RESUMO
BACKGROUND: Large-vessel occlusion (LVO) stroke represents one-third of acute ischemic stroke (AIS) in the United States but causes two-thirds of poststroke dependence and >90% of poststroke mortality. Prehospital LVO stroke detection permits efficient emergency medical systems (EMS) transport to an endovascular thrombectomy (EVT)-capable center. Our primary objective was to determine the feasibility of using a cranial accelerometry (CA) headset device for prehospital LVO stroke detection. Our secondary objective was development of an algorithm capable of distinguishing LVO stroke from other conditions. METHODS: We prospectively enrolled consecutive adult patients suspected of acute stroke from 11 study hospitals in four different U.S. geographical regions over a 21-month period. Patients received device placement by prehospital EMS personnel. Headset data were matched with clinical data following informed consent. LVO stroke diagnosis was determined by medical chart review. The device was trained using device data and Los Angeles Motor Scale (LAMS) examination components. A binary threshold was selected for comparison of device performance to LAMS scores. RESULTS: A total of 594 subjects were enrolled, including 183 subjects who received the second-generation device. Usable data were captured in 158 patients (86.3%). Study subjects were 53% female and 56% Black/African American, with median age 69 years. Twenty-six (16.4%) patients had LVO and 132 (83.6%) were not LVO (not-LVO AIS, 33; intracerebral hemorrhage, nine; stroke mimics, 90). COVID-19 testing and positivity rates (10.6%) were not different between groups. We found a sensitivity of 38.5% and specificity of 82.7% for LAMS ≥ 4 in detecting LVO stroke versus a sensitivity of 84.6% (p < 0.0015 for superiority) and specificity of 82.6% (p = 0.81 for superiority) for the device algorithm (CA + LAMS). CONCLUSIONS: Obtaining adequate recordings with a CA headset is highly feasible in the prehospital environment. Use of the device algorithm incorporating both CA and LAMS data for LVO detection resulted in significantly higher sensitivity without reduced specificity when compared to the use of LAMS alone.
RESUMO
BACKGROUND/OBJECTIVE: We combined cranial accelerometry, a device-based approach to large vessel occlusion (LVO) prediction, with neurological examination findings to determine if this improves diagnostic accuracy compared to either alone. METHODS: Cranial accelerometry recordings and NIHSS scores were obtained during stroke codes and thrombectomy transfers at an academic medical center using convenience sampling. The reference standard was discharge diagnosis of LVO stroke. We compared accuracy statistics between machine learning models trained using cranial accelerometry alone, with asymmetric arm weakness added, with NIHSS scores added, and retrospective examination only LVO prediction scales. An exploratory analysis required asymmetric arm weakness prior to model training or scale testing. RESULTS: Of 68 patients, there were 23 LVO strokes. Cranial accelerometry was 65% sensitive (95% CI 43-84%) and 87% specific (95% CI 73-95%). Adding asymmetric arm weakness increased specificity to 91% (95% CI 79-98%). Adding asymmetric arm weakness and the NIHSS increased sensitivity to 74% (95% CI 52-90%) and decreased specificity to 89% (95% CI 76-96%). LVO prediction scales had wide sensitivity and specificity ranges. The exploratory analysis improved sensitivity to 91% (95% CI 72-99%) and specificity to 93% (95% CI 92-99%) with only three false positives and two false negatives. CONCLUSIONS: Cranial accelerometry models are improved by various additions of asymmetric arm weakness and the NIHSS. An exploratory analysis requiring asymmetric arm weakness prior to cranial accelerometry model training minimized false positives and negatives.
Assuntos
Isquemia Encefálica , Acidente Vascular Cerebral , Acelerometria , Humanos , Exame Neurológico , Valor Preditivo dos Testes , Estudos Retrospectivos , Acidente Vascular Cerebral/diagnósticoRESUMO
BACKGROUND: Cranial accelerometry is used to detect cerebral vasospasm and concussion. We explored this technique in a cohort of code stroke patients to see whether a signature could be identified to aid in the diagnosis of large vessel occlusion (LVO) stroke. METHODS: A military-grade three-axis accelerometer was affixed to a headset. Accelerometer and electrocardiogram (ECG) outputs were digitized at 1.6 kHz. We call the resulting digitized signals the "headpulse." Three-minute recordings were performed immediately after computed tomography (CT) angiography (CTA) and/or immediately before and after attempted mechanical thrombectomy in patents with suspected stroke. The resulting waveforms were inspected by eye and then subjected to supervised machine learning (MATLAB Classification Learner R2018a) to train a model using fivefold cross-validation. RESULTS: Of 42 code stroke subjects with recordings, 19 (45%) had LVO and 23 (55%) had normal CTAs. In patients without LVO, ECG-triggered waveforms followed a self-similar time course revealing that the headpulse is highly coupled to the cardiac contraction. However, in most patients with LVO, headpulses showed little cardiac contraction correlation. We term this abnormality "chaos" and parameterized it with 156 measures of trace-by-trace variation from the ECG-signal-averaged mean for machine learning model training. Selecting the best model, using biometric data only, we properly classified 15/19 LVOs and 20/23 non-LVO patients, with receiver operating characteristic curve area = 0.79, sensitivity of 73%, and specificity of 87%, P < 0.0001. Headpulse waveforms following thrombectomy showed return of cardiac contraction correlation. CONCLUSIONS: Headpulse recordings performed on patients with suspected acute stroke significantly identify those with LVO. The lack of temporal correlation of the headpulse with cardiac contraction and resolution to normal may reflect changes in cerebral blood flow and may provide a useful technique to triage stroke patients for thrombectomy using a noninvasive device.