved after switching from VKAs to dabigatran at visit 2 and visit 3 (convenience: p80th percentile) response on treatment convenience were female sex, younger age (

Background. Multimodal computed tomography (CT) guides decision-making regarding use of thrombolytic agents in acute ischemic stroke patients. However, postcontrast acute kidney injury (PC-AKI) is a potential adverse effect of the contrast media used, which may require hemodialysis and cause a longer hospital stay. The incidence and risk factors of PC-AKI in acute ischemic stroke patients, particularly in Thailand, remain unclear. Goal. We aimed at determining the incidence and risk factors of PC-AKI in patients with acute ischemic stroke undergoing multimodal CT. Methods. We conducted a retrospective review of Thai acute ischemic stroke patients admitted to the King Chulalongkorn Memorial Hospital between January 2014 and December 2017 who received multimodal CT and thrombolytic treatment with alteplase. Result. Overall, 109 patients were included for analysis; eight patients (7.3%) developed PC-AKI. Estimated glomerular filtration rate eGFR≤30 mL/min and mechanical thrombectomy were risk factors significantly associated with PC-AKI. Conclusion. The incidence of PC-AKI in a real practice setting did not differ from previous reports. Two factors were associated with PC-AKI, eGFR≤30 mL/min and mechanical thrombectomy. Patients without these risk factors may not need to wait for the results of renal function testing prior to multimodal CT.

Concurrent acute ischemic stroke and acute myocardial infarction is an uncommon medical emergency condition. The challenge for the physicians regarding the management of this situation is paramount since early management of one condition will inevitably delay the other. We present two illustrative cases of “hyperacute simultaneous cardiocerebral infarction” who presented with simultaneous cardiocerebral infarction and arrived at the hospital within the thrombolytic therapeutic window for acute ischemic stroke of 4.5 h. We propose an algorithm for managing the patient with hyperacute simultaneous cardiocerebral infarction based on hemodynamic status and suggest close cardiac monitoring based on the site of cerebral infarction.

People living with HIV (PLWH) have higher ischemic cerebrovascular disease rates than HIV-negative individuals. We aimed to determine the incidence and risk factors of ischemic stroke (IS) and transient ischemic attack (TIA) among Thai PLWH. Data from adults living with HIV who were enrolled in a prospective HIV-NAT 006 cohort in Bangkok, Thailand, from 1996 to 2020 were included in the analysis. The primary endpoint was first-ever IS or TIA. Among 2020 PLWH included in the analysis, 16 (0.8%) developed first-ever IS/TIA over 23,579 person-years (incidence: 0.7 per 1,000 person-years [95% confidence interval {CI} 0.4–1.1]). Median CD4 cell counts before developing IS/TIA was 480 cells/mL and 87.5% were virologically suppressed. In multivariate models, hypertension was the only factor significantly associated with IS/TIA incidence (adjusted subhazard ratio 4.4; 95% CI 1.2–15.6, p = .02). The incidence of IS/TIA was low among well-suppressed Thai PLWH. Traditional risk factors, particularly hypertension, still play an essential role in developing IS/TIA. [ABSTRACT FROM AUTHOR]