Background and purpose: Endovascular thrombectomy is an evidence‐based treatment for large vessel occlusion (LVO) stroke. Commercially available artificial intelligence has been designed to detect the presence of an LVO on computed tomography angiogram (CTA). We compared Viz.ai‐LVO (San Francisco, CA, USA) to CTA interpretation by board‐certified neuroradiologists (NRs) in a large, integrated stroke network.Methods: From January 2021 to December 2021, we compared Viz.ai detection of an internal carotid artery (ICA) or middle cerebral artery first segment (MCA‐M1) occlusion to the gold standard of CTA interpretation by board‐certified NRs for all code stroke CTAs. On a monthly basis, sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Trend analyses were conducted to evaluate for any improvement of LVO detection by the software over time.Results: 3851 patients met study inclusion criteria, of whom 220 (5.7%) had an ICA or MCA‐M1 occlusion per NR. Sensitivity and specificity were 78.2% (95% CI 72%–83%) and 97% (95% CI 96%–98%), respectively. PPV was 61% (95% CI 55%–67%), NPV 99% (95% CI 98%–99%), and accuracy was 95.9% (95% CI 95.3%–96.5%). Neither specificity or sensitivity improved over time in the trend analysis.Conclusions: Viz.ai‐LVO has high specificity and moderately high sensitivity to detect an ICA or proximal MCA occlusion. The software has the potential to streamline code stroke workflows and may be particularly impactful when emergency access to NRs or vascular neurologists is limited.
Despite randomized trials showing a functional outcome benefit in favor of endovascular therapy (EVT), large artery occlusion acute ischemic stroke is associated with high mortality. We performed a retrospective analysis from a prospectively collected code stroke registry and included patients presenting between November 2016 and April 2019 with internal carotid artery and/or proximal middle cerebral artery occlusions. Ninety-day mortality status from registry follow-up was corroborated with the Social Security Death Index. A multivariable logistic regression model was fitted to determine demographic and clinical characteristics associated with 90-day mortality. Among 764 patients, mortality rate was 26%. Increasing age (per 10 years, OR 1.48, 95% CI 1.25–1.76;p < 0.0001), higher presenting NIHSS (per 1 point, OR 1.05, 95% CI 1.01–1.09,p = 0.01), and higher discharge modified Rankin Score (per 1 point, OR 4.27, 95% CI 3.25–5.59,p < 0.0001) were independently associated with higher odds of mortality. Good revascularization therapy, compared to no EVT, was independently associated with a survival benefit (OR 0.61, 95% CI 0.35–1.00,p = 0.048). We identified factors independently associated with mortality in a highly lethal form of stroke which can be used in clinical decision-making, prognostication, and in planning future studies.
Post-stroke depression (PSD) is common but is not routinely assessed for in hospitalized patients. As a Comprehensive Stroke Center, we screen all stroke inpatients for depression, though the feasibility of early screening has not been established. We assessed the hypothesis that early depression screening in stroke patients is feasible. We also explored patient level factors associated with being screened for PSD and the presence of early PSD. The medical records of all patients admitted with ischemic stroke (IS) or intracerebral hemorrhage (ICH) between 01/02/13 and 15/04/13 were reviewed. A depression screen, modified from the Patient Health Questionnaire-9, was administered (maximum score 27, higher scores indicating worse depression). Patients were eligible if they did not have a medical condition precluding screening. Feasibility was defined as screening 75% of all eligible patients. Of 303 IS and ICH inpatients, 70% (211) were eligible for screening, and 75% (158) of all eligible patients were screened. More than one-third of all patients screened positive for depression (score > 4). Women (OR 2.06, 95% CI 1.06–4.01) and younger patients (OR 0.97, 95% CI 0.96–0.99) were more likely to screen positive. Screening positive was not associated with poor discharge/day 7 outcome (mRS > 3; OR 1.45, 95% CI 0.74–2.83). Screening stroke inpatients for depression is feasible and early depression after stroke is common. Women and younger patients are more likely to experience early PSD. Our results provide preliminary evidence supporting continued screening for depression in hospitalized stroke patients.
Introduction: Prognostic factors for functional outcome after basilar artery occlusion (BAO) treated with modern endovascular therapy (EVT) are sparse. We investigated the association between clinical characteristics, readily available imaging variables, and outcome in BAO patients treated with EVT. Methods: Retrospective analysis from a large healthcare system’s prospectively collected code stroke registry of acute BAO patients treated with EVT between January 2017–January 2020. The primary outcome measure was a favorable 90-day modified Rankin score (mRS) of 0-2. Results: 65 patients (median age 67 years, 57% male, median NIHSS 16) met the study inclusion criteria. Thrombolysis in Cerebral Infarction (TICI) 2 b-3 revascularization was achieved in 57/65 patients (88%) with a median time to revascularization of 445 minutes [IQR 302-840]. Ninety-day good outcome was seen in 35% (23/65) of patients. In a univariate analysis, age, history of ischemic stroke, baseline NIHSS, BAO site, and discharge mRS were associated with significant differences between the good and poor outcome groups. A multivariable logistic regression analysis demonstrated an independent association with 90-day good outcome and younger age (per 1-year, OR 0.79, 95% CI 0.64, 0.98) and good discharge mRS (0-2) (OR > 999.99, 95% CI 13.26, > 999.99). Conclusions: Patients presenting with an acute BAO treated with modern EVT have a good 90-day outcome in over one-third of cases. Age and discharge mRS are independently associated with good 90-day outcome. Additional studies may focus on factors that can enhance discharge function after BAO, a novel prognostic indicator for favorable 90-day outcome in our study.