Cincinnati Prehospital Stroke Scale Research Articles

MAMAF-Net: Motion-aware and multi-attention fusion network for stroke diagnosis

Stroke is a major cause of mortality and disability worldwide from which one in four people are in danger of incurring in their lifetime. The pre-hospital stroke assessment plays a vital role in identifying stroke patients accurately to accelerate further examination and treatment in hospitals. Accordingly, the National Institutes of Health Stroke Scale (NIHSS), Cincinnati Pre-hospital Stroke Scale (CPSS) and Face Arm Speed Time (F.A.S.T.) are globally known tests for stroke assessment. However, the validity of these tests is skeptical in the absence of neurologists and access to healthcare may be limited. Therefore, in this study, we propose a motion-aware and multi-attention fusion network (MAMAF-Net) that can detect stroke from multiple examination videos. Contrary to other studies on stroke detection from video analysis, our study for the first time collected a dataset encapsulating transient ischemic attack (TIA), stroke, and healthy controls, and proposes an end-to-end solution using multiple video recordings of each subject. The proposed MAMAF-Net consists of motion-aware modules to sense the mobility of patients, attention modules to fuse the multi-input video data, and 3D convolutional layers to perform diagnosis from the attention-based extracted features. Experimental results over the collected Stroke-data dataset show that the proposed MAMAF-Net achieves a successful detection of stroke with the highest levels of 93.62% sensitivity, 91.19% F1-Score, and 0.7472 Kappa measure in addition to 3.92% increase in the AUC score compared to state-of-the-art deep learning models.

Optimization of the stroke hospital selection strategy and the distribution of endovascular thrombectomy resources.

Nowadays, emergency medical technicians (EMTs) decide to send a suspected stroke patient to a primary stroke center (PSC) or to an endovascular thrombectomy (EVT)-capable hospital, based on the Cincinnati Prehospital Stroke Scale (CPSS) and the number of symptoms a patient presents at the scene. Based on existing studies, the patient is likely to have a better functional outcome after three months if the time between the onset of symptoms and receiving EVT treatment is shorter. However, if an acute ischemic stroke (AIS) patient with large vessel occlusion (LVO) is first sent to a PSC, and then needs to be transferred to an EVT-capable hospital, the time to get definitive treatment is significantly increased. For this purpose, We formulate an integer programming model to minimize the expected time to receive a definitive treatment for stroke patients. We then use real-world data to verify the validity of the model. Also, we expand our model to find the optimal redistribution and centralization of EVT resources. It will enable therapeutic teams to increase their experience and skills more efficiently within a short period of time.

Sex Differences in Prehospital Identification of Large Vessel Occlusion in Patients With Suspected Stroke.

Differences in clinical presentation of acute ischemic stroke between men and women may affect prehospital identification of anterior circulation large vessel occlusion (aLVO). We assessed sex differences in diagnostic performance of 8 prehospital scales to detect aLVO. We analyzed pooled individual patient data from 2 prospective cohort studies (LPSS [Leiden Prehospital Stroke Study] and PRESTO [Prehospital Triage of Patients With Suspected Stroke Study]) conducted in the Netherlands between 2018 and 2019, including consecutive patients ≥18 years suspected of acute stroke who presented within 6 hours after symptom onset. Ambulance paramedics assessed clinical items from 8 prehospital aLVO detection scales: Los Angeles Motor Scale, Rapid Arterial Occlusion Evaluation, Cincinnati Stroke Triage Assessment Tool, Cincinnati Prehospital Stroke Scale, Prehospital Acute Stroke Severity, gaze-face-arm-speech-time, Conveniently Grasped Field Assessment Stroke Triage, and Face-Arm-Speech-Time Plus Severe Arm or Leg Motor Deficit. We assessed the diagnostic performance of these scales for identifying aLVO at prespecified cut points for men and women. Of 2358 patients with suspected stroke (median age, 73 years; 47% women), 231 (10%) had aLVO (100/1114 [9%] women and 131/1244 [11%] men). The area under the curve of the scales ranged from 0.70 (95% CI, 0.65-0.75) to 0.77 (95% CI, 0.73-0.82) in women versus 0.69 (95% CI, 0.64-0.73) to 0.75 (95% CI, 0.71-0.79) in men. Positive predictive values ranged from 0.23 (95% CI, 0.20-0.27) to 0.29 (95% CI, 0.26-0.31) in women versus 0.29 (95% CI, 0.24-0.33) to 0.37 (95% CI, 0.32-0.43) in men. Negative predictive values were similar (0.95 [95% CI, 0.94-0.96] to 0.98 [95% CI, 0.97-0.98] in women versus 0.94 [95% CI, 0.93-0.95] to 0.96 [95% CI, 0.94-0.97] in men). Sensitivity of the scales was slightly higher in women than in men (0.53 [95% CI, 0.43-0.63] to 0.76 [95% CI, 0.68-0.84] versus 0.49 [95% CI, 0.40-0.57] to 0.63 [95% CI, 0.55-0.73]), whereas specificity was lower (0.79 [95% CI, 0.76-0.81] to 0.87 [95% CI, 0.84-0.89] versus 0.82 [95% CI, 0.79-0.84] to 0.90 [95% CI, 0.88-0.91]). Rapid arterial occlusion evaluation showed the highest positive predictive values in both sexes (0.29 in women and 0.37 in men), reflecting the different event rates. aLVO scales show similar diagnostic performance in both sexes. The rapid arterial occlusion evaluation scale may help optimize prehospital transport decision-making in men as well as in women with suspected stroke.

Abstract WP47: Creation of a Pediatric Stroke Alert Protocol

Background: In 2021, our Comprehensive Stroke Center (CSC) in San Antonio (SA), Texas received 7 pediatric patients suffering from signs and symptoms of stroke. These patients ranged in age from 4-17 and approximately 57% were positive for an acute ischemic stroke (AIS). During the month of March, 2 patients were brought in via EMS and both MRIs were positive for AIS, prompting our stroke team to evaluate our adult processes. We concluded that an Emergency Department (ED) Pediatric Stroke Alert Protocol was needed in order for our hospital to have the capability to care for this patient population, and also appropriately triage and offer acute therapies to give these patients the best chance possible. Purpose: Develop an ED Pediatric Stroke Alert Protocol in order to provide rapid triage and advanced therapies if warranted. The ED Pediatric Stroke Alert protocol was developed with our same stroke alert time frame in mind, 0-6 hours, and with the age range of 2-17 years. Methods: An interdisciplinary team consisting of Vascular neurology, Pediatric Neurology, Pediatric Hematology/Oncology, Pediatric Critical Care nursing, Pediatric / Adult ED nursing & Faculty, Neuro Critical Care, Pharmacy, and our Stroke Team met to discuss how to implement a pediatric protocol. It was decided that modeling it after the Adult ED Stroke Alert Protocol would be best to limit confusion and triage errors. The Cincinnati Stroke Scale was used as the tool of choice in order for our ED team to identify stroke symptoms, also a time frame of less than 6 hours from onset of symptoms AND a blood glucose between 60 and 600. This would then prompt the activation of the Pedi ED Stroke Alert Protocol. Triage on the protocol includes inclusion and exclusion criteria for IV tPA, which was also tailored to the pediatric population with the help of Pediatric Hematology/Oncology. Results: The ED Pedi SA Protocol has since been revised to meet the needs of our changing pediatric stroke population. The CSC continues to treat pediatric patients and continues to develop other tools to meet the needs of this population. Conclusion: Our CSC has been categorized by EMS as one of the only CSCs in SA, Texas that is capable of providing complete stroke care to the pediatric population.

Early identification of stroke through deep learning with multi-modal human speech and movement data

JOURNAL/nrgr/04.03/01300535-202501000-00031/figure1/v/2024-05-10T114357Z/r/image-tiff Early identification and treatment of stroke can greatly improve patient outcomes and quality of life. Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale (CPSS) and the Face Arm Speech Test (FAST) are commonly used for stroke screening, accurate administration is dependent on specialized training. In this study, we proposed a novel multimodal deep learning approach, based on the FAST, for assessing suspected stroke patients exhibiting symptoms such as limb weakness, facial paresis, and speech disorders in acute settings. We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements, facial expressions, and speech tests based on the FAST. We compared the constructed deep learning model, which was designed to process multi-modal datasets, with six prior models that achieved good action classification performance, including the I3D, SlowFast, X3D, TPN, TimeSformer, and MViT. We found that the findings of our deep learning model had a higher clinical value compared with the other approaches. Moreover, the multi-modal model outperformed its single-module variants, highlighting the benefit of utilizing multiple types of patient data, such as action videos and speech audio. These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke, thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.

Cincinnati Prehospital Stroke Scale (CPSS) as a Screening Tool for Early Identification of Cerebral Large Vessel Occlusions; a Systematic Review and Meta-analysis.

Large vessel occlusion (LVO) strokes are associated with worse functional outcomes and higher mortality rates. In the present systematic review and meta-analysis, we evaluated the diagnostic yield of the Cincinnati Prehospital Stroke Scale (CPSS) in detecting LVO. We performed an extensive systematic search among online databases including Medline, Embase, Web of Science, and Scopus, until July 31st, 2023. We also conducted a manual search on Google and Google scholar, along with citation tracking to supplement the systematic search in retrieving all studies that evaluated the diagnostic accuracy of the CPSS in detecting LVO among patients suspected to stroke. Fourteen studies were included in the present meta-analysis. CPSS showed the sensitivity of 97% (95% CI: 87%-99%) and the specificity of 17% (95% CI: 4%-54%) at the cut-off point of ≥1. The optimal threshold was determined to be ≥2, with a sensitivity of 82% (95% CI: 74%-88%) and specificity of 62% (95% CI: 48%-74%) in detecting LVO. At the highest cut-off point of ≥3, the CPSS had the lowest sensitivity of 60% (95% CI: 51%-69%) and the highest specificity of 81% (95% CI: 71%-88%). Sensitivity analyses showed the robustness of the results regardless of study population, inclusion of hemorrhagic stroke patients, pre-hospital or in-hospital settings, and the definition of LVO. A very low level of evidence demonstrated that CPSS, with a threshold set at ≥2, is a useful tool for identifying LVO stroke and directing patients to CSCs, both in prehospital and in-hospital settings.

Changing the stroke network during pandemic scenarios does not affect the management of patients with a positive Cincinnati prehospital stroke scale.

Time plays a crucial role in the management of stroke, and changing the prehospital emergency network, altering the HUB and spoke relationship in pandemic scenarios, might have an impact on time to fibrinolysis or thrombectomy. The aim of this study was to evaluate the time-dependent stroke emergency network in Lombardy region (Italy) by comparing 2019 with 2020 and early 2021. Three parameters were investigated: (i) time of arrival of the first vehicle at the scene, (ii) overall duration of missions, and (iii) number of patients transported by emergency vehicles. Data analysis process conducted using the SAS-AREU portal (SAS Institute, USA). The number of patients with a positive CPSS was similar among the different pandemic waves. Mission duration increased from a mean time (SD) of 52.9 (16.1) min in 2019 to 64.1 (19.7) in 2020 and 55.0 (16.8) in 2021. Time to first vehicle on scene increased to 15.7 (8.4) min in 2020 and 16.0 (7.0) in 2021 compared to 2019, 13.6 (7.2) (P < 0.05). The number of hospital with available stroke units decreased from 46 in 2019 to 10 during the first pandemic wave. The pandemic forced changes in the clinical mission of many hospitals by reducing the number of stroke units. Despite this, the organization of the emergency system allowed to identify strategic hospitals and thus avoid excessive transport time. The result was an adequate time for fibrinolysis/thrombectomy, in agreement with the guidelines. Coordinated management in emergency situations makes it possible to maintain service quality standards, despite the unfavorable scenario.

Inter-Rater Agreement on Cincinnati Prehospital Stroke Scale (CPSS) and Prehospital Acute Stroke Severity Scale (PASS) Between EMS Providers, Neurology Residents and Neurology Consultants.

To examine the agreement between emergency medical service (EMS) providers, neurology residents and neurology consultants, using the Cincinnati Prehospital Stroke Scale (CPSS) and the Prehospital Acute Stroke Severity Scale (PASS). Patients with stroke, transient ischemic attack (TIA) and stroke mimic were included upon primary stroke admission or during rehabilitation. Patients were included from June 2018 to September 2019. Video recordings were made of patients being assessed with CPSS and PASS. The recordings were later presented to the healthcare professionals. To determine relative and absolute interrater reliability in terms of inter-rater agreement (IRA), we used generalisability theory. Group-level agreement was determined against a gold standard and presented as an area under the curve (AUC). The gold standard was a consensus agreement between two neurology consultants. A total of 120 patient recordings were assessed by 30 EMS providers, two neurology residents and two neurology consultants. Using the CPSS and the PASS, a total of 1,800 assessments were completed by EMS providers, 240 by neurology residents and 240 by neurology consultants. The overall relative and absolute IRA for all items combined from the CPSS and PASS score was 0.84 (95% CI 0.80; 0.87) and 0.81 (95% CI 0.77; 0.85), respectively. Using the CPSS, the agreement on a group-level resulted in AUCs of 0.83 (95% CI 0.78; 0.88) for the EMS providers and 0.86 (95% CI 0.82; 0.90) for the neurology residents when compared with the gold standard. Using the PASS, the AUC was 0.82 (95% CI 0.77; 0.87) for the EMS providers and 0.88 (95% CI 0.84; 0.93) for the neurology residents. The high relative and absolute inter-rater agreement underpins a high robustness/generalisability of the two scales. A high agreement exists across individual raters and different groups of healthcare professionals supporting widespread applicability of the stroke scales.

A nomogram-based clinical tool for acute ischemic stroke screening in prehospital setting.

Background: We believe that designing a new tool which is comparable in terms of both sensitivity and specificity may play an important role in rapid and more accurate diagnosis of acute ischemic stroke (AIS) in prehospital stage. Therefore, we intended to develop a new clinical tool for the diagnosis of AIS in the prehospital stage. Methods: This was a cross-sectional diagnostic accuracy study. All patients transferred to the emergency department (ED) who underwent brain magnetic resonance imaging (MRI) with impression of AIS were evaluated by 9 clinical tools for stroke diagnosis in the pre-hospital phase including Rapid Arterial Occlusion Evaluation (RACE), Cincinnati Prehospital Stroke Scale (CPSS), Los Angeles Prehospital Stroke Screen (LAPSS), Melbourne Ambulance Stroke Screen (MASS), Medic Prehospital Assessment for Code Stroke (Med PACS), Ontario Prehospital Stroke Screening Tool (OPSS), PreHospital Ambulance Stroke Test (PreHAST), Recognition of Stroke in the Emergency Room (ROSIER), and Face Arm Speech Test (FAST), and totally 19 items were reviewed and recorded. The new clinical tool was developed based on backward method of multivariable logistic regression analysis. The discrimination power of the new clinical tool for diagnosis of AIS was assessed with the area under the receiver operating characteristic curve (AUC-ROC). Results: Data from 806 patients were analyzed; of them, 57.4% were men. The mean age of the study patients was 66.9 years [standard deviation (SD) = 13.9]. In the multivariable model, 8 items remained. The AUC-ROC of the new clinical tool was 0.893 [95% confidence interval (CI): 0.869-0.917], and its best cut-off point was score ≥ 3 for positive AIS. At this cut-off point, sensitivity and specificity were 84.42% and 79.72%, respectively. Conclusion: We introduced a new nomogram-based clinical tool for the diagnosis of AIS in the prehospital stage, which has acceptable specificity and sensitivity; moreover, it is comparable with previous tools.

Effect of using G-FAST to recognize emergent large vessel occlusion: A city-wide community experience

A prehospital bypass strategy was suggested for large vessel occlusion. This study aimed to evaluate the effect of a bypass strategy using the gaze-face-arm-speech-time test (G-FAST) implemented in a metropolitan community. Pre-notified patients with positive Cincinnati Prehospital Stroke Scale and symptom onset <3h from July 2016 to December 2017 (pre-intervention period) and those with positive G-FAST and symptom onset <6h from July 2019 to December 2020 (intervention period) were included. Patients aged <20 years and those with missing in-hospital data were excluded. The primary outcomes were the rates of receiving endovascular thrombectomy (EVT) and intravenous thrombolysis (IVT). The secondary outcomes were total prehospital time, door-to-computed tomography (CT) time, door-to-needle (DTN) time, and door-to-puncture (DTP) time. We included 802 and 695 pre-notified patients from the pre-intervention and intervention periods, respectively. The characteristics of the patients in the two periods were similar. In the primary outcomes, pre-notified patients during the intervention period showed higher rates of receiving EVT (4.49% vs. 15.25%, p<0.001) and IVT (15.34% vs. 21.58%, p=0.002). In the secondary outcomes, pre-notified patients during intervention period had longer total prehospital time (mean 23.38 vs 25.23min, p<0.001), longer door-to-CT time (median 10 vs 11min, p<0.001), longer DTN time (median 53 vs 54.5min, p<0.001) but shorter DTP time (median 141 vs 139.5min, p<0.001). The prehospital bypass strategy with G-FAST showed benefits for stroke patients.

Impact of bilingual face, arm, speech, time (FAST) public awareness campaigns on emergency medical services (EMS) activation in a large Canadian metropolitan area.

Face, arm, speech, time (FAST) public awareness campaigns improve stroke recognition in the general population. Whether this translates into improved emergency medical services (EMS) activation remains unclear. We assessed the association of five consecutive FAST campaigns with EMS calls for suspected strokes in a large urban area of Quebec, Canada. We conducted an observational study to assess data collected between June 2015 and December 2019 by the public EMS agency covering the cities of Laval and Montreal (Quebec, Canada). Five FAST campaigns were held over this period (mean duration: 9weeks). We compared daily EMS calls before and after all FAST campaigns (2015 vs 2019) with t tests and Mann-Whitney U tests. We used single-group, univariate interrupted time series to measure changes in daily EMS calls for suspected strokes following each FAST campaign (stroke categories: any, symptom onset < 5h, Cincinnati Prehospital Stroke Scale [CPSS] 3/3). Calls for headache served as negative control. After five FAST campaigns, mean daily EMS calls increased by 28% (p < 0.001) for any suspected stroke and by 61% (p < 0.001) for stroke with symptom onset < 5h, compared to 10.1% for headache (p = 0.012). Significant increases in daily EMS calls were observed after three campaigns (highest OR = 1.26; 95%CI 1.11, 1.43; p < 0.001). There were no significant changes in calls after individual campaigns for suspected stroke with symptom onset < 5h, or suspected stroke with CPSS 3/3. We observed an inconsistent impact of individual FAST campaigns on EMS calls for any suspected stroke, and did not observe significant EMS call changes after individual campaigns for acute (< 5h) and severe (CPSS 3/3) strokes. These results may help stakeholders identify potential benefits and limitations of public awareness campaigns using the FAST acronym.

Abstract TP51: Establishing Stroke Pre-alert Criteria Reduces Delays In Endovascular Management

Background: Mechanical thrombectomy (MT) is standard of care for patients with cerebral large vessel occlusions (LVO). Efficacy of MT depends on the timeliness of reperfusion. Establishing a pre-alert criteria to activate the stroke team prior to patient arrival in the emergency department (ED) may help rapidly identify candidates for MT. Objective: To determine whether establishment of pre-alert criteria can improve door-to-groin (DTG) and door-to-reperfusion (DTR) times. Methods: We retrospectively reviewed electronic prehospital and hospital records of stroke-alerted patients prior to (pre-protocol) and after (post-protocol) implementation of our stroke pre-alert protocol. We initiated our protocol in November 2022 to pre-alert patients that EMS found with (1) positive on Cincinnati Pre-Hospital Stroke Scale with last known well (LKW) &lt;4.5 hours or positive CPSS and Vision-Aphasia-Neglect with LKW &lt;24 hours, (2) Glasgow Coma Score &gt;8, (3) glucose 60-400mg/dL, (4) systolic blood pressure &gt;90, (5) oxygen saturation &gt;90%, and (6) no seizures at presentation. Patients stroke-alerted in the ED prior to protocol (April 1, 2020-November 10, 2021) were historical controls. Results: EMS presented 667 (49% female) patients to our hospital, of which 195 patients arrived after pre-alert protocol initiation. Among post-protocol patients, 13.8% (27/195) underwent MT, while 11% (52/472) of pre-protocol patients underwent MT. Among patients who underwent MT, 26 post-protocol patients (96%) and 22 pre-protocol patients (42%) were pre-alerted [X 2 =21, p&lt;0.001]. Mean DTR decreased by 63.83 minutes in post-change group [19.83-115.85]. Mean DTG decreased by 65.26 minutes in post-change group [36.54-102.90]. Conclusion: Establishment of a reasonable pre-alert criteria facilitates stroke alert activation and reduces time to MT intervention in patients presenting to the ED with an LVO. More studies are needed to determine an optimal pre-alert criteria to further reduce MT delays.

Abstract TP5: Helicopter Emergency Medical Services (HEMS) Transportation Utilization For Acute Ischemic Strokes At A Community Based Hospital In South Florida

Background: Efficiency in the transfer of patients with ischemic stroke is a vital factor for patient prognosis. A comprehensive stroke center servicing remote areas in south Florida became HEMS direct-from-field capable on October 15, 2020. In some remote areas, the transfer of patients is via ground or air; the severity of the clinical presentation determines the mode. Concern about HEMS overutilization for lower stroke acuities prompted this study. Purpose: The purpose of this project was to evaluate the current HEMS stroke triage process, assess the accuracy of stroke diagnosis, and use this information to improve EMS education to prevent over-triage for stroke. Methods: A retrospective cohort study from October 15, 2020, to July 31, 2021, collected HEMS adult stroke alert data and compared it to the prior year's summary ground EMS (GEMS) stroke alert data. Using HEMS transportation logs, presenting stroke symptoms and pre-hospital assessment were abstracted. In addition, we evaluated initial NIHSS, downgrade rate, stroke diagnosis percentage, treatment rate, and times. Results: The analysis included a total of 52 HEMS stroke alerts. Assessment tools utilized by HEMS included the Cincinnati stroke scale (4%) and the FAST-ED (37%); the majority of cases (59%) did not document a stroke assessment tool. The median NIHSS was 10, with 37% presenting with a score &lt;6. Respectively, 6% and 15 % of cases were downgraded upon arrival and after CT imaging. Significantly (p&lt;.001), more HEMS cases were diagnosed as a stroke (69%) compared to GEMS (57%). Stroke treatment rates remained similar (HEMS=23%; GEMS=23%). Median door-to-needle times were significantly faster for HEMS (15min) than GEMS (25min) (p&lt;.05). Median door-to puncture times were significantly faster for HEMS (61mins) than GEMS (72mins) (p&lt;.05). Conclusion: With low downgrade rates and high diagnosis accuracy, the current HEMS triage process, although not consistently documented, accurately detects stroke, even for low acuity cases. Patients arriving via HEMS receive equal access to stroke treatment with significantly faster treatment times, ensuring the best possible prognosis. EMS educational efforts should focus on improving documentation compliance.

The clinical relevance assessment of ROSIER scale in emergency care

Stroke incidence and its consequences are nowadays a common cause of death, disability and financial burden for the health system. The scale of this phenomenon is estimated to increase in further years. To ensure the best patients care, therapy should be applied in a dedicated stroke unit as soon as possible. Nevertheless, even 2 out of 3 suspected patients visit the emergency department in the first place. The probable lack of knowledge and experience from the personnel indicates up to a 60% rate of misdiagnosis resulting in delays in treatment administration and consequently a reduction of chance for survival and full recovery. The Recognition of Stroke in the Emergency Room scale has been developed to improve the emergency physicians’ assessment. It evaluates the initial event history and physical examination, which translates into a score from –2 to 5 with a &gt; 0 cut-off point anticipating a high probability of stroke. Simple construction assures easy use and evaluation quality by all emergency staff members. The scale shows satisfactory accuracy, which establishes its superiority over the basic neurological examination, Face Arm Speech Time Test (FAST), and Cincinnati Prehospital Stroke Scale (CPSS) proven in several studies. On the contrary, the application is considerably reduced in cases of hemorrhage stroke, transient ischemic attack (TIA) and posterior circulation infarct in both adult and pediatric patients. Despite those limitations, the Recognition of Stroke in the Emergency Room Scale (ROSIER) scale constitutes a valuable instrument that can improve the insufficient stroke recognition rate and following patients’ prognosis.

Large vessel occlusion prediction scales provide high negative but low positive predictive values in prehospital suspected stroke patients

IntroductionWe studied a registry of Emergency Medical Systems (EMS) identified prehospital suspected stroke patients brought to an academic endovascular capable hospital over 1 year to assess the prevalence of disease...

Use of deep artificial neural networks to identify stroke during triage via subtle changes in circulating cell counts

BackgroundThe development of tools that could help emergency department clinicians recognize stroke during triage could reduce treatment delays and improve patient outcomes. Growing evidence suggests that stroke is associated with several changes in circulating cell counts. The aim of this study was to determine whether machine-learning can be used to identify stroke in the emergency department using data available from a routine complete blood count with differential.MethodsRed blood cell, platelet, neutrophil, lymphocyte, monocyte, eosinophil, and basophil counts were assessed in admission blood samples collected from 160 stroke patients and 116 stroke mimics recruited from three geographically distinct clinical sites, and an ensemble artificial neural network model was developed and tested for its ability to discriminate between groups.ResultsSeveral modest but statistically significant differences were observed in cell counts between stroke patients and stroke mimics. The counts of no single cell population alone were adequate to discriminate between groups with high levels of accuracy; however, combined classification using the neural network model resulted in a dramatic and statistically significant improvement in diagnostic performance according to receiver-operating characteristic analysis. Furthermore, the neural network model displayed superior performance as a triage decision making tool compared to symptom-based tools such as the Cincinnati Prehospital Stroke Scale (CPSS) and the National Institutes of Health Stroke Scale (NIHSS) when assessed using decision curve analysis.ConclusionsOur results suggest that algorithmic analysis of commonly collected hematology data using machine-learning could potentially be used to help emergency department clinicians make better-informed triage decisions in situations where advanced imaging techniques or neurological expertise are not immediately available, or even to electronically flag patients in which stroke should be considered as a diagnosis as part of an automated stroke alert system.

Cincinnati Prehospital Stroke Scale Implementation of an Urban County Severity-Based Stroke Triage Protocol: Impact and Outcomes on a Comprehensive Stroke Center

Background and purposeScreening scales are recommended to assist field-based triage of acute stroke patients to designated stroke centers. Cincinnati prehospital stroke scale (CPSS) is a commonly used prehospital stroke screening tool and has been validated to identify large vessel occlusion (LVO). This study addresses the impact of county-based CPSS implementation to triage suspected LVO patients to a comprehensive stroke center (CSC). Materials and methodsDekalb County in Atlanta, Georgia, implemented CPSS-based protocol with score of 3 and last seen normal time < 24 h mandating transfer to the nearest CSC if the added bypass time was <15 min. Frequency of stroke codes, LVO, IV-tPA use, and thrombectomy treatment were compared six months before and after protocol change (November 1, 2020). ResultsDuring the study period, 907 stroke patients presented to the CSC by EMS, including 289 (32%) with CPSS score 3. There was an increase in monthly ischemic stroke volume (pre-16 ± 2 vs.19 ± 3 p = 0.03), LVO (pre-4.3 ± 1.7 vs. post-7.0 ± 2.4; p = 0.03), EVT (pre-15% vs. post-30%; p = 0.001), without significant increase in stroke mimic volume or delay in mean time from last seen normal to IV-tPA (pre-165 ± 66, post-158 ± 49 min; p = 0.35). CPSS score 3 was associated with increased likelihood of LVO diagnosis (OR 8.5, 95% CI 5.0-14.4; p = 0.001) and decreased the likelihood of stroke mimics (OR 0.66, 95% CI 0.50-0.88; p = 0.004). ConclusionCPSS is a quick, easy to implement, and reliable prehospital severity scale for EMS to triage LVO to CSC without delaying IV-tPA treatment or significantly increasing stroke mimics.

P.065 Emergency medical services activation Following Face, Arm, Speech, Time (FAST) public awareness campaigns in Quebec, Canada

Background: Face, Arm, Speech, Time (FAST) campaigns improve stroke recognition in the general population. We assessed the effect of five consecutive FAST campaigns on emergency medical services (EMS) calls for suspected strokes in Quebec, Canada. Methods: We compared with t-tests the daily EMS call volume changes in the greater Montreal area before and after five FAST campaigns held between 2015 and 2019. We used interrupted time-series to measure changes in EMS daily call volume for suspected strokes following each FAST campaign (all calls, calls &lt;5 hours from symptom onset, calls rated 3/3 on the Cincinnati Prehospital Stroke Scale [CPSS]) and used calls for acute headaches as a comparator. Results: After five FAST campaigns, mean daily calls increased by 28% (p&lt;0.001) for suspected strokes, compared to 10% for acute headaches (p=0.012). Significant increases in daily stroke calls were only observed after three campaigns (highest OR=1.26, 95% CI: 1.11, 1.43; p&lt;0.001). There were no significant changes in calls after individual campaigns for strokes &lt;5 hours from symptom onset and 3/3 CPSS strokes. Conclusions: The individual effect of FAST campaigns on daily stroke calls to EMS was inconsistent. Further refinement of FAST campaigns may help improve prompt EMS activation.

Improving the Prehospital Identification and Acute Care of Acute Stroke Patients: A Quality Improvement Project.

Background There are a large number of stroke patients in China, and there is currently a lack of prehospital acute stroke care training programs. Aim To develop a prehospital emergency medical service (PEMS) training program to improve the prehospital identification and acute care of acute stroke. Methods Forty prehospital emergency doctors whose service stations are located within a 10 km radius from Shanghai Pudong New Area Medical Emergency Service Center took this course on November 13, 2014. A questionnaire was designed to evaluate the PEMS personnel's knowledge in stroke and acute stroke care and was conducted before and after training as an assessment of the effectiveness of training. The patient population in this study included a baseline cohort before training and a prospective cohort after training, each composed of patients who were sent to Shanghai East Hospital South Stoke Center within one year. The transit time, final diagnosis, administration of thrombolysis, and door-to-needle time (DNT) were collected and analyzed. Results After the training, 100% of the PEMS personnel were competent to identify stroke cases using the Cincinnati prehospital stroke scale (CPSS). All participants realized that intravenous thrombolysis therapy in a time-sensitive manner is the most effective way to treat acute ischemic stroke. Although there was no difference in first-aid transit time before and after training, the stroke diagnosis rate improved by 6.5% after training (P=0.03). The thrombolysis rate increased to 29.6% from 24.3% but did not reach statistical significance. Compared to 84.0 minutes (standard deviation: 23.1 minutes) before the training, the average DNT after training was 53 minutes (standard deviation: 15.0 minutes), demonstrating a remarkable reduction (P < 0.01). Conclusion The training program effectively improved the PEMS personnel's knowledge in stroke and stroke acute care.

Abstract TP55: Prehospital Stroke Scale: Classifying The Inconclusive Result

Introduction: The Cincinnati Pre-Hospital Stroke Scale (CPSS) is one of the most utilized, validated tools for stroke assessment by emergency medical services (EMS) providers. While the CPSS was developed to convey that a patient has a positive or negative finding, EMS providers designate some patients with “inconclusive” CPSS. To date, there is no data concerning the clinical presentation or stroke diagnosis of this cohort of patients. Methods: Retrospectively reviewed prehospital electronic medical records from 26 EMS agencies linked with hospital data of patients stroke alerted between April 1, 2020 to July 12, 2021 in our institution. The National Emergency Medical Services Information System Technical Assistance Center (NEMSIS TAC) 2020 Dataset was also evaluated. Data collected included CPSS, EMS chief complaint, EMS primary impression, and final discharge diagnosis. Results: At our institution 362 patients arrived by EMS and were stroke alerted at the hospital, of which 311 patients had a recorded prehospital CPSS. CPSS was recorded as inconclusive in 33.4% (104/311), positive in 52.1% (162/311), and negative in 14.5% (45/311) of patients. Neurological symptoms accounted for 76.9% (80/104) of EMS primary impression for those classified as inconclusive. Sixty percent (48/80) and 18.8% (15/80) of those were stroke-like symptoms and altered mental status, respectively. Stroke/TIA was the discharge diagnosis for 30.8% (32/104) of inconclusive, 63.6% (103/162) of positive, and 37.8% (17/45) of negative CPSSs. Nationally, 7.3% (142,422/1,955,591) of prehospital patients with recorded CPSS had an inconclusive finding. Among patients with primary impression of stroke-like symptoms with recorded prehospital CPSS, 17.3% (21,740/125,581) had an inconclusive label. Conclusion: Inconclusive CPSS designations in the prehospital setting are common. Although these patients present commonly with stroke-like symptoms, they have a low rate of stroke diagnosis. More studies with available prehospital linked hospital data are needed at a national level to understand the inconclusive prehospital CPSS designation and inform proper EMS education on in-practice use of stroke screening tools that reduce the number of inconclusive CPSS.