Hyperacute Stroke Research Articles

Hyperglycemia Treatment with Intravenous Insulin in Acute Stroke Patients: A Scoping Review

Introduction/Background: Hyperglycemia has been shown to lead to worse outcomes for ischemic stroke patients, including those undergoing reperfusion therapies. However current guidelines do not exclude hyperglycemic patients from reperfusion therapy. This scoping review examines what is known about the safety, feasibility, and efficacy of intravenous insulin treatment for hyperacute and acute ischemic stroke patients. Methods: PubMed, EBSCOhost, the Cochrane Database of Systemic Reviews, Embase, and Google Scholar were searched from inception to March 25, 2024. Titles, abstracts, and full texts were reviewed. Studies qualified for inclusion if they were peer-reviewed, published in English, full-text, human experimental studies using intravenous insulin for hyperglycemia treatment for hyperacute or acute stroke patients reviewing serious adverse events, feasibility, disability, or functional outcomes. Results: Ten studies were included (n=6 safety/feasibility design, n=4 efficacy design). Intravenous insulin infusion treatment targets ranged from 72-144 mg/dL, comprising of both loose and tight target controls, with symptom onset to treatment max times of 6-24 hours. Conclusions: There are limited clinical trials evaluating IV insulin for the ischemic stroke population. Of the studies found, hyperglycemia treatment with regular or GKI intravenous insulin in acute stroke patients suggest that with tight or loose control, is a safe and feasible option for at least 72 hours after symptom onset. However, it has not been demonstrated that hyperglycemia treatment alters outcomes when initiated within 6-24 hours of symptom onset.

Outcomes of Cardio-Cerebral Infarction Patients: A Single-Centre Retrospective Study.

Background Cardio-cerebral infarction (CCI) belongs to an area of growing interest within cerebrovascular medicine as it refers to the concurrence of acute ischaemic stroke (AIS) and acute myocardial infarction (AMI) usually within 72 hours. A scenario where both the heart and brain sustain a catastrophic ischaemic insult can be devastating. We describe the incidence, treatment, and outcomes of CCI patients from a North London Hyper-Acute Stroke Unit (HASU) over two years and propose a potential treatment algorithm for the treatment of CCI. Methodology A retrospective analysis of AIS patients admitted to a North London HASU between January 2020 to December 2021 was performed to investigate the occurrence of concurrent AIS and AMI. Patients were initially included if they had elevated troponins upon admission to the stroke unit, following which they were excluded or included based on the diagnosis and treatment of myocardial infarction (MI) within 72 hours of AIS or vice versa. We describe the clinical characteristics of admission, clinical progression, management, and outcomes of patients suffering from CCIs. Results A total of 1,921 AIS patients were analysed. Of these, 302(16%) patients had elevated troponin and 35 (1.8%) patients were treated as acute coronary syndrome. Overall, 18 (0.9%) patients had CCI. Further analysis of CCI patients showed in-hospital death occurred in seven (41%) patients.The median length of stay was six days (range = 1-44 days). Angioplasty was used to treat MI in five (29%) patients, and the rest were medically managed or died. Conclusions Although rare, CCI has an exceedingly high mortality, and therefore, recognising and choosing the appropriate therapy is vital when attempting to re-perfuse both vital organs. Collaboration between stroke physicians, neuro-interventionalists, and cardiologists with a clear CCI pathway will enable better management and outcomes for these patients.

Pre-hospital Blood Pressure Lowering in Presumed Hyperacute Stroke: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

BackgroundHigh blood pressure (BP) is common in acute stroke and a predictor of poor outcomes. Treatment of acute stroke, before a distinction can be made between ischemic and hemorrhagic types, is challenging. We aimed to assess whether patients with presumed acute stroke benefit from pre-hospital BP lowering. MethodsWe conducted a comprehensive systematic review and meta-analysis of randomized controlled trials from PubMed, Web of Science, Scopus, and Cochrane searches until June 2024. Dichotomous data were pooled using risk ratio (RR), and continuous data were pooled using mean difference (MD), both with a 95% confidence interval (CI), using (R version 4.3). PROSPERO ID: CRD42024560200. ResultsOur analysis included five RCTs encompassing 3,933 patients. There was no difference between early BP control and usual care regarding National Institutes of Health Stroke Scale (NIHSS) after 24 hours (MD: 0.65 with 95% CI [0.01, 1.29], P = 0.05), excellent neurological recovery (Modified Rankin Score (mRS) 0–1) (RR: 1.00 with 95% CI [0.91, 1.11], P= 0.98), functional independence (mRS 0–2) (RR: 1.04 with 95% CI [0.96, 1.13], P= 0.30), and independent Ambulation (mRS 0–3) (RR: 1.01 with 95% CI [0.95, 1.06], P= 0.84). Also, there was no difference between both groups in poor neurological recovery (mRS 4–6) (RR: 0.98 with 95% CI [0.91, 1.07], P= 0.68), all-cause mortality (RR: 1.02 with 95% CI [0.90, 1.15], P= 0.79), and any serious adverse events (RR: 1.04 with 95% CI [0.95, 1.15], P= 0.40). However, early BP control significantly increased the incidence of hypotension (RR: 2.24 with 95% CI [1.14, 4.38], P= 0.02) and headache (RR: 1.51 with 95% CI [1.01, 2.26], P= 0.04). ConclusionIn patients with presumed hyperacute stroke and elevated blood pressure, the rapid initiation of blood pressure reduction in the ambulance very early after symptom onset had no significant benefit regarding functional outcomes in patients with undifferentiated stroke but with an increased incidence of hypotension and headaches.

Mild hypercapnia before reperfusion reduces ischemia-reperfusion injury in hyperacute ischemic stroke rat model.

Endovascular thrombectomy has a recanalization rate over 80%; however, approximately 50% of ischemic stroke patients still experience dependency or mortality. Recently, clinical trials demonstrated the benefits of administering neuroprotective agents prior to endovascular thrombectomy. Additionally, recent studies showed neuroprotective effects of mild hypercapnia in patients resuscitated after cardiac arrest. However, its efficacy in ischemic stroke remains unclear. We aimed to investigate whether carbon dioxide (CO2) per-conditioning has neuroprotective effects in rat models with middle cerebral artery occlusion (MCAO). Rat models received intermittent inhalation of mixed gas during the MCAO period. After surgery, behavioral assessments, infarct size measurement, immunohistochemistry, and western blot analysis were performed. We found CO2 per-conditioning reduced infarct size and neurological deficit. The number of 8-hydroxy-2-deoxyguanosine (8-OHdG) positive cells and matrix metalloproteinase 9 (MMP-9)/platelet derived growth factor receptor beta (PDGFRβ) double positive cells were significantly decreased after CO2 per-conditioning. The expressions of tight junction protein and pericytes survival were preserved. This study underscores mild hypercapnia before reperfusion not only reduces neurologic deficit and infarct size, but also maintains the integrity of the blood-brain barrier and neurovascular unit, alongside mitigating oxidative stress in hyperacute stroke rat models. Therapeutic mild hypercapnia before reperfusion is promising and requires further clinical application.

Telemedicine networks for acute stroke: An analysis of global coverage, gaps, and opportunities.

Despite the proven efficacy of telestroke in improving clinical outcomes by providing access to specialized expertise and allowing rapid expert hyperacute stroke management and decision-making, detailed operational evidence is scarce, especially for less developed or lower income regions. We aimed to map the global telestroke landscape and characterize existing networks. We employed a four-tiered approach to comprehensively identify telestroke networks, primarily involving engagement with national stroke experts, stroke societies, and international stroke authorities. A carefully designed questionnaire was then distributed to the leaders of all identified networks to assess these networks' structures, processes, and outcomes. We identified 254 telestroke networks distributed across 67 countries. High-income countries (HICs) concentrated 175 (69%) of the networks. No evidence of telestroke services was found in 58 (30%) countries. From the identified networks, 88 (34%) completed the survey, being 61 (71%) located in HICs. Network setup was highly heterogeneous, ranging from 17 (22%) networks with more than 20 affiliated hospitals, providing thousands of annual consultations using purpose-built highly specialized technology, to 11 (13%) networks with fewer than 120 consultations annually using generic videoconferencing equipment. Real-time video and image transfer was employed in 64 (75%) networks, while 62 (74%) conducting quality monitoring. Most networks established in the past 3 years were located in low- and middle-income countries (LMICs). This comprehensive global survey of telestroke networks found significant variation in network coverage, setup, and technology use. Most services are in HICs, and a few services are in LMICs, although an emerging trend of new networks in these regions marks a pivotal moment in global telestroke care. The wide variation in quality monitoring practices across networks, with many failing to report key performance metrics, underscores the urgent need for standardized, resource-appropriate, quality assurance measures that can be adapted to diverse settings.

Evaluation of Physiological Variables Determining Time-to-Mortality after Stroke-Associated Pneumonia

Introduction: Stroke-associated pneumonia (SAP) frequently complicates stroke and is associated with significant mortality. Clinicians often use physiological variables within the National Early Warning Score (NEWS) when diagnosing and prescribing antibiotics for SAP, but little is known of its association with mortality. We investigated the relationship of the NEWS 2 score and its components (respiratory rate, heart rate, temperature, oxygen requirement, oxygen saturation, and alertness level) prior to antibiotic initiation, with time-to-mortality in SAP. Methods: We included patients with SAP (n = 389) from a single hyperacute stroke unit. Diagnosis of SAP was made if pneumonia occurred within 7 days of hospital admission. Kaplan-Meier survival curves were generated to assess NEWS 2 parameters influencing survival at pre-defined time periods (1 year and 5 years). The association of these parameters on time-to-mortality were analysed using multivariable Cox-regression models to account for a set of pre-specified potential confounders. Results: The median age was 80 years (71–87 years) and median NIHSS was 7 (IQR 4–17). Mortality within 1 year was 52.4% and 65.8% within 5 years. In the multivariable analyses, time-to-mortality was independently associated with respiratory rate (heart rate [HR] 1.04, 95% confidence intervals [CI] 1.01–1.08, p = 0.009) and total NEWS 2 score (HR 1.13, 95% CI 1.06–1.21, p < 0.001). Conclusions: In patients with SAP, higher respiratory rate and total NEWS 2 score prior to antibiotic initiation were independently associated with time-to-mortality. Further studies are warranted to identify potential opportunities for intervention and ultimately guide treatment to improve outcomes in SAP patients.

Real-world evaluation of Brainomix e-Stroke software

Background and purposeBrainomix e-Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. While e-Stroke has the potential to...

Soluble Glycoprotein VI Levels Assessed Locally within the Extra- and Intracerebral Circulation in Hyper-Acute Thromboembolic Stroke: A Pilot Study.

Background: Severe acute ischemic stroke (AIS) is mainly caused by thromboembolism originating from symptomatic carotid artery (ICA) stenosis or in the heart due to atrial fibrillation. Glycoprotein VI (GPVI), a principal platelet receptor, facilitates platelet adherence and thrombus formation at sites of vascular injury such as symptomatic ICA stenosis. The shedding of GPVI from the platelet surface releases soluble GPVI (sGPVI) into the circulation. Here, we aimed to determine whether sGPVI can serve as a local biomarker to differentiate between local atherosclerotic and systemic cardiac thromboembolism in AIS. Methods: We conducted a cohort study involving 105 patients undergoing emergency endovascular thrombectomy (EVT) for anterior circulation stroke. First, sGPVI concentrations were measured in systemic arterial plasma samples collected at the ipsilateral ICA level, including groups with significantly (≥50%) stenotic and non-stenotic arteries. A second sample, taken from the intracerebral pial circulation, was used to assess GPVI shedding locally within the ischemic brain. Results: Our analysis revealed no significant increase in systemic sGPVI levels in patients with symptomatic ≥ 50% ICA stenosis (3.2 [95% CI 1.5-5.0] ng/mL; n = 33) compared with stroke patients without significant ICA stenosis (3.2 [95% CI 2.3-4.2] ng/mL; n = 72). Additionally, pial blood samples, reflecting intravascular molecular conditions during collateral flow, showed similar sGPVI levels when compared to the systemic ICA samples in both groups. Conclusions: Our findings indicate that GPVI is not locally cleaved and shed into the bloodstream in significant amounts during hyper-acute ischemic stroke, neither at the level of symptomatic ICA nor intracranially during collateral blood supply. Therefore, sGPVI does not appear to be suitable as a local stroke biomarker despite strong evidence of a major role for GPVI-signaling in stroke pathophysiology.

Process Evaluation of an Ambulance-Delivered Early Intensive Blood Pressure-Lowering Stroke Trial: Design, Rationale, and Reflection

Introduction: The fourth INTEnsive ambulance-delivered blood pressure Reduction in hyper-ACute stroke Trial (INTERACT4) is a large-scale, multicenter, prospective, randomized, open-label, blinded endpoint assessment trial, initiated in an ambulance in China, aiming at evaluating the effectiveness and safety of prehospital blood pressure (BP) lowering in patients with suspected acute stroke and elevated BP. A prespecified process evaluation is intended to explore the implementation of the trial intervention, provide support to interpret the trial outcomes and put forward suggestions to scale up the intervention in broader settings in the future. Methods: This process evaluation is a mixed-methods design, and follows the Normalization Process Theory (NPT) and the UK Medical Research Council (UK MRC) guidance. Fidelity, reach, acceptability, appropriateness, adoption, sustainability, and relevant contextual factors and mechanisms affecting the implementation of prehospital early intensive BP-lowering treatment will be analyzed. Semi-structured interviews with ambulance staff, ward and emergency department clinicians, and nurses are undertaken to explore perceptions of the intervention, contextual factors, and potential suggestions for future implementation in practice. Data from observational records, surveys, conventional monitoring data, on-site records, and case report forms will be analyzed to understand background care and context. Conclusion: The process evaluation of INTERACT4 will provide insights for the implementation of prehospital early intensive BP-lowering intervention in different health systems and help better explain the trial results for further scale up.

Characteristics and outcomes of atrial fibrillation detected before and after acute ischemic stroke.

Atrial fibrillation (AF) can be known before the stroke (KAF) or be newly detected after stroke (AFDAS). It is unknown whether the outcome of stroke differs between KAF and AFDAS. We performed a propensity-matched analysis to investigate the outcome of patients with AFDAS and their counterparts with KAF. We analysed a consecutive series of patients enrolled into the EIDASAF study, a single centre, retrospective study of ischemic stroke patients with a diagnosis of AF before or after the event who had been admitted to the Hyperacute Stroke Unit of Imperial College Healthcare NHS Trust between 2010 and 2017. Overall, our cohort included 959 patients with AF and acute ischemic stroke. After propensity score matching, 547 patients were matched (404 KAF group and 143 AFDAS group). The rates of in hospital death and of haemorrhagic transformation were significantly higher in KAF patients compared to AFDAS patients. Logistic regression analysis did not reveal a statistically significant influence of AF subtypes on the outcome of death. However, in logistic regression analysis KAF was associated with increased probability of haemorrhagic transformation (OR 9.64; CI 1.29-71.68, p = 0.022) after the index event. KAF is associated with an increased risk of haemorrhagic transformation but not of death when compared to AFDAS.

Mechanical Thrombectomy for Hyperacute Vertebrobasilar Ischemic Stroke via Nondominant Vertebral Artery : Clinical Experience and Considerations.

The dominant vertebral artery (VA) approach is primarily considered in mechanical thrombectomy (MT) for acute occlusion of the vertebrobasilar (VB) artery. As accessing the dominant artery is sometimes difficult, we present our experience treating acute VB stroke via a nondominant VA approach through a comparison with the dominant VA approach. Among 2,785 patients diagnosed with hyperacute ischemic stroke between January 2014 and December 2022, 50 patients with VB ischemic stroke underwent recanalization therapy through either dominant, nondominant, or bilateral VA approach. We evaluated patient characteristics and clinical course, highlighting the pros and cons of the access routes. The patients with hyperacute VB ischemic stroke were predominantly male (72%), with a mean age of 68.12 years and an initial National Institutes of Health Stroke Scale (NIHSS) score mean of 17.1. Large-artery atherosclerosis (LAA, 48%) and cardio-embolism (CE, 36%) were the main etiologic factors in the TOAST (Trial of Org 10172 in Acute Stroke Treatment) classification. After thrombectomy, 45 (90%) cases had final modified thrombolysis in cerebral infarction (mTICI) score of 2b or higher. In summary, 41 patients were treated through the dominant VA, and 8 patients underwent the nondominant VA approach. However, there was no statistically significant difference in functional outcome or mortality between the two approaches. In MT for VB occlusions, nondominant VA approach may be an option in situations when the vessel is accessible, stable, or less risky, as recanalization can be achieved without rescue balloon angioplasty and/or stenting.

Effectiveness of the Stroke e-Learning Module on Malaysian Doctors' Knowledge of Acute Ischaemic Stroke Management.

The Stroke e-Learning Module (SEM) is a nationwide initiative to improve stroke care in Malaysia. This study aimed to assess the module's effectiveness in improving knowledge on acute ischaemic stroke (AIS) management among Malaysian doctors. This was a pre-post study design. Medical officers, specialists and general practitioners from various disciplines who work in healthcare facilities in Malaysia were recruited virtually from those who registered for the SEM on the Docquity platform between 1 February 2021 and 31 January 2022. The Acute Stroke Management Questionnaire (ASMaQ), an existing validated questionnaire, was used to measure the doctors' knowledge of AIS management before and after the SEM. The ASMaQ had three domains: i) general stroke knowledge (GSK), ii) hyperacute stroke management (HSM) and iii) advanced stroke management (ASM). The paired t- and the McNemar-tests were used to evaluate the effectiveness of the module. One hundred and seventy-one participants voluntarily responded to the pre- and post-module questionnaires. The paired t-test revealed statistically significant improvement for the ASM knowledge scores (mean difference = 2.5; 95% CI: 1.8, 3.2; P < 0.001). The baseline proportion of participants with good knowledge of GSK, HSM and ASM were 92.4%, 64.9%, and 76%, respectively. The McNemar test showed that approximately 14% of the participants had significant improvement in ASM knowledge (P < 0.001). However, no significant changes were noted for GSK (-0.6%) and HSM (4.1%). The SEM has been shown to increase Malaysian doctors' knowledge on ASM. However, greater effort should be made to improve GSK and HSM knowledge, particularly in areas related to stroke thrombolysis.

Utilization of Artificial Intelligence to Improve Door-In Door-Out Times for Mechanical Thrombectomy-Eligible Patients at a Hub-and-Spoke Community-Based Comprehensive Stroke Center: A Single Case Study Presentation

Background: Delays in the transfer of patients with hyperacute stroke may lead to treatment ineligibility due to the degree of cerebral hypoxic injury suffered. Cloud-based artificial intelligence applications may improve transfer times and expand access to advanced therapies. One case between a community-based comprehensive stroke center (CSC) and a primary stroke center (PSC) using a third-party telemedicine service and shared cloud-based artificial intelligence application may provide insight in opportunities to improve stroke systems of care. Case Presentation: A 62-year-old female with a past medical history of hypertension, current everyday tobacco smoker, and marijuana user presented to an outlying emergency department (ED) with dense left-sided hemiplegia affecting the arm and leg, right-sided gaze preference, and severe dysarthria. Her last known well (LKW) time was 0900 hours. CNS imaging revealed a right middle cerebral artery occlusion, visible to members of the CSC stroke team through the use of a cloud-based artificial intelligence cell phone application. The patient was treated with intravenous thrombolytics at the PSC, and she was transferred to the CSC, where she underwent a diagnostic cerebral arteriogram with carotid artery stenting. Later, Magnetic Resonance Imaging (MRI) of the brain revealed a 3.5 cm x 2.5 cm hemorrhagic lesion in the right frontal lobe and diffusion restriction in the right frontal and right posterior temporal lobes. The patient’s hospital stay was three days and, at the time of discharged, her modified Rankin score and NIHSS were zero. She was discharged on dual antiplatelet therapy, statin therapy, and nicotine replacement. Utilization of Artificial Intelligence: Transfer delays are complicated by organizing care at PSC and CSC and can be lengthy when communication across different facilities and subspecialties. Implementing cloud-based AI image sharing in stroke systems of care has reduced DIDO times by providing rapid imaging interpretation, streamlining communication, and enhancing coordination between PSCs and CSCs. Conclusions: Our case presentation showed how a hub-and-spoke model combined with cloud-based AI utilization can improve DIDO times and enhance stroke systems of care.

Temporal structures that determine consistency and quality of care: a case study in hyperacute stroke services

BackgroundTemporal structuring is determined by practices and social norms and affects the quality and timing of care. In this case study of hyperacute stroke wards which provide initial stroke investigation,...

Impact of in-hospital COVID-19 quarantine policy on the quality of care of hyperacute stroke: A single-center study

Impact of in-hospital COVID-19 quarantine policy on the quality of care of hyperacute stroke: A single-center study

Hyperacute ischemic stroke care-Current treatment and future directions.

A decade on from the first positive thrombectomy trials, hyperacute therapies for ischemic stroke continue to rapidly advance. Effective treatments remain limited to reperfusion, although several cytoprotective approaches continue to be investigated. Intravenous fibrinolytics are now demonstrated to be beneficial up to 24 h in patients selected using perfusion imaging, but their role in patients with non-disabling symptoms appears very limited. Tenecteplase is superior to alteplase in meta-analysis of the latest trials, and adjuvant thrombolytics are an area of active investigation. Endovascular thrombectomy is beneficial in a wide range of anterior and posterior circulation large vessel occlusions up to 24 h after onset with the more distal occlusions, mild presentations, and >24 h window being the main frontiers to be tested in ongoing trials. Imaging parameters are prognostic but appear not to modify the relative treatment benefit of thrombectomy versus standard medical care. Therefore, deciding who not to treat with thrombectomy is a key clinical challenge that requires careful but rapid integration of clinical, imaging, and patient preference considerations. Systems of care to accelerate delivery of these highly effective therapies will maximize benefits for the greatest number of patients with stroke.

Improving follow-up care for people after minor stroke using early personalised care: A protocol for a randomised, mixed-methods, feasibility study.

Background Of the 150 000 people per year in the UK who have strokes, a third to a quarter will experience a so-called ‘minor stroke’. Although appearing benign these strokes put a person at increased risk of further strokes and survivors are usually considered ‘too good’ for referral onto community stroke services. When back at home the hidden effects of stroke like fatigue and changes in mood and cognition become apparent and impact return to work, relationships and everyday activities. Alongside this, managing the risk of recurrence, highest early after an initial stroke, is a priority. People with stroke report feeling abandoned after discharge with unmet information and support needs. Methods To address this issue, we reviewed the literature, met with people with stroke and other stakeholders to develop an early, personalised follow-up programme of care for those who currently only receive routine medical follow-up appointments. This complex intervention is underpinned by self-determination theory, which forms a framework for delivery of the intervention. We will be conducting a randomised, mixed methods, single-centre feasibility study to explore the acceptability and feasibility of the intervention. Sixty participants will be recruited from a Hyperacute Stroke Unit and Rapid Assessment Clinic and randomised to the intervention or control group. The intervention group will receive personalised follow-up appointments at two- and six-weeks post-discharge. All participants will have outcome measures taken at baseline and twelve-weeks post-stroke. Patient reported outcomes will be reviewed to assess their suitability for a later definitive trial. Qualitative interviews will be conducted to gain a deeper understanding of life after stroke from those who did and did not receive the intervention. Conclusions Study findings will be used to further refine the intervention, methods and outcome measurements used. These refinements will inform a future multicentre randomised controlled trial.

The Clinical Utility of Cardiac CT Performed During Hyperacute Stroke CT Imaging

The Clinical Utility of Cardiac CT Performed During Hyperacute Stroke CT Imaging

Days Alive and Out of Hospital as an Outcome Measure in Patients Receiving Hyperacute Stroke Intervention.

Patient outcome after stroke is frequently assessed with clinical scales such as the modified Rankin Scale score (mRS). Days alive and out of hospital at 90 days (DAOH-90), which measures survival, time spent in hospital or rehabilitation settings, readmission and institutionalization, is an objective outcome measure that can be obtained from large administrative data sets without the need for patient contact. We aimed to assess the comparability of DAOH with mRS and its relationship with other prognostic variables after acute stroke reperfusion therapy. Consecutive patients with ischemic stroke treated with intravenous thrombolysis or endovascular thrombectomy were analyzed. DAOH-90 was calculated from a national minimum data set, a mandatory nationwide administrative database. mRS score at day 90 (mRS-90) was assessed with in-person or telephone interviews. The study included 1278 patients with ischemic stroke (714 male, median age 70 [59-79], median National Institutes of Health Stroke Scale score 14 [9-20]). Median DAOH-90 was 71 [29-84] and median mRS-90 score was 3 [2-5]. DAOH-90 was correlated with admission National Institutes of Health Stroke Scale score (Spearman rho -0.44, P<0.001) and Alberta Stroke Program Early CT [Computed Tomography] Score (Spearman rho 0.24, P<0.001). There was a strong association between mRS-90 and DAOH-90 (Spearman rho correlation -0.79, P<0.001). Area under receiver operating curve for predicting mRS score >0 was 0.86 (95% CI, 0.84-0.88), mRS score >1 was 0.88 (95% CI, 0.86-0.90) and mRS score >2 was 0.90 (95% CI, 0.89-0.92). In patients with stroke treated with reperfusion therapies, DAOH-90 shows reasonable comparability to the more established outcome measure of mRS-90. DAOH-90 can be readily obtained from administrative databases and therefore has the potential to be used in large-scale clinical trials and comparative effectiveness studies.

Hybrid Ensemble Deep Learning Model for Advancing Ischemic Brain Stroke Detection and Classification in Clinical Application.

Ischemic brain strokes are severe medical conditions that occur due to blockages in the brain's blood flow, often caused by blood clots or artery blockages. Early detection is crucial for effective treatment. This study aims to improve the detection and classification of ischemic brain strokes in clinical settings by introducing a new approach that integrates the stroke precision enhancement, ensemble deep learning, and intelligent lesion detection and segmentation models. The proposed hybrid model was trained and tested using a dataset of 10,000 computed tomography scans. A 25-fold cross-validation technique was employed, while the model's performance was evaluated using accuracy, precision, recall, and F1 score. The findings indicate significant improvements in accuracy for different stages of stroke images when enhanced using the SPEM model with contrast-limited adaptive histogram equalization set to 4. Specifically, accuracy showed significant improvement (from 0.876 to 0.933) for hyper-acute stroke images; from 0.881 to 0.948 for acute stroke images, from 0.927 to 0.974 for sub-acute stroke images, and from 0.928 to 0.982 for chronic stroke images. Thus, the study shows significant promise for the detection and classification of ischemic brain strokes. Further research is needed to validate its performance on larger datasets and enhance its integration into clinical settings.