Predicting the clinical prognosis of acute ischemic stroke using machine learning: an application of radiomic biomarkers on non-contrast CT after intravascular interventional treatment.

Purpose: This study aimed to develop a radiomic model based on non-contrast computed tomography (NCCT) after interventional treatment to predict the clinical prognosis of acute ischemic stroke (AIS) with large vessel occlusion. Methods: We retrospectively collected 141 cases of AIS from 2016 to 2020 and analyzed the patients' clinical data as well as NCCT data after interventional treatment. Then, the total dataset was divided into training and testing sets according to the subject serial number. The cerebral hemispheres on the infarct side were segmented for radiomics signature extraction. After radiomics signatures were standardized and dimensionality reduced, the training set was used to construct a radiomics model using machine learning. The testing set was then used to validate the prediction model, which was evaluated based on discrimination, calibration, and clinical utility. Finally, a joint model was constructed by incorporating the radiomics signatures and clinical data. Results: The AUCs of the joint model, radiomics signature, NIHSS score, and hypertension were 0.900, 0.863, 0.727, and 0.591, respectively, in the training set. In the testing set, the AUCs of the joint model, radiomics signature, NIHSS score, and hypertension were 0.885, 0.840, 0.721, and 0.590, respectively. Conclusion: Our results provided evidence that using post-interventional NCCT for a radiomic model could be a valuable tool in predicting the clinical prognosis of AIS with large vessel occlusion.

Novel metabolic biomarkers for the diagnosis of acute ischemic stroke.

Aim: To identify novel metabolic biomarkers for patients with acute ischemic stroke (AIS).Methods: The metabolites in the sera of 63 patients with AIS aged 45∼77 years and 60 healthy individuals were analyzed by liquid chromatography (LC)-mass spectrometry (MS)/MS. The efficiency of significantly altered metabolites as biomarkers of AIS was evaluated by ROC curve analysis.Results: Different metabolic profiles were revealed in AIS patients' sera compared with healthy persons. Twelve significantly altered metabolites had an area under the curve (AUC) value >0.80, demonstrating their potential as a biomarker of AIS. Among them, six metabolites are firstly reported to distinguish between AIS patients and healthy individuals.Conclusion: These 12 metabolites can be further researched as potential diagnostic biomarkers of AIS.

In this study, the serum metabolome of patients with AIS aged 45­77 years were analyzed and the potential biomarkers for AIS diagnosis were identified. Twelve serum compounds were found to be significantly altered and have the ability to distinguish patients with AIS and healthy individuals effectively. Among them, six metabolites were firstly reported to have the potential as biomarkers for AIS diagnosis. These results will contribute to biomarker explorations from blood metabolites to predict AIS in patients from different age groups.

AC-ASPECTS, ACh-ASPECTS, and H-ASPECTS: new imaging scales to assess territorial and total cerebral hemispheric ischemic injury.

Background: The extent of ischemic injury in acute stroke is assessed in clinical practice using the Acute Stroke Prognosis Early CT Score (ASPECTS) rating system. However, current ASPECTS semi-quantitative topographic scales assess only the middle cerebral artery (MCA) (original ASPECTS) and posterior cerebral (PC-ASPECTS) territories. For treatment decision-making in patients with anterior cerebral artery (ACA) occlusions and internal carotid artery (ICA) occlusions with large ischemic cores, measures of all hemispheric regions are desirable. Methods: In this cohort study, anatomic rating systems were developed for the anterior cerebral (AC-ASPECTS, 3 points) and anterior choroidal artery (ACh-ASPECTS, 1 point) territories. In addition, a total supratentorial hemisphere (H-ASPECTS, 16 points) score was calculated as the sum of the MCA ASPECTS (10 regions), supratentorial PC-ASPECTS (2 regions), AC-ASPECTS (3 regions), and ACh-ASPECTS (1 region). Three raters applied these scales to initial and 24 h CT and MR images in consecutive patients with ischemic stroke (IS) due to ICA, M1-MCA, and ACA occlusions. Results: Imaging ratings were obtained for 96 scans in 50 consecutive patients with age 74.8 (±14.0), 60% female, NIHSS 15.5 (9.25-20), and occlusion locations ICA 34%; M1-MCA 58%; and ACA 8%. Treatments included endovascular thrombectomy +/- thrombolysis in 72%, thrombolysis alone in 8%, and hemicraniectomy in 4%. Among experienced clinicians, inter-rater reliability for AC-, ACh-, and H-ASPECTS scores was substantial (kappa values 0.61-0.80). AC-ASPECTS abnormality was present in 14% of patients, and ACh-ASPECTS abnormality in 2%. Among patients with ACA and ICA occlusions, H-ASPECTS scores compared with original ASPECTS scores were more strongly associated with disability level at discharge, ambulatory status at discharge, discharge destination, and combined inpatient mortality and hospice discharge. Conclusion: AC-ASPECTS, ACh-ASPECTS, and H-ASPECTS expand the scope of acute IS imaging scores and increase correlation with functional outcomes. This additional information may enhance prognostication and decision-making, including endovascular thrombectomy and hemicraniectomy.

Review of Microwave Near-Field Sensing and Imaging Devices in Medical Applications.

Microwaves can safely and non-destructively illuminate and penetrate dielectric materials, making them an attractive solution for various medical tasks, including detection, diagnosis, classification, and monitoring. Their inherent electromagnetic properties, portability, cost-effectiveness, and the growth in computing capabilities have encouraged the development of numerous microwave sensing and imaging systems in the medical field, with the potential to complement or even replace current gold-standard methods. This review aims to provide a comprehensive update on the latest advances in medical applications of microwaves, particularly focusing on the near-field ones working within the 1-15 GHz frequency range. It specifically examines significant strides in the development of clinical devices for brain stroke diagnosis and classification, breast cancer screening, and continuous blood glucose monitoring. The technical implementation and algorithmic aspects of prototypes and devices are discussed in detail, including the transceiver systems, radiating elements (such as antennas and sensors), and the imaging algorithms. Additionally, it provides an overview of other promising cutting-edge microwave medical applications, such as knee injuries and colon polyps detection, torso scanning and image-based monitoring of thermal therapy intervention. Finally, the review discusses the challenges of achieving clinical engagement with microwave-based technologies and explores future perspectives.

Utilizing machine learning to facilitate the early diagnosis of posterior circulation stroke.

BACKGROUND: Posterior Circulation Syndrome (PCS) presents a diagnostic challenge characterized by its variable and nonspecific symptoms. Timely and accurate diagnosis is crucial for improving patient outcomes. This study aims to enhance the early diagnosis of PCS by employing clinical and demographic data and machine learning. This approach targets a significant research gap in the field of stroke diagnosis and management. METHODS: We collected and analyzed data from a large national Stroke Registry spanning from January 2014 to July 2022. The dataset included 15,859 adult patients admitted with a primary diagnosis of stroke. Five machine learning models were trained: XGBoost, Random Forest, Support Vector Machine, Classification and Regression Trees, and Logistic Regression. Multiple performance metrics, such as accuracy, precision, recall, F1-score, AUC, Matthew's correlation coefficient, log loss, and Brier score, were utilized to evaluate model performance. RESULTS: The XGBoost model emerged as the top performer with an AUC of 0.81, accuracy of 0.79, precision of 0.5, recall of 0.62, and F1-score of 0.55. SHAP (SHapley Additive exPlanations) analysis identified key variables associated with PCS, including Body Mass Index, Random Blood Sugar, ataxia, dysarthria, and diastolic blood pressure and body temperature. These variables played a significant role in facilitating the early diagnosis of PCS, emphasizing their diagnostic value. CONCLUSION: This study pioneers the use of clinical data and machine learning models to facilitate the early diagnosis of PCS, filling a crucial gap in stroke research. Using simple clinical metrics such as BMI, RBS, ataxia, dysarthria, DBP, and body temperature will help clinicians diagnose PCS early. Despite limitations, such as data biases and regional specificity, our research contributes to advancing PCS understanding, potentially enhancing clinical decision-making and patient outcomes early in the patient's clinical journey. Further investigations are warranted to elucidate the underlying physiological mechanisms and validate these findings in broader populations and healthcare settings.

Association between depression and stroke risk in adults: a systematic review and meta-analysis.

Introduction: Stroke is a significant global health concern, and numerous studies have established a link between depression and an increased risk of stroke. While many investigations explore this link, some overlook its long-term effects. Depression may elevate stroke risk through physiological pathways involving nervous system changes and inflammation. This systematic review and meta-analysis aimed to assess the association between depression and stroke. Methodology: We conducted a comprehensive search of electronic databases (PubMed, Embase, Scopus, and PsycINFO) from inception to 9 April 2023, following the Preferred Reporting Items for Systemic Review and Meta-analysis (PRISMA) and Meta-analysis Of Observational Studies in Epidemiology (MOOSE) guidelines. We included all articles assessing the association between different stroke types and depression, excluding post-stroke depression. Two investigators independently extracted data and assessed quality using the Newcastle-Ottawa Scale and Cochrane Risk of Bias tool, utilizing a random-effects model for data synthesis. The primary outcome was the association of depression with stroke, with a secondary focus on the association of antidepressants with stroke. Results: The initial search yielded 10,091 articles, and 44 studies were included in the meta-analysis. The pooled analysis revealed a significant association between depression and stroke risk, with an overall hazard ratio of 1.41 (95% CI 1.32, 1.50; p < 0.00001), indicating a moderately positive effect size. Subgroup analyses showed consistent associations with ischemic stroke (HR = 1.30, 95% CI 1.13, 1.50; p = 0.007), fatal stroke (HR = 1.39, 95% CI 1.24, 1.55; p < 0.000001), and hemorrhagic stroke (HR = 1.33, 95% CI 1.01, 1.76; p = 0.04). The use of antidepressants was associated with an elevated risk of stroke (HR = 1.28, 95% CI 1.05, 1.55; p = 0.01). Conclusion and relevance: This meta-analysis indicates that depression moderately raises the risk of stroke. Given the severe consequences of stroke in individuals with depression, early detection and intervention should be prioritized to prevent it. Systematic review registration: Prospero (CRD42023472136).

Advances in the diagnosis and management of acute vertigo.

BACKGROUND: Patients presenting to the emergency department with acute vertigo pose a diagnostic challenge. While 'benign' peripheral vestibulopathy is the most common cause, the possibility of a posterior circulation stroke is paradoxically the most feared and missed diagnosis in the emergency department. OBJECTIVES: This review will attempt to cover the significant advances in the ability to diagnose acute vertigo that have occurred in the last two decades. The review discusses the role of neurological examinations, imaging and specific oculomotor examinations. The review then discusses the relative attributes of the Head Impulse-Nystagmus-Test of Skew plus hearing ('HINTS+') examination, the timing, triggers and targeted bedside eye examinations ('TiTrATE'), the associated symptoms, timing and triggers, examination signs and testing ('ATTEST') algorithm, and the spontaneous nystagmus, direction, head impulse testing and standing ('STANDING') algorithm. The most recent technological advancements in video-oculography guided care are discussed, as well as other potential advances for clinicians to look out for.

Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis.

Background: Artificial intelligence-derived software technologies have been developed that are intended to facilitate the review of computed tomography brain scans in patients with suspected stroke. Objectives: To evaluate the clinical and cost-effectiveness of using artificial intelligence-derived software to support review of computed tomography brain scans in acute stroke in the National Health Service setting. Methods: Twenty-five databases were searched to July 2021. The review process included measures to minimise error and bias. Results were summarised by research question, artificial intelligence-derived software technology and study type. The health economic analysis focused on the addition of artificial intelligence-derived software-assisted review of computed tomography angiography brain scans for guiding mechanical thrombectomy treatment decisions for people with an ischaemic stroke. The de novo model (developed in R Shiny, R Foundation for Statistical Computing, Vienna, Austria) consisted of a decision tree (short-term) and a state transition model (long-term) to calculate the mean expected costs and quality-adjusted life-years for people with ischaemic stroke and suspected large-vessel occlusion comparing artificial intelligence-derived software-assisted review to usual care. Results: A total of 22 studies (30 publications) were included in the review; 18/22 studies concerned artificial intelligence-derived software for the interpretation of computed tomography angiography to detect large-vessel occlusion. No study evaluated an artificial intelligence-derived software technology used as specified in the inclusion criteria for this assessment. For artificial intelligence-derived software technology alone, sensitivity and specificity estimates for proximal anterior circulation large-vessel occlusion were 95.4% (95% confidence interval 92.7% to 97.1%) and 79.4% (95% confidence interval 75.8% to 82.6%) for Rapid (iSchemaView, Menlo Park, CA, USA) computed tomography angiography, 91.2% (95% confidence interval 77.0% to 97.0%) and 85.0 (95% confidence interval 64.0% to 94.8%) for Viz LVO (Viz.ai, Inc., San Fransisco, VA, USA) large-vessel occlusion, 83.8% (95% confidence interval 77.3% to 88.7%) and 95.7% (95% confidence interval 91.0% to 98.0%) for Brainomix (Brainomix Ltd, Oxford, UK) e-computed tomography angiography and 98.1% (95% confidence interval 94.5% to 99.3%) and 98.2% (95% confidence interval 95.5% to 99.3%) for Avicenna CINA (Avicenna AI, La Ciotat, France) large-vessel occlusion, based on one study each. These studies were not considered appropriate to inform cost-effectiveness modelling but formed the basis by which the accuracy of artificial intelligence plus human reader could be elicited by expert opinion. Probabilistic analyses based on the expert elicitation to inform the sensitivity of the diagnostic pathway indicated that the addition of artificial intelligence to detect large-vessel occlusion is potentially more effective (quality-adjusted life-year gain of 0.003), more costly (increased costs of £8.61) and cost-effective for willingness-to-pay thresholds of £3380 per quality-adjusted life-year and higher. Limitations and conclusions: The available evidence is not suitable to determine the clinical effectiveness of using artificial intelligence-derived software to support the review of computed tomography brain scans in acute stroke. The economic analyses did not provide evidence to prefer the artificial intelligence-derived software strategy over current clinical practice. However, results indicated that if the addition of artificial intelligence-derived software-assisted review for guiding mechanical thrombectomy treatment decisions increased the sensitivity of the diagnostic pathway (i.e. reduced the proportion of undetected large-vessel occlusions), this may be considered cost-effective. Future work: Large, preferably multicentre, studies are needed (for all artificial intelligence-derived software technologies) that evaluate these technologies as they would be implemented in clinical practice. Study registration: This study is registered as PROSPERO CRD42021269609. Funding: This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR133836) and is published in full in Health Technology Assessment; Vol. 28, No. 11. See the NIHR Funding and Awards website for further award information.

Stroke is a serious life-threatening medical condition caused by a blood clot or haemorrhage in the brain. Quick and effective management, including a brain scan, of the patients with suspected stroke can make a big difference in their outcome. Artificial intelligence-derived computer programmes exist that are intended to help with the interpretation of computed tomography scans of the brain in stroke. We undertook a thorough review of the existing research into the effectiveness and value for money of using these programmes to help doctors and other specialists to interpret computed tomography brain scans. We found very little evidence to tell us how well artificial intelligence-derived computer programmes work in practice. Some studies have looked at artificial intelligence-derived computer programmes on their own (i.e. not taken together with a doctor's judgement, as they were designed to be used). Other studies have looked at what happens to patients who are treated for stroke when artificial intelligence-derived computer programmes are used; these studies provide no information about whether using artificial intelligence-derived computer programmes may have led to patients who could have benefitted from treatment being missed. It is unclear how well artificial intelligence-derived software-assisted review works when added to current clinical practice.

Analysis of electrode arrangements for brain stroke diagnosis via electrical impedance tomography through numerical computational models.

Objective.Rapid stroke-type classification is crucial for improved prognosis. However, current methods for classification are time-consuming, require expensive equipment, and can only be used in the hospital. One method that has demonstrated promise in a rapid, low-cost, non-invasive approach to stroke diagnosis is electrical impedance tomography (EIT). While EIT for stroke diagnosis has been the topic of several studies in recent years, to date, the impact of electrode placements and arrangements has rarely been analyzed or tested and only in limited scenarios. Optimizing the location and choice of electrodes can have the potential to improve performance and reduce hardware cost and complexity and, most importantly, diagnosis time.Approach.In this study, we analyzed the impact of electrodes in realistic numerical models by (1) investigating the effect of individual electrodes on the resulting simulated EIT boundary measurements and (2) testing the performance of different electrode arrangements using a machine learning classification model.Main results.We found that, as expected, the electrodes deemed most significant in detecting stroke depend on the location of the electrode relative to the stroke lesion, as well as the role of the electrode. Despite this dependence, there are notable electrodes used in the models that are consistently considered to be the most significant across the various stroke lesion locations and various head models. Moreover, we demonstrate that a reduction in the number of electrodes used for the EIT measurements is possible, given that the electrodes are approximately evenly distributed.Significance.In this way, electrode arrangement and location are important variables to consider when improving stroke diagnosis methods using EIT.

Frequency and Characteristics of Non-Neurological and Neurological Stroke Mimics in the Emergency Department.

BACKGROUND: Stroke mimics are common in the emergency department (ED) and early detection is important to initiate appropriate treatment and withhold unnecessary procedures. We aimed to compare the frequency, clinical characteristics and predictors of non-neurological and neurological stroke mimics transferred to our ED for suspected stroke. METHODS: This was a cross-sectional study of consecutive patients with suspected stroke transported to the ED of the University Hospital Essen between January 2017 and December 2021 by the city's Emergency Medical Service. We investigated patient characteristics, preclinical data, symptoms and final diagnoses in patients with non-neurological and neurological stroke mimics. Multinominal logistic regression analysis was performed to assess predictors of both etiologic groups. RESULTS: Of 2167 patients with suspected stroke, 762 (35.2%) were diagnosed with a stroke mimic. Etiology was non-neurological in 369 (48.4%) and neurological in 393 (51.6%) cases. The most common diagnoses were seizures (23.2%) and infections (14.7%). Patients with non-neurological mimics were older (78.0 vs. 72.0 y, p < 0.001) and more likely to have chronic kidney disease (17.3% vs. 9.2%, p < 0.001) or heart failure (12.5% vs. 7.1%, p = 0.014). Prevalence of malignancy (8.7% vs. 13.7%, p = 0.031) and focal symptoms (38.8 vs. 57.3%, p < 0.001) was lower in this group. More than two-fifths required hospitalization (39.3 vs. 47.1%, p = 0.034). Adjusted multinominal logistic regression revealed chronic kidney and liver disease as independent positive predictors of stroke mimics regardless of etiology, while atrial fibrillation and hypertension were negative predictors in both groups. Prehospital vital signs were independently associated with non-neurological stroke mimics only, while age was exclusively associated with neurological mimics. CONCLUSIONS: Up to half of stroke mimics in the neurological ED are of non-neurological origin. Preclinical identification is challenging and a high proportion requires hospitalization. Awareness of underlying etiologies and differences in clinical characteristics is important to provide optimal care.

The Positive Predictive Value of Pediatric Stroke Diagnoses in Administrative Data: A Retrospective Validation Study.

Background: This retrospective cohort study aimed to examine the positive predictive value (PPV) of pediatric stroke diagnoses in the Danish National Registry of Patients (DNRP) and the impact of different stroke definitions on the PPV. Methods: We included children registered with a stroke or stroke-related diagnosis in the DNRP between January 2017 through December 2020. Two assessors reviewed medical records and validated cases according to the American Heart and American Stroke Association (AHA/ASA) stroke definition. The level of interrater agreement was examined using kappa statistics. Validation by the AHA/ASA definition was compared with validation according to the definition in the International Classification of Disease 11th version (ICD-11) and the World Health Organization's definition. Results: Stroke was confirmed in 120 of 309 included children, yielding an overall PPV of 0.39 (95% CI: 0.33-0.45). PPV varied across stroke subtypes from 0.83 (95% CI: 0.71-0.92) for ischemic stroke (AIS), 0.57 (95% CI: 0.37-0.76) for unspecified stroke, 0.42 (95% CI: 0.33-0.52) for intracerebral hemorrhage (ICH) to 0.31 (95% CI: 0.55-0.98) and 0.07 (95% CI: 0.01-0.22) for cerebral venous thrombosis and subarachnoid hemorrhage (SAH), respectively. Most non-confirmed ICH and SAH diagnoses were in children with traumatic intracranial hemorrhages (36 and 66% respectively). Among 70 confirmed AIS cases, 25 (36%) were identified in non-AIS code groups. PPV varied significantly across stroke definitions with the highest for the AHA/ASA definition (PPV = 0.39, 95% CI: 0.34-0.45) and the lowest for the WHO definition (PPV = 0.29, 95% CI: 0.24-0.34). Correspondingly, the incidence of pediatric AIS per 100.000 person-years changed from 1.5 for the AHA/ASA definition to 1.2 for ICD-11 and 1.0 for the WHO-definition. The overall interrater agreement was considered excellent (κ=0.85). Conclusion: After validation, stroke was confirmed in only half of the children registered in the DNRP with a stroke-specific diagnosis. Non-validated administrative data should be used with caution in pediatric stroke research. Pediatric stroke incidence rates may vary markedly depending on which stroke definition is used.

The Future of Ischemic Stroke Diagnosis and a Review of Underrecognized Ischemic Stroke Etiologies.

Accurate ischemic stroke etiologic determination and diagnosis form the foundation of excellent cerebrovascular care as from it stems initiation of the appropriate secondary prevention strategy as well as appropriate patient education regarding specific risk factors for that subtype. Recurrent stroke rates are highest among those patients who receive an incorrect initial stroke diagnosis. Patient distrust and patient reported depression are also higher. The cause of the ischemic stroke also informs predicted patient outcomes and the anticipated recovery trajectory. Finally, determining the accurate cause of the ischemic stroke provides the patient the opportunity to enroll in appropriate research studies studying mechanism, or targeting treatment approaches for that particular disease process. Advances in ischemic stroke research, imaging techniques, biomarkers, and the ability to rapidly perform genetic sequencing over the past decade have shown that classifying patients into large etiologic buckets may not always be appropriate and may represent one reason why some patients are labeled as cryptogenic, or for whom an underlying etiology is never found. Aside from the more traditional stroke mechanisms, there is new research emerging regarding clinical findings that are not normative, but the contributions to ischemic stroke are unclear. In this article, we first review the essential steps to accurate ischemic stroke etiologic classification and then transition to a discussion of embolic stroke of undetermined source (ESUS) and other new entities that have been postulated as causal in ischemic stroke (i.e., genetics and subclinical atherosclerosis). We also discuss the limitations that are inherent in the current ischemic stroke diagnostic algorithms and finally review the most recent studies regarding more uncommon diagnoses and the future of stroke diagnostics and classification.

Is improved access to magnetic resonance imaging imperative for optimal ischemic stroke care?

Neuroimaging, including CT and MRI, is integral to ischemic stroke (IS) treatment, management, and prevention. However, the use of MRI for IS patients is limited despite its potential to provide high-quality images that yield definitive information related to the management of IS. MRI is beneficial when the information provided by CT is insufficient for decisions related to the diagnosis, etiology, or treatment of IS. In the emergency setting, MRI can improve the diagnostic accuracy of CT-negative acute ischemic strokes (AIS) and ensure a better selection of patients for reperfusion therapies with thrombolysis and/or thrombectomy. Moreover, MR imaging may help avoid hospital admissions for patients with stroke mimics, facilitate earlier discharge, and reduce overall hospital costs. MRI in the in-patient setting can help determine stroke etiology to aid in stroke prevention management upon discharge. Furthermore, early access to MRI in IS out-patients can aid in diagnosing, risk stratifying, and determining optimal management strategies for patients with a TIA or a minor stroke. Recent technological advances, particularly low-to-mid-field MR scanners, can improve access to MRI. These MR scanners provide faster protocols, cost-effectiveness, smaller footprints, safety, and lower power requirements. In conclusion, MRI use for IS treatment, management, and prevention is imperative and justifiable, and the latest technological advancements in MR scanners hold the potential to enhance access.

A deep learning wearable-based solution for continuous at-home monitoring of upper limb goal-directed movements.

Introduction: Monitoring upper limb function is crucial for tracking progress, assessing treatment effectiveness, and identifying potential problems or complications. Hand goal-directed movements (GDMs) are a crucial aspect of daily life, reflecting planned motor commands with hand trajectories towards specific target locations. Previous studies have shown that GDM tasks can detect early changes in upper limb function in neurodegenerative diseases and can be used to track disease progression over time. Methods: In this study, we used accelerometer data from stroke survivor participants and controls doing activities of daily living to develop an automated deep learning approach to detect GDMs. The model performance for detecting GDM or non-GDM from windowed data achieved an AUC of 0.9, accuracy 0.83, sensitivity 0.81, specificity 0.84 and F1 0.82. Results: We further validated the utility of detecting GDM by extracting features from GDM periods and using these features to classify whether the measurements are collected from a stroke survivor or a control participant, and to predict the Fugl-Meyer assessment score from stroke survivors. Discussion: This study presents a promising and reliable tool for monitoring upper limb function in a real-world setting, and assessing biomarkers related to upper limb health in neurological, neuromuscular and muscles disorders.

Deep-Learning-Based Stroke Screening Using Skeleton Data from Neurological Examination Videos.

According to the Korea Institute for Health and Social Affairs, in 2017, the elderly, aged 65 or older, had an average of 2.7 chronic diseases per person. The concern for the medical welfare of the elderly is increasing due to a low birth rate, an aging population, and the lack of medical personnel. The demand for services that take user age, cognitive capacity, and difficulty into account is rising. As a result, there is an increased demand for smart healthcare systems that can lower hospital admissions and offer patients individualized care. This has motivated us to develop an AI system that can easily screen and manage neurological diseases through videos. As neurological diseases can be diagnosed by visual analysis to some extent, in this study, we set out to estimate the possibility of a person having a neurological disease from videos. Among neurological diseases, we focus on stroke because it is a common condition in the elderly population and results in high mortality and morbidity worldwide. The proposed method consists of three steps: (1) transforming neurological examination videos into landmark data, (2) converting the landmark data into recurrence plots, and (3) estimating the possibility of a stroke using deep neural networks. Major features, such as the hand, face, pupil, and body movements of a person are extracted from test videos taken under several neurological examination protocols using deep-learning-based landmark extractors. Sequences of these landmark data are then converted into recurrence plots, which can be interpreted as images. These images can be fed into convolutional neural networks to classify stroke using feature-fusion techniques. A case study of the application of a disease screening test to assess the capability of the proposed method is presented.

Artificial intelligence for early stroke diagnosis in acute vestibular syndrome.

Objective: Measuring the Vestibular-Ocular-Reflex (VOR) gains with the video head impulse test (vHIT) allows for accurate discrimination between peripheral and central causes of acute vestibular syndrome (AVS). In this study, we sought to investigate whether the accuracy of artificial intelligence (AI) based vestibular stroke classification applied in unprocessed vHIT data is comparable to VOR gain classification. Methods: We performed a prospective study from July 2015 until April 2020 on all patients presenting at the emergency department (ED) with signs of an AVS. The patients underwent vHIT followed by a delayed MRI, which served as a gold standard for stroke confirmation. The MRI ground truth labels were then applied to train a recurrent neural network (long short-term memory architecture) that used eye- and head velocity time series extracted from the vHIT examinations. Results: We assessed 57 AVS patients, 39 acute unilateral vestibulopathy patients (AUVP) and 18 stroke patients. The overall sensitivity, specificity and accuracy for detecting stroke with a VOR gain cut-off of 0.57 was 88.8, 92.3, and 91.2%, respectively. The trained neural network was able to classify strokes with a sensitivity of 87.7%, a specificity of 88.4%, and an accuracy of 87.9% based on the unprocessed vHIT data. The accuracy of these two methods was not significantly different (p = 0.09). Conclusion: AI can accurately diagnose a vestibular stroke by using unprocessed vHIT time series. The quantification of eye- and head movements with the use of machine learning and AI can serve in the future for an automated diagnosis in ED patients with acute dizziness. The application of different neural network architectures can potentially further improve performance and enable direct inference from raw video recordings.

Acute Middle Cerebral Artery Occlusion Detection Using Mobile Non-Imaging Brain Perfusion Ultrasound-First Case.

Mobile brain perfusion ultrasound (BPU) is a novel non-imaging technique creating only hemispheric perfusion curves following ultrasound contrast injection and has been specifically designed for early prehospital large vessel occlusion (LVO) stroke identification. We report on the first patient investigated with the SONAS® system, a portable point-of-care ultrasound system for BPU. This patient was admitted into our stroke unit about 12 h following onset of a fluctuating motor aphasia, dysarthria and facial weakness resulting in an NIHSS of 3 to 8. Occlusion of the left middle cerebral artery occlusion was diagnosed by computed tomography angiography. BPU was performed in conjunction with injection of echo-contrast agent to generate hemispheric perfusion curves and in parallel, conventional color-coded sonography (TCCS) assessing MCAO. Both assessments confirmed the results of angiography. Emergency mechanical thrombectomy (MT) achieved complete recanalization (TICI 3) and post-interventional NIHSS of 2 the next day. Telephone follow-up after 2 years found the patient fully active in professional life. Point-of-care BPU is a non-invasive technique especially suitable for prehospital stroke diagnosis for LVO. BPU in conjunction with prehospital stroke scales may enable goal-directed stroke patient placement, i.e., directly to comprehensive stroke centers aiming for MT. Further results of the ongoing phase II study are needed to confirm this finding.

Development of Early-Stage Stroke Diagnosis System for the Elderly Neurogenic Bladder Prevention.

PURPOSE: There are various neurogenic bladder patterns that occur in patients during stroke. Among these patterns, the focus was mainly on the patient's facial parsy diagnosis. Stroke requires early response, and it is most important to identify initial symptoms such as facial parsy. There is an urgent need for a diagnostic technology that notifies patients and caregivers of the onset of disease in the early stages of stroke. We developed an artificial intelligence (AI) stroke early-stage analysis software that can alert the early stage of stroke through analysis of facial muscle abnormalities for the elderly neurogenic bladder prevention. METHODS: The method proposed in this paper developed a learning-based deep learning analysis technology that outputs the initial stage of stroke after acquiring a high-definition digital image and then deep learning face analysis. The applied AI model was applied as a multimodal deep learning concept. The system is linked and integrated with the existing urine management integrated system to support patient management with a total-care concept. RESULTS: We developed an AI stroke early-stage analysis software that can alert the early stage of stroke with 86% hit performance through analysis of facial muscle abnormalities in the elderly. This result shows the validation result of the landmark image learning model based on the distance learning model. CONCLUSION: We developed an AI stroke early-stage diagnostic system as a wellness personal medical service plan and prevent cases of missing golden time when existing stroke occurs. In order to secure and facilitate distribution of this, it was developed in the form of AI analysis software so that it can be mounted on various hardware products. In the end, it was found that using AI for these stroke diagnoses and making them quickly and accurately had a positive effect indirectly, if not directly, on the neurogenic bladder.