Prediction Of Large Vessel Occlusion In Acute Ischemic Stroke Patients

Part One Conveniently-Grasped Field Assessment Stroke Triage(CG-FAST):A Modified Scale to Detect Large Vessel Occlusion StrokePurpose:Patients with acute ischemic stroke with large vessel occlusion(AIS-LVO)need to be rapidly identified and transferred to comprehensive stroke centers.However,previous prehospital strategy remains challenging.We aimed to develop a modified scale to better predict LVO.Methods:We retrospectively reviewed our prospectively collected database for AIS patients within 8 hours of onset who underwent computed tomography angiography(CTA)or time of flight-magnetic resonance angiography(TOF-MRA)and had a detailed National Institutes of Health Stroke Scale(NIHSS)score at admission in our center during period from June 2009 to December 2018.Large vessel occlusion(LVO)was defined as the complete occlusion of large vessels,including the intracranial internal carotid artery,M1 and M2 segments of the middle cerebral artery,and basilar artery.The Conveniently-Grasped Field Assessment Stroke Triage(CG-FAST)scale was consisted of Level of Consciousness(LOC)questions,Gaze deviation,Facial palsy,Arm weakness and Speech changes and coincided with all tested items as an acronym.Receiver Operating Characteristic(ROC)analysis was used to obtain the Area Under the Curve(AUC)of CG-FAST and previously established prehospital prediction scales.Results:Finally,1499 patients were included in the analysis.LVO was detected in 686(45.8%)patients.The sensitivity,specificity,positive predictive value,and negative predictive value of CG-FAST were 0.622,0.829,0.754,and 0.722 respectively,at the optimal cutoff(?4).The AUC of the CG-FAST scale(0.792)was higher than other prehospital prediction scales,including FAST-ED(0.780),3-ISS(0.758),CPSSS(0.776),PASS(0.769),RACE(0.772),LAMS(0.736),G-FAST(0.754),and NIHSS score(0.784).Conclusions:CG-FAST scale could be an effective and simple scale for accurate identification of patients with AIS-LVO.Part Two Novel Prehospital Prediction Model of Large Vessel Occlusion Using Artificial Neural NetworkBackground:We aim to develop an artificial neural network(ANN)algorithm to predict LVO using prehospital accessible data including demographics,vascular risk factors and NIHSS items.Methods:We retrospectively reviewed our prospectively collected database for AIS patients within 8 hours of onset who underwent CTA or TOF-MRA and had demographics,vascular risk factors and NIHSS items at admission in our center during period from June 2009 to December 2018.The diagnosis of LVO was defined as occlusion of the intracranial internal carotid artery,M1 and M2 segments of the middle cerebral artery 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.