Dataset Information

Novel Prehospital Prediction Model of Large Vessel Occlusion Using Artificial Neural Network.

ABSTRACT: Background: Identifying large vessel occlusion (LVO) patients in the prehospital triage stage to avoid unnecessary and costly delays is important but still challenging. We aim to develop an artificial neural network (ANN) algorithm to predict LVO using prehospital accessible data including demographics, National Institutes of Health Stroke Scale (NIHSS) items and vascular risk factors. Methods: Consecutive acute ischemic stroke patients who underwent CT angiography (CTA) or time of flight MR angiography (TOF-MRA) and received reperfusion therapy within 8 h from symptom onset were included. The diagnosis of LVO was defined as occlusion of the intracranial internal carotid artery (ICA), M1 and M2 segments of the middle cerebral artery (MCA) and basilar artery on CTA or TOF-MRA before treatment. Patients with and without LVO were randomly selected at a 1:1 ratio. The ANN model was developed using backpropagation algorithm, and 10-fold cross-validation was used to validate the model. The comparison of diagnostic parameters between the ANN model and previously established prehospital prediction scales were performed. Results: Finally, 300 LVO and 300 non-LVO patients were randomly selected for the training and validation of the ANN model. The mean Youden index, sensitivity, specificity and accuracy of the ANN model based on the 10-fold cross-validation analysis were 0.640, 0.807, 0.833 and 0.820, respectively. The area under the curve (AUC), Youden index and accuracy of the ANN model were all higher than other prehospital prediction scales. Conclusions: The ANN can be an effective tool for the recognition of LVO in the prehospital triage stage.

SUBMITTER: Chen Z

PROVIDER: S-EPMC6028566 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Novel Prehospital Prediction Model of Large Vessel Occlusion Using Artificial Neural Network.

Chen Zhicai Z Zhang Ruiting R Xu Feizhou F Gong Xiaoxian X Shi Feina F Zhang Meixia M Lou Min M

Frontiers in aging neuroscience 20180626

<b>Background</b>: Identifying large vessel occlusion (LVO) patients in the prehospital triage stage to avoid unnecessary and costly delays is important but still challenging. We aim to develop an artificial neural network (ANN) algorithm to predict LVO using prehospital accessible data including demographics, National Institutes of Health Stroke Scale (NIHSS) items and vascular risk factors. <b>Methods</b>: Consecutive acute ischemic stroke patients who underwent CT angiography (CTA) or time of ...[more]

PMID: 29997494

Similar Datasets

Project description:Background and objectivesEndovascular thrombectomy (EVT) is standard treatment for anterior large vessel occlusion stroke (LVO-a stroke). Prehospital diagnosis of LVO-a stroke would reduce time to EVT by allowing direct transportation to an EVT-capable hospital. We aim to evaluate the diagnostic accuracy of dry electrode EEG for the detection of LVO-a stroke in the prehospital setting.MethodsELECTRA-STROKE was an investigator-initiated, prospective, multicenter, diagnostic study, performed in the prehospital setting. Adult patients were eligible if they had suspected stroke (as assessed by the attending ambulance nurse) and symptom onset <24 hours. A single dry electrode EEG recording (8 electrodes) was performed by ambulance personnel. Primary endpoint was the diagnostic accuracy of the theta/alpha frequency ratio for LVO-a stroke (intracranial ICA, A1, M1, or proximal M2 occlusion) detection among patients with EEG data of sufficient quality, expressed as the area under the receiver operating characteristic curve (AUC). Secondary endpoints were diagnostic accuracies of other EEG features quantifying frequency band power and the pairwise derived Brain Symmetry Index. Neuroimaging was assessed by a neuroradiologist blinded to EEG results.ResultsBetween August 2020 and September 2022, 311 patients were included. The median EEG duration time was 151 (interquartile range [IQR] 151-152) seconds. For 212/311 (68%) patients, EEG data were of sufficient quality for analysis. The median age was 74 (IQR 66-81) years, 90/212 (42%) were women, and the median baseline NIH Stroke Scale was 1 (IQR 0-4). Six (3%) patients had an LVO-a stroke, 109/212 (51%) had a non-LVO-a ischemic stroke, 32/212 (15%) had a transient ischemic attack, 8/212 (4%) had a hemorrhagic stroke, and 57/212 (27%) had a stroke mimic. AUC of the theta/alpha ratio was 0.80 (95% CI 0.58-1.00). Of the secondary endpoints, the pairwise derived Brain Symmetry Index in the delta frequency band had the highest diagnostic accuracy (AUC 0.91 [95% CI 0.73-1.00], sensitivity 80% [95% CI 38%-96%], specificity 93% [95% CI 88%-96%], positive likelihood ratio 11.0 [95% CI 5.5-21.7]).DiscussionThe data from this study suggest that dry electrode EEG has the potential to detect LVO-a stroke among patients with suspected stroke in the prehospital setting. Toward future implementation of EEG in prehospital stroke care, EEG data quality needs to be improved.Trial registration informationClinicalTrials.gov identifier: NCT03699397.Classification of evidenceThis study provides Class II evidence that prehospital dry electrode scalp EEG accurately detects LVO-a stroke among patients with suspected acute stroke.

Project description:ImportanceThe efficacy of endovascular thrombectomy (EVT) for symptomatic large anterior vessel occlusion (sLAVO) sharply decreases with time. Because EVT is restricted to comprehensive stroke centers, prehospital triage of patients with acute stroke codes for sLAVO is crucial, and although several prediction scales are already in use, external validation, head-to-head comparison, and feasibility data are lacking.ObjectiveTo conduct external validation and head-to-head comparisons of 7 sLAVO prediction scales in the emergency medical service (EMS) setting and to assess scale feasibility by EMS paramedics.Design, setting, and participantsThis prospective cohort study was conducted between July 2018 and October 2019 in a large urban center in the Netherlands with a population of approximately 2 million people and included 2 EMSs, 3 comprehensive stroke centers, and 4 primary stroke centers. Participants were consecutive patients aged 18 years or older for whom an EMS-initiated acute stroke code was activated. Of 2812 acute stroke codes, 805 (28.6%) were excluded, because no application was used or no clinical data were available, leaving 2007 patients included in the analyses.ExposuresApplications with clinical observations filled in by EMS paramedics for each acute stroke code enabling reconstruction of the following 7 prediction scales: Los Angeles Motor Scale (LAMS); Rapid Arterial Occlusion Evaluation (RACE); Cincinnati Stroke Triage Assessment Tool; Prehospital Acute Stroke Severity (PASS); gaze-face-arm-speech-time; Field Assessment Stroke Triage for Emergency Destination; and gaze, facial asymmetry, level of consciousness, extinction/inattention.Main outcomes and measuresPlanned primary and secondary outcomes were sLAVO and feasibility rates (ie, the proportion of acute stroke codes for which the prehospital scale could be reconstructed). Predictive performance measures included accuracy, sensitivity, specificity, the Youden index, and predictive values.ResultsOf 2007 patients who received acute stroke codes (mean [SD] age, 71.1 [14.9] years; 1021 [50.9%] male), 158 (7.9%) had sLAVO. Accuracy of the scales ranged from 0.79 to 0.89, with LAMS and RACE scales yielding the highest scores. Sensitivity of the scales ranged from 38% to 62%, and specificity from 80% to 93%. Scale feasibility rates ranged from 78% to 88%, with the highest rate for the PASS scale.Conclusions and relevanceThis study found that all 7 prediction scales had good accuracy, high specificity, and low sensitivity, with LAMS and RACE being the highest scoring scales. Feasibility rates ranged between 78% and 88% and should be taken into account before implementing a scale.

Project description:BACKGROUND AND PURPOSE:Prehospital scales have been developed to identify patients with acute cerebral ischemia (ACI) because of large vessel occlusion (LVO) for direct routing to Comprehensive Stroke Centers (CSCs), but few have been validated in the prehospital setting, and their impact on routing of patients with intracranial hemorrhage has not been delineated. The purpose of this study was to validate the Los Angeles Motor Scale (LAMS) for LVO and CSC-appropriate (LVO ACI and intracranial hemorrhage patients) recognition and compare the LAMS to other scales. METHODS:The performance of the LAMS, administered prehospital by paramedics to consecutive ambulance trial patients, was assessed in identifying (1) LVOs among all patients with ACI and (2) CSC-appropriate patients among all suspected strokes. Additionally, the LAMS administered postarrival was compared concurrently with 6 other scales proposed for paramedic use and the full National Institutes of Health Stroke Scale. RESULTS:Among 94 patients, age was 70 (±13) and 49% female. Final diagnoses were ACI in 76% (because of LVO in 48% and non-LVO in 28%), intracranial hemorrhage in 19%, and neurovascular mimic in 5%. The LAMS administered by paramedics in the field performed moderately well in identifying LVO among patients with ACI (C statistic, 0.79; accuracy, 0.72) and CSC-appropriate among all suspected stroke transports (C statistic, 0.80; accuracy, 0.72). When concurrently performed in the emergency department postarrival, the LAMS showed comparable or better accuracy versus the 7 comparator scales, for LVO among ACI (accuracies LAMS, 0.70; other scales, 0.62-0.68) and CSC-appropriate (accuracies LAMS, 0.73; other scales, 0.56-0.73). CONCLUSIONS:The LAMS performed in the field by paramedics identifies LVO and CSC-appropriate patients with good accuracy. The LAMS performs comparably or better than more extended prehospital scales and the full National Institutes of Health Stroke Scale.

Dataset Information

Novel Prehospital Prediction Model of Large Vessel Occlusion Using Artificial Neural Network.

Publications

Novel Prehospital Prediction Model of Large Vessel Occlusion Using Artificial Neural Network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets