Stroke Recognition Research Articles

Abstract WMP37: Neighborhood Socioeconomic Status, Race and Prehospital Emergency Care and Time to Presentation for Stroke

Introduction: It is unclear how neighborhood socioeconomic status (nSES) affects the pre-hospital recognition and care of acute stroke at the national level. Methods: Patients with ischemic stroke, intracerebral hemorrhage, and subarachnoid hemorrhage in the Get With the Guidelines-Stroke registry, presenting from July 2015 to December 2019, with symptom onset <24 hours were included. Social deprivation index (SDI) at the county level approximated nSES. Logistic and quantile regressions evaluated the impact of SDI on EMS use, EMS prenotification, and time of symptom onset to emergency department (ED) arrival. Sequential models were adjusted for patient age, gender, race, vascular risk factors, arrival mode, stroke severity (NIHSS), and insurance status. Results: 634,823 patients met inclusion criteria. Patients were 51.2% Male, 67.1% White, with median NIHSS of 4 (IQR: 2-10), and median SDI of 51 (IQR: 27-75). Median symptom onset to arrival time was 176 mins (IQR: 63-565). SDI was not associated with differences in EMS use, but was associated with lower odds of EMS prenotification (upper SDI tercile vs lowest, OR 0.87, 95% CI 0.86-0.89). SDI was also significantly associated with stroke symptom onset to ED arrival time (upper SDI tercile vs lowest +2.72 mins, 95% CI 0.68-4.77); however, this association became nonsignificant when insurance was added to the model. By contrast, Black race was significantly associated with prolonged symptom onset to ED arrival time (+28.7 mins, 95% CI 26.0-31.5), and decreased odds of EMS prenotification OR 0.76 (95% CI 0.74-0.77). Conclusions: Higher SDI was associated with reduced odds of EMS prenotification, despite similar odds of EMS use across SDI levels. Race had a greater effect, with prolonged prehospital times and decreased odds of EMS pre-notification. Efforts to reduce place-based disparities in stroke care must address significant race-based inequities which exist in pre-hospital recognition and care of stroke.

Abstract WP45: A Collaborative Approach to Improving Inpatient Stroke Code Time Target Metrics

Much effort and education has been placed on pre-hospital and emergency departments to recognize signs and symptoms of acute stroke and time metrics such as door-to-CT, door-to-needle, and door-to-device. For admitted patients with acute onset of stroke symptoms, our data analysis identified a gap in the timeliness of stroke code activation upon symptoms discovery and subsequent delays in CT initiation and treatment. We evaluated our current process and implemented action plans to enhance the current inpatient stroke code process through focused education and training of staff to improve their recognition of acute stroke, timely activation of stroke code and improved CT initiation and treatment times. In 2021, several cardiology pilot units were selected and neuroscience nurse specialists conducted staff education which focused on recognition of stroke signs and symptoms, code activation criteria and response time targets. A resource binder and checklist were created to guide staff in putting together pertinent elements for communication and documentation. Data was collected on stroke code response times and individual feedback was provided. The group meets quarterly to evaluate progress, discuss opportunities for improvement and highlight best practices and outcomes. The checklist was a useful tool in reminding staff of pertinent information to communicate to the stroke team although form completion is not consistent. In 2021-2022, 54% of stroke codes were called within 10 minutes of symptoms discovery. CTH initiation time within 25 minutes of symptoms discovery was achieved in 16.2% of patients. Data analysis showed an opportunity to improve documentation of symptoms discovery time which were missing in 13.8% of cases. This collaborative approach with the pilot units has increased awareness and focus to the inpatient stroke code process. Opportunities exist to improve time target achievements in CTH initiation, treatment, and documentation of symptoms discovery time. Communication between the stroke team and the patient’s primary team has been identified as an essential factor for continued improvement along with on-going staff education.

Abstract TP58: Stroke Recognition Task Force: Increasing Early Activation of Inpatient Stroke Codes

Background: 1 in 5 strokes occur in the hospital. Patients with in-hospital stroke have increased vascular risk factors, delayed time to recognition, and increased mortality compared to patients with community-onset stroke. All staff should be able to recognize and initiate management of patients with a suspected acute stroke. Purpose The goals of this project were to increase early activation of inpatient stroke codes and confidence levels related to the recognition of stroke and management of patients during a code. Methods: An education program, providing unit specific information, was provided to each inpatient unit at an academic medical center. A survey was created for learners to take before and after the education session; including questions regarding symptom recognition, how to activate a stroke code, and tasks required following activation. Additional questions included self-assessment of the learner’s confidence level in different aspects of stroke care, including stroke recognition and management. To assess time to activation, data related to inpatient stroke code activations was analyzed pre- and post-intervention. Data included symptom discovery and stroke team activation time gathered from the electronic medical record. Results: Data from 119 codes was reviewed. Prior to intervention, only 50% of inpatient stroke codes were activated within 10 minutes of symptom discovery. Following intervention, 75% of inpatient stroke codes were activated within 10 minutes of symptom discovery. There were 61 pre-session survey responses and 39 post-session. Before the session, 56.1% of participants were slightly or moderately confident in identifying stroke, but after the session, 80.5% of participants were very or extremely confident in identifying stroke. Before the session, 81.8% of participants did not feel comfortable managing a patient during a code, but after the session, 95% of participants felt comfortable. Conclusion: An education session for hospital staff can increase knowledge and confidence level in the recognition of stroke and their management of patients. This curriculum has potential to be used nationally to reduce delays to diagnosis, increase usage of acute therapies and reduce mortality associated with in-hospital stroke.

Abstract TP71: Creative Methods Utilized to Improve Stroke Education at an Academic Medical Center

Background: Stroke patients admitted to a hospital can be cared for in several different settings requiring hospital clinical staff to have a strong knowledge base of signs and symptoms of a stroke as well as the care and management of patients after a stroke. Stroke patients may present with other co-morbidities which may take precedence over their stroke diagnosis causing them to be admitted to non-stroke units. In addition, patients may also have an acute stroke during their hospitalization for a non-related admission. Therefore, hospital systems must continue to expose all staff to education regarding stroke recognition, care and management. Purpose: To increase the knowledge of stroke recognition, prevention, care, and treatment options of clinical staff at one academic medical center. Methods: Members of the stroke clinical team and unit nurse specialists provide educational opportunities through a mobile education program which brings interactive games to the unit staff to test and reinforce their stroke knowledge. They provide brain themed prizes and provide direct staff feedback on stroke codes that occurred on the unit. This team also provides in-person educational in-services to units where gaps in our data metrics have occurred. They are a resource that all clinical staff can reach out to for additional education on stroke management. Results: Feedback from the clinical staff after receiving education either from interactive games, in-services or direct feedback has been positive. We have seen increased confidence with our inpatient units nursing staff in activating the stroke code immediately as soon as signs and symptoms of stroke are observed. They also have a stronger understanding of the importance of meeting our time targets to improve patient outcomes. Conclusions: Making learning fun and rewarding staff for their understanding and impact on patient care creates an incentive to continue to learn more about stroke care, management, and improves their recognition of stroke among all patients. We continue to develop creative and alternative methods to provide education to the clinical staff throughout the health care system.

Abstract WP148: Implementation of a Hospital Wide Process Improves Rapid Administration of In-Hospital Intravenous Thrombolytics and Endovascular Therapy

Background: The recognition of in-hospital strokes (IHS) and their subsequent interventions remain challenging. IHS do not have guideline-based efficiency metrics established. Only 1 in 5 IHS receive treatment within 60 minutes of symptom recognition time (SRT). We aimed to establish a resident physician-nursing collaborative effort to improve IHS time metrics. Methods: We retrospectively compared SRT to bolus time and/or skin puncture time Pre (2010-2016) and Post (2017-2023) implementation of our hospital wide process, which focuses on rapid nursing identification of BEFAST stroke symptoms and notification of the neurology resident physician, who then immediately assesses the patient, validates the last known well time and calls a code stroke if indicated. Chi-square or Fisher’s exact test were used for categorical variables; Wilcoxon’s rank sum test was used for the outcomes of SRT to bolus and SRT to puncture. Result: We identified 196 IHS who received emergent treatment: 58 (30%) in Pre and 138 (70%) in Post Intervention (p=0.05). There was no difference in baseline demographics. SRT to thrombolytic administration significantly improved Post Intervention {49 minutes (IQR: 23-268) vs 82 minutes (IQR: 33-220, p<0.05}; Post Intervention SRT to skin puncture time trended towards improvement {90 minutes (IQR: 33-266) vs 110 minutes (IQR: 52-420), p=0.09}. There were no differences in symptomatic intracerebral hemorrhages between the two groups. Conclusion: The implementation of a hospital wide process that focuses on a neurology resident physician and nursing collaboration greatly improves IHS SRT to thrombolytic administration time with a trend towards improvement in SRT to skin puncture time.

Abstract WP42: Transition to Tenecteplase: A Regional Experience

Background: Timely recognition and treatment of acute ischemic stroke is well-supported to promote better outcomes. Historically, alteplase has been the drug of choice for thrombolytic treatment, and while it is an excellent drug, there were barriers that would routinely come up during administration. Following the results of several studies that compared alteplase to tenecteplase, our leadership team decided to initiate the transition to tenecteplase within our region, spanning several states with approximately 40 hospitals. Purpose: The purpose of this clinical initiative was to implement tenecteplase as the primary thrombolytic in acute ischemic stroke and evaluate time to treatment (door in door out [DIDO] and door to needle [DTN]). Methods: Following the approval by leadership, the first step was identification of stakeholders at facility, market, service-line, and regional levels and initiation of bi-weekly meetings. The project relied heavily on facility-level structure that facilitates stroke quality improvement. We were able to utilize market specific stroke databases to understand historical data and to monitor ongoing success and complications. Results: Post-implementation, several positive changes were noted, which are visualized in the graphs. Conclusions: Through reduction of DIDO, treatment is initiated sooner to reperfuse at-risk brain tissue. Further evaluation is needed on the correlation between the transition and decreased length of stay, but we recognize tenecteplase has been shown to have a better rate of recanalizing large vessel occlusions, potentially resulting in less disability and shorter hospitalizations.

Abstract WP84: The 'When' in Response to BEFAST by EMS

Background: In cases of suspected stroke in prehospital patients, EMS response focuses on rapid assessment and transport. In Arkansas, stroke patients are identified by a unique barcode wristband for tracking and quality assurance. Prehospital stroke screens, such as BEFAST (Balance, Eyes, Face, Speech and Time), may influence destination decisions and transport time. We examined utilization of Stroke as a primary impression, compliance with placing stroke bands, if prehospital BEFAST influenced transport times from First Medical Contact (FMC), and which components were associated with rapid transport. Methods: In a single large urban EMS agency, prehospital care records of suspected stroke from Jan 1 to Dec 31, 2022, were retrospectively evaluated utilizing primary or secondary impression of Stroke or Transient Ischemic Attack (TIA). FMC and BEFAST performance time was noted and time intervals of FMC to BEFAST (FMC2BEFAST) and FMC to Arrival at destination (FMC2Arrival). Protocol compliance was determined by the placement of a stroke band. Time measures and BEFAST normal or abnormal scores were determined by ANOVA and protocol compliance with BEFAST with chi-square analysis. Results: There were 224 EMS transports for Stroke/TIA in 2022. Stroke bands were placed in 54% of patients with Stroke/TIA impressions. Stroke was a primary impression in 13% of transports and a secondary impression in 77% of transports. Patients with abnormal BEFAS(T) were 54, 26, 36, 41 and 60%, respectively. Stroke bands were placed in 61, 65, 69, 27 and 62%, respectively of cases with an abnormal BEFAS(T) (p < 0.018). FMC2Arrival time had a 9 min improvement with stroke band placement (p=0.0021). Patients with abnormal Facial Droop (p=0.043) and Eye Disturbance (p=0.022) had significantly shorter FMC2Arrival times. Abnormal Balance, Arm Drift nor Speech was not associated with shorter FMC2Arrival times (p=NS). Conclusions: Rapid evaluation and transport of suspected stroke patients can be challenging. Identification was low in our single center study, abnormalities in Facial Droop and Eye Disturbances resulted in faster transport time. Improved training on the identification and screening may result in a higher stroke band placement, recognition and rapid transport times.

Abstract WP57: Who Needs to Compete When You Can Collaborate? Celebrating 25 Years of Successful Stroke Care

Background: In 2004, Kansas City nurses partnered with the American Stroke Association to provide stroke education to health care providers and the community. Over time, the goal shifted to stroke systems of care. Today this group is known as the Bistate Stroke Consortium, comprised of 34 hospitals and rehab facilities. The group continues to work together to facilitate their mission in a spirit of collegiality and collaboration throughout two states. The communities have also benefited as evidenced by an increase in Primary and Comprehensive Stroke Centers in the region. Methods: In 2021, this Consortium formed a community outreach and stroke leader development sub-committee. Multiple innovative projects were created for both community outreach and stroke leader development to help with educating our region about strokes, celebrating successes, and highlighting best practices from our group. The purpose of this research is to evaluate the effectiveness of these projects. Results: This group placed an emphasis on community and leader education. The group distributed over 10,000 resources in the region and gained substantial community viewership. The group members of the Bistate group provide over 130 hours of education each year including best practices and benchmarked data from GWTG. Notably, during this same period, these two states experienced improvements in stroke related mortality and hospitalizations. The increasing number of patients with stroke symptoms arriving at the hospital via EMS indicates a clear preference for calling 911 and the impact of community education. While the precise factors contributing to these improvements are multifaceted, it is likely that the efforts of this group have played a pivotal role in influencing these positive outcomes. Conclusion: The Bistate Stroke Consortium collaborates to improve patient care, community education, and supports Stroke Coordinators. Stroke mortality and hospitalizations are decreasing in the Consortium's region. Timely stroke recognition by non-healthcare providers and presentation to appropriate healthcare systems are essential to improve outcomes. Continued focus on community outreach and program development is crucial to the Consortium's success.

Abstract WMP25: Implementing a Rapid Response Model to Improve Efficiency of In-Hospital Stroke Code Processes

Introduction: In-hospital stroke (IHS), which occurs during hospitalization for other conditions, presents unique challenges and complexities. Studies have shown IHS is associated with worse patient outcomes, e.g., higher morbidity and mortality, compared to community-onset stroke treated in the emergency department. Time from initial symptom recognition to diagnostic imaging is critical for implementing first line therapy. During IHS, efficient and consistent performance of time-sensitive treatments relies on well-defined roles and parallel processing of tasks. Method: A QI initiative aimed at reducing time from initial stroke symptom recognition to initiation of a non-contrast CT (NCCT) scan was implemented at the start of FY 2022 at our CSC. Focus included broad education of all hospital personnel and their defined role in IHS recognition and care. Program analysis included retrospective and prospective data collected from patients’ electronic health records (EHR) and daily EHR audits for comparison of pre- and post-implementation data (FY 2021 and FY 2022, respectively). Data collection included time of stroke code call (symptom recognition), time of NCCT, and compliance of turn-around-time (TAT) between data points, with a goal of < 20 minutes. Results: An overall increase in the number of IHS code calls between FY 2021 and FY 2022 (n=82 vs. n=106, respectively) was appreciated, with an overall decrease in mean time from stroke recognition to NCCT ( M =22 vs. M =18.3 minutes, respectively). Overall compliance of TAT between these two data points increased from 53% to 73% post QI implementation. Additionally, we experienced an improvement in IHS activation time to IV thrombolytics administration time with a median time of 64.5 minutes (FY 2021, n=8) to median time of 59 minutes (FY 2022). Conclusion: Implementing a system wide QI initiative for IHS with well-defined roles and expectations, and parallel processing of tasks can lead to early recognition and activation of IHS code calls. Improved symptom recognition, code activation, and coordinated response efforts improved time and compliance to initial imaging as well as time to thrombolytic administration in our patient population.

Orange peel-like triboelectric nanogenerators with multiscale micro-nano structure for energy harvesting and touch sensing applications

With the continuous advancements in technology, triboelectric nanogenerators (TENGs) have gained significant traction as efficient harnessers of low-frequency mechanical energy to meet the escalating energy demands. Notably, employing solid polymer electrolyte (SPE) as a contact layer or optimizing the microstructural composition of the surface material represents a prevalent strategy for augmenting the output performance of TENGs. However, the fabrication of numerous microstructures poses significant challenges, particularly in terms of incorporating environmentally harmful materials. Moreover, the utilization of triboelectric nanogenerators is further constrained by limitations associated with electrode materials. Although various techniques are available for producing transparent and stretchable electrodes for such generators, these procedures can be intricate and necessitate the use of hazardous chemicals. In this study, we exploit Poly(vinyl alcohol) (PVA) and natural bacterial cellulose (BC) nanofibers to fabricate contact layers with OP structures characterized by micron-scale domes and nanoscale microcracks. The electrodes were fabricated using BC hydrogel and ionic liquids(ILs). Under the action of hydrogen bond topological network, a multi-scale structure is formed comprising of a molecular-scale interlacing network of hydrogen bonds and a nanoscale fiber skeleton, which synergistically confer the ionic gel with remarkable tensile strength and high ionic conductivity (up to 83.51mS/cm). The resulting OP-TENG exhibited an output open-circuit voltage of 280 V, a short-circuit current of 24μA, and a maximum power density of 5.6 W m−2, enabling it to illuminate up to 303 LEDs. A SSEM-TENG was devised by stacking two single electrode mode TENGs on top of each other using a single wire. This innovative design holds great potential for applications in wearable motion monitoring, high-precision writing stroke recognition, and low-frequency mechanical energy harvesting.

A Review of an Interfacility Transport Program Pediatric Stroke Clinical Practice Guideline.

Pediatric acute ischemic stroke is a rare diagnosis that requires timely recognition and definitive management to prevent morbidity and mortality. Children often present to primary care offices, urgent care clinics, and adult emergency departments for evaluation of symptoms that may be signs and symptoms of stroke. Currently, there are no published prehospital or transport protocols specific to pediatric acute ischemic stroke. The Children's Mercy Hospital Critical Care Transport Team (CMCCT) created a pediatric-specific clinical practice guideline (CPG) for suspected acute ischemic stroke. This retrospective, descriptive study reports pediatric patients aged younger than 18 years who met criteria for the pediatric stroke CPG and required interfacility transport by CMCCT over a 4- year period. Large vessel occlusion (LVO) scores used in adults were calculated retrospectively. Seventeen patients met inclusion criteria. Four (24%) of 17 had radiographic evidence of acute thrombus, 3 of whom received alteplase and/or endovascular clot retrieval. Median age of confirmed stroke was 83 months (interquartile range, 65-148) compared with 177 months for nonstroke (interquartile range, 169-191), P = 0.126. The most common presenting symptom was hemiplegia in the confirmed stroke group. The confirmed stroke group scored significantly lower on the Glasgow Coma Scale (median of 8 vs 15, P = 0.014), significantly higher on the Los Angeles Motor Scale LVO score (median 4 vs 0, P = 0.021), and significantly higher on the Rapid Arterial Occlusion Evaluation LVO (median 4 vs 0, P = 0.036). To our knowledge, the CMCCT CPG is the first pediatric transport protocol aimed at recognition and management of pediatric stroke described in the literature. Retrospective calculation of LVO scores show that they may be helpful in application to pediatric patients.

TIME IS BRAIN: ASSESSING EMERGENCY HEALTHCARE WORKERS KNOWLEDGE OF EARLY RECOGNITION OF STROKE AND WARNING SIGNS

Background: A stroke, also known as a cerebrovascular accident (CVA), has a profound impact on the human brain. Early recognition and successful treatment of strokes not only enhance patients clinical outcomes but also play a crucial role in preventing fatalities. The knowledge of strokes is highly significant for Emergency Medical Services (EMS) and nurses. In order to evaluate the level of awareness, this audit was conducted in the Emergency Department (ED) of a prominent tertiary care center in Eastern India. Methodology: This study primarily involved EMS and ED nurses. A self-administered questionnaire consisting of three sections was employed to assess their level of awareness regarding stroke. The questionnaire covered various factors, which were then coded, and a basic analysis was conducted using Microsoft Excel. Results: A total of 52 participants, including nurses, EMS personnel, and students took part in the questionnaire-based audit. The mean age of 27.83 years (SD: 7.56), with a notable percentage holding a General Nurse Midwifery (GNM) degree. Around 75% (n: 37) of the participants had received BLS/ACLS training within the past 1-2 years. It was concerning to find that a significant number of nurses and EMS personnel who frequently attended ambulance calls provided incorrect responses to a question regarding the appropriate destination for suspected stroke patients. However, the majority demonstrated good awareness of warning signs, clinical manifestations, and diagnostic procedures related to acute stroke patients. Only a small fraction (one-tenth) of the participants accurately identified the time window for thrombolysis in stroke cases, and few could recognize patients who may require definitive airway intervention. Conclusion: The majority of participants showed insufficient knowledge regarding the appropriate disposition of stroke patients and correctly identifying the window period for thrombolysis. However, they demonstrated a strong understanding of warning signs, clinical manifestations, and diagnostic procedures associated with acute stroke patients.

Knowledge on Stroke Recognition and Management among Emergency Department Healthcare Professionals in the Republic of Cyprus.

Stroke is a global leading cause of death and disability. Knowledge of related guidelines is crucial for emergency department (ED) staff, influencing early diagnosis and timely treatment. We investigated Greek Cypriot ED healthcare professionals' (nurses and physicians) knowledge in recognizing and managing stroke. A descriptive cross-sectional study spanned November 2019 to April 2020, encompassing four private and seven public EDs in the Republic of Cyprus. The data were collected through a self-reported questionnaire developed by the research team, consisting of 37 questions. Eight questions focused on sociodemographic and employment characteristics, twenty-eight assessed knowledge in stroke recognition and management (each item was equally weighted without deliberate prioritization), and one question addressed self-assessment of knowledge in stroke care. A total of 255 nurses (response rate (RR): 74.1%) and 26 physicians (RR: 47.3%) completed the questionnaire. The average correct response rate was 12.9 out of 28 statements (SD: 4.2), with nurses and physicians scoring 12.6 (SD: 4.1) and 15.7 (SD: 4), respectively. Work experience significantly influenced stroke knowledge, with all groups demonstrating superiority over those with less than one year of experience. Participants with previous training scored an average of 1.45 additional correct answers while educational attainment did not significantly influence stroke knowledge. Investigating stroke knowledge among emergency department nurses and physicians in the Republic of Cyprus revealed significant deficits. This study stresses targeted interventions, including education, yearly examinations, workshops with hands-on training, and repeated training, to address these gaps and enhance the overall stroke care capabilities of the healthcare professionals.

Application of Computer Vision-based Chinese Painting Stroke Recognition and Simulation System

Application of Computer Vision-based Chinese Painting Stroke Recognition and Simulation System

A retrospective study on machine learning-assisted stroke recognition for medical helpline calls

Advanced stroke treatment is time-dependent and, therefore, relies on recognition by call-takers at prehospital telehealth services to ensure fast hospitalisation. This study aims to develop and assess the potential of machine learning in improving prehospital stroke recognition during medical helpline calls. We used calls from 1 January 2015 to 31 December 2020 in Copenhagen to develop a machine learning-based classification pipeline. Calls from 2021 are used for testing. Calls are first transcribed using an automatic speech recognition model and then categorised as stroke or non-stroke using a text classification model. Call-takers achieve a sensitivity of 52.7% (95% confidence interval 49.2–56.4%) with a positive predictive value (PPV) of 17.1% (15.5–18.6%). The machine learning framework performs significantly better (p < 0.0001) with a sensitivity of 63.0% (62.0–64.1%) and a PPV of 24.9% (24.3–25.5%). Thus, a machine learning framework for recognising stroke in prehospital medical helpline calls may become a supportive tool for call-takers, aiding in early and accurate stroke recognition.

Predictive stroke risk model with vision transformer-based Doppler features.

Acute stroke is the leading cause of death and disability globally, with an estimated 16 million cases each year. The progression of carotid stenosis reduces blood flow to the intracranial vasculature, causing stroke. Early recognition of ischemic stroke is crucial for disease treatment and management. A computer-aided diagnosis (CAD) system was proposed in this study to rapidly evaluate ischemic stroke in carotid color Doppler (CCD). Based on the ground truth from the clinical examination report, the vision transformer (ViT) features extracted from all CCD images (513 stroke and 458 normal images) were combined in machine learning classifiers to generate the likelihood of ischemic stroke for each image. The pretrained weights from ImageNet reduced the time-consuming training process. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve were calculated to evaluate the stroke prediction model. The chi-square test, DeLongtest, and Bonferroni correction for multiple comparisons were applied to deal with the type-I error. Only p values equal to or less than 0.00125 were considered to be statistically significant. The proposed CAD system achieved an accuracy of 89%, a sensitivity of 94%, a specificity of 84%, and an area under the receiver operating characteristic curve of 0.95, outperforming the convolutional neural networks AlexNet (82%, p<0.001), Inception-v3 (78%, p<0.001), ResNet101 (84%, p<0.001), and DenseNet201 (85%, p<0.01). The computational time in model training was only 30 s, which would be efficient and practical in clinical use. The experiment shows the promising use of CCD images in stroke estimation. Using the pretrained ViT architecture, the image features can be automatically and efficiently generated without human intervention. The proposed CAD system provides a rapid and reliable suggestion for diagnosing ischemic stroke.

Simulated Patients to Demonstrate Common Stroke Syndromes: Accurate and Convincing

Introduction: Stroke detection in the preclinical setting is challenging, resulting in more than 1/3 of missed strokes by emergency medical services (EMS) personnel. Recently, prehospital identification of anterior large vessel occlusion (LVO) stroke has come into focus. Cortical signs have a high predictive value for the presence of LVO stroke but are often missed. Simulated patients (SPs) could be an excellent tool to train EMS personnel in the evaluation of stroke syndromes with cortical symptoms, but it has not been studied whether they can simulate these important signs convincingly. The main objective of this study was, thus, to examine whether SPs can simulate stroke syndromes and symptoms so that stroke experts can identify them correctly and reliably, applying the NIH stroke scale (NIHSS). Methods: Lay actors were trained to simulate one of 8 stroke syndromes either typical of a lacunary stroke or of an anterior LVO stroke and then videotaped during an examination according to the NIHSS. Stroke experts were asked to rate each item of the NIHSS based on the videos, determine which stroke syndrome was being demonstrated, and rate the quality of simulation. The primary outcome was the correct identification of the target stroke syndrome by the expert raters. Secondary outcomes were the agreement of the rating of the NIHSS score with the target NIHSS score and the expert raters’ assessment of the quality of simulation. Results: Seven of eight syndromes were rated correctly by at least twelve of fifteen raters and the mean rated NIHSS score was within one point of the target score for six of eight syndromes. The mean rating for the quality of simulation was between 3.54 and 3.98 (as rated on a scale from 1 to 4) for each syndrome. Discussion/Conclusion: SPs are capable of simulating acute stroke symptoms and syndromes accurately and convincingly. Thus, they represent a great resource to improve educational interventions that improve stroke recognition.

Large‐Vessel Occlusion Stroke Knowledge and Training for Stroke Severity Assessment Among Emergency Medical Services Personnel in the United States

BACKGROUND Prehospital identification of large‐vessel occlusion (LVO) stroke facilitates the development of a regional triage protocol that could lead to an improvement in intrahospital and interhospital workflows. This requires stroke education of emergency medical services (EMS) personnel to improve stroke recognition, severity assessment, and prenotification. However, the current state of EMS personnel's knowledge of LVO stroke, their training for stroke severity assessment, and their preferences for educational methods are unknown. We conducted a nationwide EMS survey across the United States to glean insights that can inform and customize future EMS educational efforts. METHODS The Society of Vascular and Interventional Neurology, in collaboration with EMS World , created an online questionnaire for EMS personnel. It included 12 multiple‐choice and free‐response questions designed to test participants’ clinical knowledge of LVO, knowledge of stroke center certification levels, prior LVO educational experiences, preferences for educational content delivery, and perspectives on prehospital hurdles to stroke care. All subscribers of EMS World received a survey link via email. RESULTS Of the 38 486 subscribers of EMS World , the survey email was opened by 1830, of whom 1107 completed the survey across all states in the United States, with a response rate of 2.9%. Most of the respondents identified themselves as paramedics/emergency medical technicians (91%). The number of patients with stroke that survey participants transported in the past year was &lt;10 for 618 (56%). Only 285 (26%) participants answered both LVO knowledge questions correctly, and only 128 (12%) respondents correctly identified all types of stroke centers with thrombectomy capability. A total of 362 EMS personnel (33%) denied receiving training to perform LVO severity assessment. Respondents who received training to perform an LVO scale demonstrated nearly twice the prevalence of LVO knowledge (30.6% versus 15.7%; prevalence ratio, 1.94 [95% CI, 1.50–2.53]) than respondents who did not receive training. The top hurdle to prehospital LVO education was identified as the lack of standardized LVO training by 535 (48%) respondents. CONCLUSIONS EMS providers in the United States reported inadequate LVO training and demonstrated gaps in knowledge of LVO, stroke severity scales, and stroke center levels. Systematic efforts to enhance and standardize the educational content and delivery of LVO education are needed.

Abstract 300: An Opportunity for Awareness: The International Academy of Emergency Medical Dispatch's Stroke Diagnostic Tool is Predictive, but Underutilized, for Hospital Confirmed Large Vessel Occlusion Strokes

Background: Accurate identification of ischemic stroke from large vessel occlusion (LVO) by 9-1-1 professionals can facilitate prompt patient transfer to stroke centers that perform endovascular thrombectomy. We sought to determine the proportion of LVO stroke patients that were evaluated using the Medical Priority Dispatch System's (MPDS) Stroke Diagnostic Tool (SDxT). Methods: Structured, retrospective review of our institution’s stroke registry, EMS Records, and dispatch codes between January 1, 2019 and November 30, 2022. Inclusion: Adult (age &gt;17), accessed the 9-1-1 system and transported by a ground EMS agency for an acute stroke. Exclusion: age &lt;18, pregnant, incarcerated, cases with missing 9-1-1 data, and intracranial hemorrhage. Two trained/monitored abstractors, blinded to the study purpose, used a standardized data collection tool/dictionary to extract data. Data included MPDS codes, SDxT outcome, EMS care, demographics, hospital NIHSS score, advanced imaging, tPA administration, and mechanical thrombectomy. Primary outcome: the proportion of LVO cases that had an acute stroke (28 protocol) dispatch code. Secondary outcome: the proportion of LVO cases that that a SDxT score indicating “strong or clear evidence of a stroke”. We report proportions and 95% CI's as appropriate. Results: 60 patients met inclusion/exclusion criteria. 11/60, 18.3 % (95%CI= 10.4, 30) of the patients had complete data and a LVO. 54% were male, the median (IQR) age was 69.5 (61.3-77.5), and the median (IQR) NIHSS was 16 (5-19.75). Primary outcome: 45.5 % (95% CI= 21.3.72.0) of the LVO’s were coded as an Acute Stroke by the 9-1-1 center. Of those, 3/5 utilized the stroke diagnostic tool, all 3 of these were determined to have "Clear Evidence of Stroke". Limitations: Retrospective, unlinked data, small number of LVO's. Conclusion: When utilized, the SDxT correctly identified all LVO’s. There is an opportunity to increase awareness and utilization of the SDxT by 9-1-1 centers. Future research should focus on identifying barriers to stroke recognition and provide additional tools to address the real-life challenges our 9-1-1 communications specialists face when rapidly assessing for an acute stroke over the phone.

Design of a school-based stroke preparedness intervention: challenges in acute diseases recognition

Abstract Background Timely activation of emergency medical services (EMS) by bystanders is important and it can improve outcomes of acute diseases such as stroke in Europe. Since there are no effective interventions addressing the complexity of help-seeking behaviour in the event of stroke, this study describes the development of the Czech “HOBIT” programme, which educates secondary school children to correctly activate the EMS. Methods Intervention Mapping was used to guide the development of the intervention using theory and evidence, as well as principles of co-creation. A needs assessment was completed by reviewing the evidence and interviewing stroke survivors. It identified sub-behaviours and their determinants. The information obtained was utilised to select the methods of behaviour change and their practical applications. In the last phase, the intervention tools were created. Results The needs assessment revealed stroke recognition and assessment as well as ambulance call as the main behaviours that must be done for EMS activation. Risk perception, outcome expectations, social influences, knowledge, and skills were revealed as important determinants of above behaviours. Modelling was selected as a method for the behaviour change. Based on discussions with 157 children aged 11-15, the format of an entertainment-education video was chosen. Incorporation of the modelling parameters (engagement, transplantation, identification) into the video was assessed during discussions with 15 children (scored &amp;gt;4 on the 5-point scale). As a result, a 5-minute entertainment video, modelling an acute stroke with a child as the main bystander was created. Conclusions The innovative educational video teaches children to correctly activate the EMS in stroke by modelling a real-life situation. Our results enable future projects to build on our findings to create the intervention for supporting behaviours in acute events that cannot be trained by direct experience. Key messages • Using the systematic approach built on co-creation with stakeholders is a significant foundation for the development of an effective intervention to improve timely activation of the EMS in stroke. • The current paper provides a comprehensive roadmap to help health promoters approach structured planning for behaviour change in acute diseases response.