Search

The primary goal of this research is to recognize signs of brain stroke in MRI pictures. We will contrast a novel convolutional neural network that seeks to improve specificity and accuracy with K-Nearest Neighbors. Ten participants from the K-Nearest Neighbors group and ten participants from the other group were compared in this study. To determine the total sample size, power software was used with the following parameters: 0.1 enrollment ratio, 98% pre-test power, and a 95% confidence interval. A 0.05 alpha threshold was used. With 99% accuracy and 89% specificity, the suggested method performs noticeably better than the most advanced Convolutional Neural Network and the K-Nearest Neighbors algorithm. The statistical study indicated that the specificity level was p=0.045 and the accuracy level was p=0.005. When it comes to brain stroke classification, the new Convolutional Neural Network classifiers outperform K-Nearest Neighbors. [ABSTRACT FROM AUTHOR]

The purpose of this study was to compare the effectiveness of two distinct neural network architectures—a support vector machine (SVM) and a customized convolution neural network (CNN)—in brain MRI imaging and stroke scan categorization. The results showed that accuracy and precision improved when the CNN was used. In this study, two groups are compared: one using a support vector machine (N = 20) and the other a convolution neural network (N = 20). We used power software to compute the total sample size using the following parameters: 98% pre-test power, 0.05 alpha, 0.1 enrollment ratio, and 95% confidence interval. The recommended solution outperforms the alternative, according to assessments utilizing the most advanced Convolution Neural Network (98%) and Support Vector Machine (89%). After using SPSS to analyze the data, we discovered that the specificity (p = 0.010) and accuracy rate (p = 0.044) had significant statistical significance. The novel Convolution Neural Network classifier significantly outperforms Support Vector Machine classifiers in the diagnosis of brain strokes. [ABSTRACT FROM AUTHOR]

The main objective of this study is to create a unique Naive Bayes (NB) classifier that can predict ischemic strokes better than cutting-edge Support Vector Machine (SVM) techniques. Twenty Support Vector Machines (SVMs) and twenty naïve Bayes classifiers are compared in this study. The G power technique was used to calculate the total sample size, with an allocation ratio of 1 and an alpha of 0.05. While the recommended method achieves 98% success rate, the support vector machine achieves 90%. The statistical analysis indicated that the specificity p-value was 0.010 and the accuracy p-value was 0.042. When it comes to brain stroke identification, the novel Naive Bayes classifier performs better than support vector machine classifiers. [ABSTRACT FROM AUTHOR]

Health is paramount in achieving overall well-being and happiness. Detecting strokes at their earliest stages is crucial for limiting brain damage and minimizing long-term consequences. Medical imaging, particularly in the form of Magnetic Resonance Imaging (MRI) technology, has emerged as a powerful tool in the field of healthcare. However, manually identifying and locating ischemic strokes in MRI images can be time-consuming and challenging. This research aims to develop a machine learning-based approach for the automatic detection of strokes including ischemic strokes, utilizing cutting-edge methods for identification and classification. The proposed methodology consists of six key stages that collectively form a comprehensive procedure. To enhance the quality of MRI images, Gabor filters are employed following preprocessing based on functional criteria. Additionally, an image enhancement technique known as adaptive histogram equalization (AHE) is implemented. For the prediction of strokes, Convolutional Neural Networks (CNNs) are employed. Experimental results demonstrate that the developed model achieves an accuracy above 90%. The approach showcased in this research is both simple and effective, offering a productive solution for the early detection of ischemic strokes. By leveraging the power of machine learning and advanced imaging techniques, this research paves the way for improved stroke diagnosis and timely intervention, leading to enhanced patient outcomes and quality of life. [ABSTRACT FROM AUTHOR]

The incidence of adult stroke patients, particularly in ischemic stroke, is predicted to increase significantly. A stroke can cause various complications such as disability or weakness in one or more body parts. Permanent disability in post-stroke patients greatly affects their quality of life, which is particularly pertinent in adult patients given its impact on productivity and self-esteem. This study aims to determine the quality of life in adult stroke patients. A phenomenological design was adopted, and participants were selected using purposive sampling. The data collection process was conducted through semi-structured interviews and was analyzed with Colaizzi by organizing and reading the transcripts to identify significant data and generate themes. This study identified 5 themes from 10 sub-themes and 15 categories, including the decrease in independence, self-confidence, and social interaction that affects the quality of life, inadequate quality of the home environment, and increase in spiritual approach during illness. These themes affect the quality of life in adult post-stroke patients. Exists decreased quality of life in the physical domain, the psychological domain, the social domain, and the environmental domain but there was an increase in the spiritual domain [ABSTRACT FROM AUTHOR]

The goals of this research were to describe the profile of cognitive abilities in stroke patients, compare their performance in speeded vs non-speeded tests, estimate the prevalence of cognitive impairment after stroke, and analyze the differences between left- and right-sided stroke patients. This retrospective study involved 51 patients with first-ever ischemic stroke. The patients underwent neuropsychological examination 3 months after the incident stroke. The control group consisted of 30 volunteers with no history of neurological disorder. Thirty (59%) stroke patients were identified as cognitively impaired. The greatest differences between stroke patients and the control group were observed in speeded and memory tests (p <.001). Left-sided stroke patients perform significantly better in nonverbal than verbal tests (p <.001), but right-sided stroke patients did not perform significantly better in verbal than nonverbal tests. However, stroke laterality did not significantly affect general cognitive performance (p =.315). In conclusion, the prevalence of cognitive impairment in patients with first-ever ischemic stroke is high. Stroke patients perform worse mainly in time-sensitive tasks. Stroke laterality does not appear to affect the general cognitive performance. Left-sided stroke patients perform better in nonverbal than verbal tests, but the difference between both test types is negligible in right-sided stroke patients The entire paper is a professional proof of the principle of work in the Eddie project, where patients are rehabilitated more efficiently and accurately according to the CHC model, even if only the result of a simple screening test was analyzed. [ABSTRACT FROM AUTHOR]

Stroke is a disease or functional disorder of the brain due to blockage (ischemic stroke) or bleeding (hemorrhagic stroke) which can cause death and disability of the sufferer. The prevalence of stroke in Indonesia is still relatively high. As a result, we need a preventive action through early detection by understanding the risk factors that can affect the incidence of stroke in Indonesian society. This study aims to identify the most important risk factors for stroke patients in Indonesia between the ages of 41 and 60 years. This study drew on secondary data from the Rand Corporation website, specifically the fifth wave of the Indonesian Family Life Survey (IFLS-5) conducted in 2014-2015. Multilevel logistic regression model is used to model one binary response variable with one or more independent variables for data having a hierarchical structure. A multilevel logistic regression analysis is used to explain the relationship between stroke case (yes/no) and variables of age, sex, activity, hypertension, diabetes, and average age per province. The multilevel logistic regression modeling results revealed that age (p<0.0001), light activity (p = 0.01), moderate activity (p = 0.02), hypertension (p<0.0001), and diabetes (p = 0.01) were significantly associated in level 1 and the average age per province (p = 0.02). [ABSTRACT FROM AUTHOR]

A stroke occurs when a blood clot or bleeding in the brain leads to potential permanent damage in areas such as mobility, cognition, vision, or speech. Strokes are considered medical emergencies and can result in long-term neurological impairments or, in severe cases, death. The majority of strokes can be categorized as either ischemic embolic or hemorrhagic. Ischemic embolic strokes occur when a blood clot forms in another part of the body, often the heart, and travels through the bloodstream to block narrower arteries in the brain. A hemorrhagic stroke refers to a type of brain stroke characterized by the leakage or rupture of a blood vessel in the brain. Stroke affects a significant portion of individuals aged 65 and above and is the second leading cause of death globally. It can result in heart damage, often referred to as a "heart attack." Strokes incur substantial medical expenses, can cause long-term disabilities, and in some cases, may lead to fatalities. Approximately one stroke is fatal every four minutes; 80% of strokes can be lessened if there is early detection of stroke or prediction of its occurrence. The results show that all the algorithms have a considerably high level of stroke prediction accuracy. The AdaBoost has the highest accuracy score of 93.7%, the random forest has the second-highest accuracy score of 91.8%, and the logistic regression has the third-highest accuracy score of 89.9%, while the decision tree has the lowest accuracy score of 89.5%. [ABSTRACT FROM AUTHOR]

Stroke is a disease among the top 10 causes of death in the world and Indonesia. Stroke is divided into two, namely ischemic stroke and hemorrhagic stroke. Stroke can happen to anyone at any age with the characteristics of blood vessels experiencing blockage or rupture resulting in a crisis of blood supply that carries oxygen to the brain. The risk factors for stroke are the same as heart disease or other blood vessel diseases such as hypertension, diabetes, and cholesterol. One way to prevent stroke is to minimize several diseases that cause clogged or ruptured blood vessels. This study aims to predict the results of the classification of stroke types based on 6 factors, namely age, gender, cholesterol levels, length of stay (LOS), history, and blood sugar levels of stroke patients. The classification method chosen is one part of machine learning, namely the resilient backpropagation neural network (RBNN) because it is in accordance with the type of data used. The results showed that the prediction results of stroke type classification using six predictors were included in the good category and reached the optimum at the use of 5 nodes in the hidden layer and the resulting error was 9.26. The results of the evaluation of classification predictions using the confusion matrix also get good results, namely with an accuracy of 80% and an F1-score of 82% with a precision of 72% and a sensitivity of 95%. This result will be more optimal if there is the handling of imbalanced data. [ABSTRACT FROM AUTHOR]

Ischemic stroke can happen from insufficiency of blood flow to the brain tissue due to the presence of thrombus in the blood vessel which obstruct blood flow to the brain. If left untreated, this condition can lead to necrosis of the brain tissue and stroke. Medical practitioners have been using non-contrast computed tomography (NECT) as an early diagnostic tool in visualizing patients' brain to identify ischemia. However, ischemic stroke from NECT sometimes is only slightly visible and can be very hard to perceive. Not only that, NECT may produce artifacts from the beam radiation and can affect the radiologists' perception when looking at the images. Although Magnetic Resonance Imaging (MRI) is a much more preferable tool when detecting ischemic stroke, it can be hard to come by at necessary time in addition to being a complicated process. Recent studies have shown multiple technique that can be utilized to help medical practitioners diagnose ischemic stroke from NECT images with the aid of medical imaging and deep learning (DL) to overcome the limitations of NECT. One of the most common way DL can be used to assist in medical field is telling apart ischemic from non-ischemic by mean of classification. This paper compares three networks; DarkNet-19, DarkNet-53 and ResNet-50 and assess the performance and processing time of each network. ResNet-50 is empirically proven to be the best with 100% validation frequency and short training period with 1.7286 second per image apart from yielding accuracy, precision and sensitivity of 92.5%, 95% and 0.9048 respectively. [ABSTRACT FROM AUTHOR]

A stroke is defined as a sudden interruption of the brain's blood supply; the leading cause for almost 80% of all strokes is ischemic stroke, where there is a clot or an abrupt blockage within an artery leading to the brain. The increase in the number of stroke patients per year and the available robotic rehabilitation device (RRD) being too expensive have exposed the need to develop an affordable RRD. Three different conceptual designs were developed, and the final design of the RRD was selected using the Pugh evaluation matrix. Load analysis was performed on the SolidWorks model of the RRD to ensure that the design and materials selected would not fail when subjected to expected loads. The RRD uses an Arduino as the microcontroller, and actuation of the motor will provide the therapy movements of the arm links. The fabricated prototype of the RRD was evaluated in a survey and has been determined to accomplish all the project's objectives. [ABSTRACT FROM AUTHOR]

Ischemic stroke is one of the two main forms of cerebrovascular accident that ranks the second highest leading killer worldwide. An attack of ischemic stroke would lead to rapid death of neurons accompanied with inflammatory events in the brain, causing acquired disabilities for the survivors. Yet better drugs for ischemic stroke treatment are still in great need. In this literature review, three major compounds are mentioned and concluded that 6-shogaol, 6-paradol, and zingerone have neuroprotective potential and discussed the possibility to make them promising drugs for ischemic stroke treatment. [ABSTRACT FROM AUTHOR]

The percentage of stroke deaths attributable to low temperature was 7.23% in 2019, accounting for 474,002 stroke deaths globally, while about 48,030 of the stroke deaths were attributed to high temperature. Joinpoint regression analysis was applied to calculate the average annual percent change (AAPC) with 95% confidence interval (CI) to evaluate stroke mortality trends in 1990–2019. Trends from global stroke mortality attributed to low temperature significantly declined (AAPC = −2.5%; 95%CI = −2.6 to −2.3) in both sexes together. A significantly increased trend for stroke mortality attributed to high temperature was observed in both sexes together (AAPC = +1.0%; 95%CI = 0.6 to 1.3). [ABSTRACT FROM AUTHOR]

The current paper focuses on correlating the region of ischemic stroke based on CT-scan and EEG image visualization, approaching using Brainstorm and BSI on each pair. Ischemic stroke occurs when the flow of blood containing oxygen and supplements to the brain is blocked, causing the body to break down. In arrange to identify stroke, we generally use CT and MRI, which have succeeded in determining the location with high accuracy. The factor is the high price of CT-scan or MRI, so we want to find another alternative with a low-cost and practical approach to using EEG. The most recent research on EEG in detecting stroke uses a signal processing approach based on time series and frequency to obtain abnormalities from the signal graph with the initial suspicion of blockage of blood vessels within the brain. Research is related to finding indications of stroke by using the brain symmetry index, which is to find the symmetry value of the relationship between the two-sided electrode locations. This study uses a signal processing approach to become an image with the help of the Brainstorm toolbox software released by the University of Southern California. The data used came from patients who experienced stroke symptoms with fewer than 72 hours. The current inquires about the investigation is based on recognizing the electrical current density in a data grouping based on the region of interest on the cortical surface in ischemic stroke conditions. All the patients were examined for ischemic stroke based on CT, which experts analyzed from the National Brain Center Hospital. Data processing is done by calculating the Brain Symmetry Index (BMI) and visualizing the data with Brainstorm on each EEG data. These results explain a correlation between expert CT-scan diagnoses to BMI values and are supported by data visualization using Brainstorm. [ABSTRACT FROM AUTHOR]

Stroke is one of the most leading causes of death and disability in the world as well as in Indonesia. Almost 85% of stroke patients suffer from Acute Ischemic Stroke (AIS). They need to be early diagnosed to improve stroke treatment. The most common tools that have been widely used in diagnosing strokes are Computed Tomography Scans (CT Scans) and Magnetic Resonance Imaging (MRI). Electroencephalography (EEG) analysis has been widely studied in identifying stroke disease due to its relatively low cost and non-invasive characteristics. The study is aimed to classify the severity of AIS patients using EEG signals into four classes: normal, minor, moderate, and severe. This study was conducted in Rumah Sakit Pusat Otak Nasional (RSPON, National Brain Center Hospital), Jakarta, and acquired 32-channel EEG data recordings, CT-Scan images, and NIHSS scores. The total subject participated in this study was 57 subjects: 35 male subjects and 22 female subjects with age ranges 40 – 60 years old. Shannon Entropy (SE), and Log Energy feature-based EEG from alpha, beta, theta, delta, and gamma sub-bands were extracted and evaluated as the EEG signals are complex, non-stationary, and non-linear. These features were combined with Delta to Alpha Ratio (DAR) and Delta Theta to Alpha Beta Ratio (DTABR) that were extracted using wavelet decomposition. All of these features were proceeded using three different classifiers: k-Nearest Neighbors, Decision Tree, and Naïve Bayes classifier to compare their performances. Besides classifiers, we also used three different sets of features: All features; Shannon Entropy; Log Energy; Shannon Entropy, and Log Energy features as training inputs. The highest accuracy was yielded by Decision Tree using Shannon Entropy feature, which yields 83% accuracy. This system would be expected to be used widely in type-C hospitals in Indonesia. [ABSTRACT FROM AUTHOR]

Most of the recent study about deep learning in medical images have revolved the ability of deep learning models to interpretation of diagnostic result and anatomical recognition. However, deep learning can also be used to enhance a wide range of non-interpretive issues such as image enhancement that relevant to radiologists and patients. For ischemic stroke, a noncontrast cranial computer tomography (NCCT) is imaging technique used for diagnosis. The cerebral infarction in early stage on NCCT is difficult to notice because of limitation of image. Normally, the patients need to do a computer tomography perfusion (CTp) for identification the damage, but it takes time while the patients should be received the treatment quickly. Another problem about NCCT image, the range of intensity is very wide and sparse. It is needed to rescale in the suitable range for the classifier. In this paper, we aim to find the suitable window setting for classifying the Hyperacute and Acute phase of ischemic stroke in NCCT image without CTp by using Inception V3. The dataset is prepared in axial slices. Each slide is classified to either normal or lesion. Due to limitation of the training samples availability, transfer learning is applied for weight initialization of the model. The result indicates that the model can perform well with window level at 35 and window width at 95, 90.84% accuracy. [ABSTRACT FROM AUTHOR]

Most of the recent study about deep learning in medical images have revolved the ability of deep learning models to interpretation of diagnostic result and anatomical recognition. However, deep learning can also be used to enhance a wide range of non-interpretive issues such as image enhancement that relevant to radiologists and patients. For ischemic stroke, a noncontrast cranial computer tomography (NCCT) is imaging technique used for diagnosis. The cerebral infarction in early stage on NCCT is difficult to notice because of limitation of image. Normally, the patients need to do a computer tomography perfusion (CTp) for identification the damage, but it takes time while the patients should be received the treatment quickly. Another problem about NCCT image, the range of intensity is very wide and sparse. It is needed to rescale in the suitable range for the classifier. In this paper, we aim to find the suitable window setting for classifying the Hyperacute and Acute phase of ischemic stroke in NCCT image without CTp by using Inception V3. The dataset is prepared in axial slices. Each slide is classified to either normal or lesion. Due to limitation of the training samples availability, transfer learning is applied for weight initialization of the model. The result indicates that the model can perform well with window level at 35 and window width at 95, 90.84% accuracy. [ABSTRACT FROM AUTHOR]

Cerebrovascular accident (CVA) or stroke is a condition where the blood flow to the brain is impaired, which can be caused by a blockage (ischemic stroke) or rupture of blood vessels (hemorrhagic stroke), resulting in cell death in some brain areas. Stroke can cause significant impairment in motoric, cognitive, and coordination skills of limbs and muscles. One of the non-invasive stimuli that can be applied in post-stroke patient rehabilitation is Transcranial Direct Current Stimulation (TDCS), aiming to improve the frequency spectrum towards normal. This study aimed to find the Quantitative Electroenchepalograph (QEEG) parameters that characterize the improvement of post-stroke patients' brain signals after the administration of TDCS. QEEG parameters included absolute power, relative power, ratio power Delta Theta Alpha Beta (DTAB), Delta Alpha (DA), and the percentage of each frequency wave band in the brain. EEG signals were recorded for 5 minutes before and after TDCS administration from 23 subjects, consisted of 12 post-stroke patients and 11 healthy subjects as a control. The result showed that there were significant differences in QEEG parameters before and after TDCS administration to both post-stroke patients and healthy subjects. The alpha frequency was dominant for healthy subjects, with the average of 25.67% before stimulus then increased by 1.91% after the stimulus. For post-stroke patients, delta frequency before the stimulus was dominant, with an average percentage of 43.03% then decreased by 10.44% after the stimulus. These results show that with TDCS, there is a change in the EEG wave pattern in post-stroke patients, which followed the profile pattern of healthy subjects. [ABSTRACT FROM AUTHOR]

This study conducted cost utility analysis comparing 4 systems of transporting acute ischemic stroke patients in Hokkaido, Japan. Hypothetical patients were generated on a geographic information system, and their outcomes were estimated according to their transport time to hospitals administering tissue plasminogen activator and/or endovascular thrombectomy. The transport systems where a neurointerventionist traveled for earlier endovascular thrombectomy were most cost-effective in some rural areas, while direct transportation to comprehensive stroke centers was more cost-effective in other areas. [ABSTRACT FROM AUTHOR]

Copyright of Proceedings of the International Scientific Conference of Daugavpils University / Daugavpils Universitates Starptautiskas Zinatniskas Konferences Materiali is the property of Daugavpils University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The aim of this paper was to investigate the importance of age and the presence of atherosclerotic lesions in the onset of stroke in patients with stroke-like symptomatology. We evaluated 159 patients in our department for atherosclerotic disease. Patients with other causes of stroke, like cardio embolism, dissections, vasculopathy, neoplasia and stroke of undetermined source were excluded from the study. Duplex carotid ultrasonography was performed and a computer tomography of the brain for all the patients included in the study. The results of the study show that there is no statistically significant difference between patients diagnosed with stroke and stroke free patients according to age and number of plaques at common carotid artery. Higher number of plaques at carotidal bulb level and external or internal carotid artery associates with a higher risk of stroke. As a conclusion, in practice, for the symptomatology of the patients with stroke the presence of atherosclerosis and the number of plaques at bulbar and external and internal carotid artery can be used to assess the risk of stroke and that the age should not be use as a criterion. [ABSTRACT FROM AUTHOR]

There are numerous ways to prevent or treat ischemic stroke and each of these competing alternatives is associated with a different effectiveness and a cost. In circumstances where health funds are budgeted and thus fixed, cost-effectiveness analysis (CEA) can provide information on how to comprehend the largest health gains with that limited fund as CEA is used to compare different strategies for preventing or treating a single disease. The most common medications for ischemic stroke are the anti-platelet drugs. While some drugs are more effective than others, they are also more expensive. This paper will thus assess the CEA of anti-platelet drug available for ischemic stroke patients using goal programming (GP) approach subject to inpatients days and patients' quality-of-life. GP presents a way of striving towards several objectives simultaneously whereby in this case we will consider minimizing the cost and maximizing the effectiveness. [ABSTRACT FROM AUTHOR]

The objective of this research is to specify Ischemic Stroke Area by using Digital Image Processing principle to analyze Computed Tomography Perfusion (CTP) images from CBV (Cerebral Blood Volume) and CBF (Cerebral Blood Flow) images with 5 stroke patient samples. By assigning Threshold level of CBV to less than 2.5 ml/100g and Threshold level of CBF to less than 20ml/100g/min. Our experimental results will be shown in N-Match (normal tissue areas), D-Match (dead tissue areas), Mismatch (blood clot tissue areas) and Undefined area. Then, separate the brain into left and right to compare distribution of Mismatch and D-Match information in order to specify Ischemic Stroke Area. As a result of experiment, it is possible to sort elementary information of left and right side of the brain to specify Ischemic Stroke Area to compare the results with brain specialists. [ABSTRACT FROM PUBLISHER]

The objective of this research is to specify Ischemic Stroke Area by using statistical methods and probability to divide image data into 2 areas, normal and abnormal areas of the brain, in order to automatically assign the Threshold level of Computed Tomography Perfusion (CTP) images from CBV (Cerebral Blood Volume) and CBF (Cerebral Blood Flow) images and apply to Digital Image Processing to analyze data images. The results will be shown in N-Match (normal tissue areas), D-Match (dead tissue areas), Mismatch (blood clot tissue areas) and Undefined area. Then, separate the brain into left and right to specify Ischemic Stroke Area. From experiments with 5 patient samples with 256×256 pixels images, N-Match, D-Match, Mismatch and Undefined values depend on Threshold value gathered from the difference of Mean and Standard Deviation values of CBV and CBF images. As a result of experiment, it is possible to sort elementary information of left and right side of the brain to specify Ischemic Stroke Area to compare the results with brain specialists. [ABSTRACT FROM PUBLISHER]

Regional disparities in the implementation rates of recombinant tissue-type plasminogen activator and endovascular thrombectomy treatments have been reported in Japan. We simulated the cost-effectiveness of specialist dispatching system in Hokkaido, Japan using Geographic Information System. In the system a qualified specialist is dispatched to another hospital for endovascular thrombectomy. Since the system improved patient accessibility, and the cost-effectiveness was excellent, the system could help enhance the equality and cost-effectiveness of ischemic stroke treatments in Hokkaido. [ABSTRACT FROM AUTHOR]