ABSTRACT
Background: Stroke misdiagnosis is estimated to occur in 9% of all stroke patients and is associated with poor outcomes. We hypothesized that machine learning (ML) could be used to detect ischemic stroke at the point of care in emergency departments (ED). Methods: Clinical data from 13 hospitals of a large health system in Pennsylvania, United States, from September 2003 to May 2019 were used for model development. Data from June 2019 to December 2020 were prospectively collected and divided into pre- and post-COVID cohorts for validation. We simulated three clinical settings by enrollment with different inclusion/exclusion criteria and created two ML pipelines: ML applied to pre-event clinical data, and natural language processing (NLP) with ML applied to clinical notes during triaging. Misdiagnosed stroke in ED was a case study to show the discriminative power. Results: We included a total of 49,155 patient encounters (8,900 consecutive ischemic stroke patients and 40,255 controls). The best model, based on the patient's pre-event information, was XGBoost (AUROC=0.91). Using NLP+ML pipeline, we collected 2,070 notes during the triage process and 9,607 notes (non-stroke) for modeling. For independent validation, we identified 2,989 notes for stroke and 4,303 notes for non-stroke. We identified nine models that reached a balanced performance in terms of AUROC, sensitivity, and specificity. Model performance, in terms of AUROC, ranged from 0.876 to 0.985. Model sensitivity and specificity reached 0.993 and 0.975, respectively. There was no performance difference between models tested on pre- and post-COVID. Three out of four models correctly identified a separate case series of five misdiagnosed strokes. Conclusion: Available clinical information can be used to reduce stroke misdiagnosis in real-time. In addition, this study serves as a foundation for prospective trials to establish how pre-event clinical data and triage information can be used to improve care.
ABSTRACT
The goal of this study was to better depict the short-term risk of stroke and its associated factors among SARS-CoV-2 hospitalized patients. Data Source: This multicenter, multinational observational study includes hospitalized SARS-CoV-2 patients from North and South America (United States, Canada, and Brazil), Europe (Greece, Italy, Finland, and Turkey), Asia (Lebanon, Iran, and India), and Oceania (New Zealand). Main Outcomes and Measures: The outcome was the risk of subsequent stroke (ischemic stroke, intracranial hemorrhage, cerebral venous/sinus thrombosis). The counts and clinical characteristics including laboratory findings and imaging of the patients with and without a subsequent stroke were recorded according to a predefined study protocol. Data Extraction and Synthesis: Quality, risk of bias, and heterogeneity assessments were conducted according to ROBINS-E and Cochrane Q-test. The risk of subsequent stroke was estimated through meta-analyses with random effect models. Binary logistic regression was used to determine the associated factors with the outcome measure. The study was reported according to the STROBE, MOOSE, and EQUATOR guidelines. Results: We received data from 18,311 hospitalized SARS-CoV-2 patients from 77 tertiary centers in 46 regions of 11 countries until May 1 , 2020. A total of 17,799 patients were included in metaanalyses. Among them, 156(0.9%) patients had a stroke-123(79%) ischemic stroke, 27(17%) intracerebral/subarachnoid hemorrhage, and 6(4%) cerebral sinus thrombosis. Subsequent stroke risks calculated with meta-analyses, under low to moderate heterogeneity, were 0.5% among all centers in all countries, and 0.7% among countries with higher health expenditures. The need formechanical ventilation (OR: 1.9, 95% CI:1.1-3.5, p = 0.03) and the presence of ischemic heartdisease (OR: 2.5, 95% CI:1.4-4.7, p =0-006) were predictive of stroke. Conclusion and Relevance: The results of this multi-national study on hospitalized patients withSARS-CoV-2 infection indicated an overall stroke risk of 0.5% (pooled risk: 0.9%). The need formechanical ventilation and the history of ischemic heart disease are the independent predictors ofstroke among SARS-CoV-2 patients.
ABSTRACT
Background: Emerging data indicates an increased risk for cerebrovascular events with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and highlights the potential impact of coronavirus disease (COVID-19) on the management and outcomes of acute stroke. We conducted a systematic review and meta-analysis to evaluate the aforementioned considerations. Methods: We performed a meta-analysis of observational cohort studies reporting on the occurrence and/or outcomes of patients with cerebrovascular events in association with their SARSCoV- 2 infection status. We used a random-effects model. Summary estimates were reported as odds ratios (ORs) and corresponding 95% confidence intervals (95%CI). Results: We identified 16 cohort studies including 44,004 patients. Among patients with SARS-CoV- 2, 1.3% (95%CI: 0.9-1.8%;I =88%) were hospitalized for cerebrovascular events, 1.2% (95%CI: 0.8-1.5%;I =85%) for ischemic stroke, and 0.2% (95%CI: 0.1-0.4%;I =69%) for hemorrhagic stroke. Compared to non-infected contemporary or historical controls, patients with SARS-CoV-2 infection had increased odds of ischemic stroke (OR=3.58, 95%CI: 1.43-8.92;I =43%) and cryptogenic stroke (OR=3.98, 95%CI: 1.62-9.77;I =0%). Odds for in-hospital mortality were higher among SARS-CoV-2 stroke patients compared to non-infected contemporary or historical stroke patients (OR=5.60, 95%CI: 3.19-9.80;I =45%). SARS-CoV-2 infection status was not associated to the likelihood of receiving intravenous thrombolysis (OR=1.42, 95%CI: 0.65-3.10;I =0%) or endovascular thrombectomy (OR=0.78, 95%CI: 0.35-1.74;I =0%) among hospitalized ischemic stroke patients during the COVID-19 pandemic. Diabetes mellitus was found to be more prevalent among SARS-CoV-2 stroke patients compared to non-infected contemporary or historical controls(OR=1.39, 95%CI: 1.04-1.86;I =0%). Conclusion: SARS-CoV-2 appears to be associated with an increased risk of ischemic stroke,particularly the cryptogenic subtype. SARS-CoV-2 infection in stroke substantially increases themortality risk.
ABSTRACT
Objective and Design: We conducted a multinational observational study on features of consecutive acute ischemic stroke (AIS), intracranial hemorrhage (ICH), and cerebral venous or sinus thrombosis (CVST) among SARS-CoV-2 infected patients. Main Outcome Measures: We investigated the association of demographics, clinical data, geographical regions, and countries' health expenditure among AIS patients with the risk of large vessel occlusion (LVO), stroke severity as measured by National Institute of Health stroke scale (NIHSS), and stroke subtype as measured by the TOAST criteria. Additionally, we applied unsupervised machine learning algorithms to uncover possible similarities among stroke patients. Results: Among the 136 tertiary centers of 32 countries who participated in this study, 71 centers from 17 countries had at least one eligible stroke patient. Out of 432 patients included, 323(74.8%) had AIS, 91(21.1%) ICH, and 18(4.2%) CVST. Among 23 patients with subarachnoid hemorrhage, 16(69.5%) had no evidence of aneurysm. A total of 183(42.4%) patients were women, 104(24.1%) patients were younger than 55 years, and 105(24.4%) patients had no identifiable vascular risk factors. Among 380 patients who had known interval onset of the SARS-CoV-2 and stroke, 144(37.8%) presented to the hospital with chief complaints of stroke-related symptoms, with asymptomatic or undiagnosed SARS-CoV-2 infection. Among AIS patients 44.5% had LVO;10% had small artery occlusion according to the TOAST criteria. We observed a lower median NIHSS (8[3-17], versus 11[5-17];p=0.02) and higher rate of mechanical thrombectomy (12.4% versus 2%;p<0.001) in countries with middle to high-health expenditure when compared to countries with lower health expenditure. The unsupervised machine learning identified 4 subgroups, with a relativelylarge group with no or limited comorbidities. Conclusions and Relevance: We observed a relatively high number of young, and asymptomaticSARS-CoV-2 infections among stroke patients. Traditional vascular risk factors were absent amonga relatively large cohort of patients. The stroke severity was lower and rate of mechanicalthrombectomy was higher among countries with middle to high-health expenditure.