scholarly journals Atrial Fibrillation Risk and Discrimination of Cardioembolic From Noncardioembolic Stroke

Stroke ◽  
2020 ◽  
Vol 51 (5) ◽  
pp. 1396-1403 ◽  
Author(s):  
Shaan Khurshid ◽  
Ludovic Trinquart ◽  
Lu-Chen Weng ◽  
Olivia L. Hulme ◽  
Wyliena Guan ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Electronic Health Record ◽  
Cardioembolic Stroke ◽  
Risk Scores ◽  
Health Record ◽  
Stroke Subtype ◽  
Aging Research ◽  
Genomic Epidemiology ◽  
Electronic Health

Background and Purpose— Classification of stroke as cardioembolic in etiology can be challenging, particularly since the predominant cause, atrial fibrillation (AF), may not be present at the time of stroke. Efficient tools that discriminate cardioembolic from noncardioembolic strokes may improve care as anticoagulation is frequently indicated after cardioembolism. We sought to assess and quantify the discriminative power of AF risk as a classifier for cardioembolism in a real-world population of patients with acute ischemic stroke. Methods— We performed a cross-sectional analysis of a multi-institutional sample of patients with acute ischemic stroke. We systematically adjudicated stroke subtype and examined associations between AF risk using CHA 2 DS 2 -VASc, Cohorts for Heart and Aging Research in Genomic Epidemiology-AF score, and the recently developed Electronic Health Record–Based AF score, and cardioembolic stroke using logistic regression. We compared the ability of AF risk to discriminate cardioembolism by calculating C statistics and sensitivity/specificity cutoffs for cardioembolic stroke. Results— Of 1431 individuals with ischemic stroke (age, 65±15; 40% women), 323 (22.6%) had cardioembolism. AF risk was significantly associated with cardioembolism (CHA 2 DS 2 -VASc: odds ratio [OR] per SD, 1.69 [95% CI, 1.49–1.93]; Cohorts for Heart and Aging Research in Genomic Epidemiology-AF score: OR, 2.22 [95% CI, 1.90–2.60]; electronic Health Record–Based AF: OR, 2.55 [95% CI, 2.16–3.04]). Discrimination was greater for Cohorts for Heart and Aging Research in Genomic Epidemiology-AF score (C index, 0.695 [95% CI, 0.663–0.726]) and Electronic Health Record–Based AF score (0.713 [95% CI, 0.681–0.744]) versus CHA 2 DS 2 -VASc (C index, 0.651 [95% CI, 0.619–0.683]). Examination of AF scores across a range of thresholds indicated that AF risk may facilitate identification of individuals at low likelihood of cardioembolism (eg, negative likelihood ratios for Electronic Health Record–Based AF score ranged 0.31–0.10 at sensitivity thresholds 0.90–0.99). Conclusions— AF risk scores associate with cardioembolic stroke and exhibit moderate discrimination. Utilization of AF risk scores at the time of stroke may be most useful for identifying individuals at low probability of cardioembolism. Future analyses are warranted to assess whether stroke subtype classification can be enhanced to improve outcomes in undifferentiated stroke.

scholarly journals Semantic computational analysis of anticoagulation use in atrial fibrillation from real world data

2019 ◽  
Author(s):  
Daniel M. Bean ◽  
James Teo ◽  
Honghan Wu ◽  
Ricardo Oliveira ◽  
Raj Patel ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Natural Language Processing ◽  
Natural Language ◽  
Electronic Health Record ◽  
Open Source ◽  
Language Processing ◽  
Risk Scores ◽  
Free Text ◽  
Health Record ◽  
Electronic Health

AbstractAtrial fibrillation (AF) is the most common arrhythmia and significantly increases stroke risk. This risk is effectively managed by oral anticoagulation. Recent studies using national registry data indicate increased use of anticoagulation resulting from changes in guidelines and the availability of newer drugs.The aim of this study is to develop and validate an open source risk scoring pipeline for free-text electronic health record data using natural language processing.AF patients discharged from 1st January 2011 to 1st October 2017 were identified from discharge summaries (N=10,030, 64.6% male, average age 75.3 ± 12.3 years). A natural language processing pipeline was developed to identify risk factors in clinical text and calculate risk for ischaemic stroke (CHA2DS2-VASc) and bleeding (HAS-BLED). Scores were validated vs two independent experts for 40 patients.Automatic risk scores were in strong agreement with the two independent experts for CHA2DS2-VASc (average kappa 0.78 vs experts, compared to 0.85 between experts). Agreement was lower for HAS-BLED (average kappa 0.54 vs experts, compared to 0.74 between experts).In high-risk patients (CHA2DS2-VASc ≥2) OAC use has increased significantly over the last 7 years, driven by the availability of DOACs and the transitioning of patients from AP medication alone to OAC. Factors independently associated with OAC use included components of the CHA2DS2-VASc and HAS-BLED scores as well as discharging specialty and frailty. OAC use was highest in patients discharged under cardiology (69%).Electronic health record text can be used for automatic calculation of clinical risk scores at scale. Open source tools are available today for this task but require further validation. Analysis of routinely-collected EHR data can replicate findings from large-scale curated registries.

Abstract 14907: Clinically Feasible Electronic Health Record Tool for Stratification of 1- to 3-Year Post-Myocardial Infarction Risk of Cardiovascular Events: The Intermountain Acute Coronary Syndromes Risk Scores

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Benjamin D Horne ◽  
Joseph B Muhlestein ◽  
Durgesh Bhandary ◽  
Greta L Hoetzer ◽  
Naeem D Khan ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Electronic Health Record ◽  
Acute Coronary Syndromes ◽  
Troponin I ◽  
Risk Scores ◽  
Health Record ◽  
Additional Risk Factor ◽  
Lipid Panel ◽  
Coronary Syndromes ◽  
Electronic Health

Background: Randomized trials report that prolonged (>1 year) use of P2Y12 inhibitors with aspirin after myocardial infarction (MI) reduces stent thrombosis and cardiovascular (CV) events, including new MI, stroke, and CV death. Post-MI patients may benefit to a differing extent from long-term dual anti-platelet therapy (DAPT); thus, a method is needed to identify those at higher risk of CV events. Hypothesis: A low-cost, easy-to-use, and highly predictive risk stratification tool can be created to differentiate risk of CV events 1-3 years after MI. Methods: Patients surviving ≥1 year after an index MI who had ≥1 additional risk factor for MI were studied. Cox regression models were used to derive sex-specific Intermountain Acute Coronary Syndromes (IMACS) risk scores in 70% of patients (N=1,342 females; 3,047 males). Validation of IMACS scores was performed in the other 30% of patients (N=576 females; 1,290 males). Variables used in model creation were age, troponin I, B-type natriuretic peptide, hemoglobin A1c, and all components of the lipid panel, complete blood count, and comprehensive metabolic panel. The primary end point was a composite of CV death, MI, or stroke. Results: Age averaged 68.7±12 and 69.8±12 for females in the derivation and validation groups, respectively, and 63.6±12 and 63.9±12 for males. IMACS scores ranged from 0-11 for females (grouping scores of 0-2, 3-6, and 7-11 into low-, moderate-, and high-risk) and 0-14 for males (0-2, 3-7, 8-14). In the validation groups, IMACS categories stratified CV event risk (Figure). IMACS c-statistics for females were c=0.675 and c=0.734 in derivation and validation groups, respectively, and for males c=0.715 and c=0.672. Conclusion: Sex-specific IMACS risk scores strongly stratified 1- to 3-year post-MI risk of CV events. IMACS is an inexpensive electronic health record tool that empowers the evaluation of which post-MI patients may be the best candidates for more aggressive therapeutic management.

scholarly journals Use and Customization of Risk Scores for Predicting Cardiovascular Events Using Electronic Health Record Data

2017 ◽  
Vol 6 (4) ◽  
Author(s):  
Julian Wolfson ◽  
David M. Vock ◽  
Sunayan Bandyopadhyay ◽  
Thomas Kottke ◽  
Gabriela Vazquez‐Benitez ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Cardiovascular Events ◽  
Risk Scores ◽  
Health Record ◽  
Electronic Health Record Data ◽  
Record Data ◽  
Electronic Health

scholarly journals COMPARISON OF A FRAILTY RISK SCORE AND COMORBIDITY FOR EARLY REHOSPITALIZATION USING ELECTRONIC HEALTH RECORD DATA

2019 ◽  
Vol 3 (Supplement_1) ◽  
pp. S906-S906
Author(s):  
Deborah A Lekan ◽  
Thomas P McCoy ◽  
Marjorie Jenkins ◽  
Somya Mohanty ◽  
Prashanti Manda
Keyword(s):  
Electronic Health Record ◽  
Average Length ◽  
Laboratory Data ◽  
Hospital Setting ◽  
Adverse Outcomes ◽  
Risk Scores ◽  
Unplanned Readmission ◽  
Health Record ◽  
Electronic Health Record Data ◽  
Electronic Health

Abstract Frailty is a clinical syndrome of impaired homeostasis and decreased physiologic reserve and resilience resulting in diminished ability to recover from stressors. In the hospital setting, barriers to adoption of popular frailty assessments make them impractical for widespread use. Improving quality and costs associated with hospitalization has motivated using data from the electronic health record (EHR) to identify patients at risk for adverse outcomes such as early readmission. Patient-level factors such as frailty and comorbidity may signal high readmission risk. In this retrospective study and secondary analysis of EHR data, we investigated Frailty Risk Scores (FRS) in models that included sociodemographic, comorbidity, and laboratory data for early 3-, 7-, and 30-day unplanned readmission. Study data were collected from a health system in the Southeastern U.S. on adults >50 years with an inpatient stay of >24 hours, 2013-2017. Exclusions included planned readmission and in-hospital mortality. The FRS was constructed using ICD-10-CM codes mapped for symptoms, syndromes, and laboratory values. Cox and logistic regression were conducted to examine associations with readmission. Area under the receiver operating characteristic curve (AUC) quantified accuracy. The sample was 53% female and 73% non-Hispanic White (N=55,778). About one-third took at least 7 prescribed medications (34%) and average length of stay was 4.3 days (max=103.6). FRS was a significant predictor of readmission for almost all models, independently of three comorbidity indices (range AUC=.850-.854 for 3-day, .809-.813 for 7-day, and .757 to .768 for 30-day). Frailty and comorbidity are independently associated with early rehospitalization.

scholarly journals An Inflammatory Polymorphisms Risk Scoring System for the Differentiation of Ischemic Stroke Subtypes

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Elena Muiño ◽  
Jurek Krupinski ◽  
Caty Carrera ◽  
Cristina Gallego-Fabrega ◽  
Joan Montaner ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Genetic Risk ◽  
Scoring System ◽  
Cardioembolic Stroke ◽  
Risk Scores ◽  
Stroke Subtype ◽  
Stroke Subtypes ◽  
Risk Scoring ◽  
Risk Scoring System ◽  
Independent Cohort

Inflammation has been associated with atherothrombotic stroke and recently with cardioembolic stroke. Different genetic risk factors have been specifically associated with the subtypes of ischemic stroke (cardioembolic, atherothrombotic, and lacunar). However, there are no studies that have generated genetic risk scores for the different subtypes of ischemic stroke using polymorphisms associated with inflammation.Methods.We have analyzed 68 polymorphisms of 30 inflammatory mediator genes in 2,685 subjects: 1,987 stroke cases and 698 controls. We generated a genetic scoring system with the most significant polymorphisms weighted by the odds ratio of every polymorphism and taken into consideration the stroke subtype.Results.Three polymorphisms, rs1205 (CRPgene), rs1800779, and rs2257073 (NOS3gene), were associated with cardioembolic stroke (pvalue<0.05). The score generated was only associated with the cardioembolic stroke subtype (pvalue: 0.001) and was replicated in an independent cohort (pvalue: 0.017). The subjects with the highest score presented a cardioembolic stroke in 92.2% of the cases (pvalue: 0.002).Conclusion.The genetics of inflammatory markers is more closely associated with cardioembolic strokes than with atherothrombotic or lacunar strokes. The genetic risk scoring system could be useful in the prediction and differentiation of ischemic stroke; however, it might be specific to particular ischemic stroke subtypes.

scholarly journals Use and Customization of Risk Scores for Predicting Cardiovascular Events Using Electronic Health Record Data

2016 ◽  
Vol 3 (3) ◽  
pp. 203-204
Author(s):  
Patrick J O'Connor ◽  
Julian Wolfson ◽  
David Vock ◽  
Sunayan Bandyopadhyay ◽  
Gabriela Vasquez Benitez ◽  
...  
Keyword(s):  
Electronic Health Record ◽  
Cardiovascular Events ◽  
Risk Scores ◽  
Health Record ◽  
Electronic Health Record Data ◽  
Record Data ◽  
Electronic Health

TIMING OF ELECTRONIC HEALTH RECORD INTEGRATED DECISION AID (IDEA) FOR STROKE PREVENTION IN ATRIAL FIBRILLATION MATTERS

2019 ◽  
Vol 73 (9) ◽  
pp. 3005
Author(s):  
Stacey L. Schott ◽  
Keren Xu ◽  
Julia Berkowitz ◽  
Curtis Petersen ◽  
Catherine Saunders ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Electronic Health Record ◽  
Stroke Prevention ◽  
Decision Aid ◽  
Health Record ◽  
Electronic Health

scholarly journals Bleeding in cardiac patients prescribed antithrombotic drugs: electronic health record phenotyping algorithms, incidence, trends and prognosis

BMC Medicine ◽  
2019 ◽  
Vol 17 (1) ◽  
Author(s):  
Laura Pasea ◽  
Sheng-Chia Chung ◽  
Mar Pujades-Rodriguez ◽  
Anoop D. Shah ◽  
Samantha Alvarez-Madrazo ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Atrial Fibrillation ◽  
Primary Care ◽  
Acute Myocardial Infarction ◽  
Electronic Health Record ◽  
Stable Angina ◽  
Health Record ◽  
Bleeding Events ◽  
All Cause Mortality ◽  
Electronic Health

Abstract Background Clinical guidelines and public health authorities lack recommendations on scalable approaches to defining and monitoring the occurrence and severity of bleeding in populations prescribed antithrombotic therapy. Methods We examined linked primary care, hospital admission and death registry electronic health records (CALIBER 1998–2010, England) of patients with newly diagnosed atrial fibrillation, acute myocardial infarction, unstable angina or stable angina with the aim to develop algorithms for bleeding events. Using the developed bleeding phenotypes, Kaplan-Meier plots were used to estimate the incidence of bleeding events and we used Cox regression models to assess the prognosis for all-cause mortality, atherothrombotic events and further bleeding. Results We present electronic health record phenotyping algorithms for bleeding based on bleeding diagnosis in primary or hospital care, symptoms, transfusion, surgical procedures and haemoglobin values. In validation of the phenotype, we estimated a positive predictive value of 0.88 (95% CI 0.64, 0.99) for hospitalised bleeding. Amongst 128,815 patients, 27,259 (21.2%) had at least 1 bleeding event, with 5-year risks of bleeding of 29.1%, 21.9%, 25.3% and 23.4% following diagnoses of atrial fibrillation, acute myocardial infarction, unstable angina and stable angina, respectively. Rates of hospitalised bleeding per 1000 patients more than doubled from 1.02 (95% CI 0.83, 1.22) in January 1998 to 2.68 (95% CI 2.49, 2.88) in December 2009 coinciding with the increased rates of antiplatelet and vitamin K antagonist prescribing. Patients with hospitalised bleeding and primary care bleeding, with or without markers of severity, were at increased risk of all-cause mortality and atherothrombotic events compared to those with no bleeding. For example, the hazard ratio for all-cause mortality was 1.98 (95% CI 1.86, 2.11) for primary care bleeding with markers of severity and 1.99 (95% CI 1.92, 2.05) for hospitalised bleeding without markers of severity, compared to patients with no bleeding. Conclusions Electronic health record bleeding phenotyping algorithms offer a scalable approach to monitoring bleeding in the population. Incidence of bleeding has doubled in incidence since 1998, affects one in four cardiovascular disease patients, and is associated with poor prognosis. Efforts are required to tackle this iatrogenic epidemic.

Sign in / Sign up

Export Citation Format

Share Document