Abstract 13771: Combining Clinical and Polygenic Risk Improves Stroke Prediction Among Individuals With Atrial Fibrillation

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Jack W Osullivan ◽  
Anna Shcherbina ◽  
Johanne M Justesen ◽  
Mintu Turakhia ◽  
Marco V Perez ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Predictive Ability ◽  
Clinical Risk Factors ◽  
Risk Scores ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Clinical Risk ◽  
Increased Risk

Introduction: Atrial fibrillation (AF) is associated with a five-fold increased risk of ischemic stroke. A portion of this risk is heritable, however current risk stratification tools (CHA 2 DS 2 -VASc) don’t include family history or genetic risk. Hypothesis: A polygenic risk scores (PRS) is both independently, and in integrated with clinical risk factors, predictive of ischemic stroke in patients with Atrial Fibrillation. Methods: Using data from the largest available GWAS in Europeans, we combined over half a million genetic variants to construct a PRS to predict ischemic stroke in patients with AF. We externally validated this PRS in independent data from the UK Biobank (UK Biobank), both independently and integrated with clinical risk factors. Results: The integrated PRS and clinical risk factors risk tool had the greatest predictive ability. Compared with the currently recommended risk tool (CHA 2 DS 2 -VASc), the integrated tool significantly improved net reclassification (NRI: 2.3% (95%CI: 1.3% to 3.0%)), and fit (χ2 P =0.002). Independently, PRS was a significant predictor of ischemic stroke in patients with AF prospectively (Hazard Ratio: 1.13 per 1 SD (95%CI: 1.04 to 1.21)). Lastly, polygenic risk scores were uncorrelated with clinical risk factors (Pearson’s correlation coefficient: -0.018). Conclusions: In patients with AF, there appears to be a significant association between PRS and risk of ischemic stroke. The greatest predictive ability was found with the integration of PRS and clinical risk factors, however the prediction of stroke remains challenging.

scholarly journals Combining clinical and polygenic risk improves stroke prediction among individuals with atrial fibrillation

2020 ◽  
Author(s):  
Jack W. O’Sullivan ◽  
Anna Shcherbina ◽  
Johanne M Justesen ◽  
Mintu Turakhia ◽  
Marco Perez ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Predictive Ability ◽  
Clinical Risk Factors ◽  
Risk Scores ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Clinical Risk ◽  
Increased Risk

AbstractBackgroundAtrial fibrillation (AF) is associated with a five-fold increased risk of ischemic stroke. A portion of this risk is heritable, however current risk stratification tools (CHA2DS2-VASc) don’t include family history or genetic risk. We hypothesized that we could improve ischemic stroke prediction in patients with AF by incorporating polygenic risk scores (PRS).ObjectivesTo construct and test a PRS to predict ischemic stroke in patients with AF, both independently and integrated with clinical risk factors.MethodsUsing data from the largest available GWAS in Europeans, we combined over half a million genetic variants to construct a PRS to predict ischemic stroke in patients with AF. We externally validated this PRS in independent data from the UK Biobank (UK Biobank), both independently and integrated with clinical risk factors.ResultsThe integrated PRS and clinical risk factors risk tool had the greatest predictive ability. Compared with the currently recommended risk tool (CHA2DS2-VASc), the integrated tool significantly improved net reclassification (NRI: 2.3% (95%CI: 1.3% to 3.0%)), and fit (χ2 P =0.002). Using this improved tool, >115,000 people with AF would have improved risk classification in the US. Independently, PRS was a significant predictor of ischemic stroke in patients with AF prospectively (Hazard Ratio: 1.13 per 1 SD (95%CI: 1.06 to 1.23))). Lastly, polygenic risk scores were uncorrelated with clinical risk factors (Pearson’s correlation coefficient: −0.018).ConclusionsIn patients with AF, there appears to be a significant association between PRS and risk of ischemic stroke. The greatest predictive ability was found with the integration of PRS and clinical risk factors, however the prediction of stroke remains challenging.

scholarly journals Combining Clinical and Polygenic Risk Improves Stroke Prediction Among Individuals with Atrial Fibrillation

2021 ◽  
Author(s):  
Jack W. O'Sullivan ◽  
Anna Shcherbina ◽  
Johanne M. Justesen ◽  
Mintu Turakhia ◽  
Marco Perez ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Predictive Ability ◽  
Clinical Risk Factors ◽  
Risk Scores ◽  
Polygenic Risk ◽  
Clinical Risk ◽  
Increased Risk ◽  
The Uk

Background - Atrial fibrillation (AF) is associated with a five-fold increased risk of ischemic stroke. A portion of this risk is heritable, however current risk stratification tools (CHA 2 DS 2 -VASc) don't include family history or genetic risk. We hypothesized that we could improve ischemic stroke prediction in patients with AF by incorporating polygenic risk scores (PRS). Methods - Using data from the largest available GWAS in Europeans, we combined over half a million genetic variants to construct a PRS to predict ischemic stroke in patients with AF. We externally validated this PRS in independent data from the UK Biobank, both independently and integrated with clinical risk factors. The integrated PRS and clinical risk factors risk tool had the greatest predictive ability. Results - Compared with the currently recommended risk tool (CHA 2 DS 2 -VASc), the integrated tool significantly improved net reclassification (NRI: 2.3% (95%CI: 1.3% to 3.0%)), and fit (χ2 P =0.002). Using this improved tool, >115,000 people with AF would have improved risk classification in the US. Independently, PRS was a significant predictor of ischemic stroke in patients with AF prospectively (Hazard Ratio: 1.13 per 1 SD (95%CI: 1.06 to 1.23)). Lastly, polygenic risk scores were uncorrelated with clinical risk factors (Pearson's correlation coefficient: -0.018). Conclusions - In patients with AF, there appears to be a significant association between PRS and risk of ischemic stroke. The greatest predictive ability was found with the integration of PRS and clinical risk factors, however the prediction of stroke remains challenging.

scholarly journals Clinical Application of a Novel Genetic Risk Score for Ischemic Stroke in Patients with Cardiometabolic Disease

Circulation ◽  
2020 ◽  
Author(s):  
Nicholas A. Marston ◽  
Parth N. Patel ◽  
Frederick K. Kamanu ◽  
Francesco Nordio ◽  
Giorgio M. Melloni ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Genetic Risk ◽  
Genetic Risk Score ◽  
Clinical Risk Factors ◽  
Cardiometabolic Disease ◽  
Clinical Risk ◽  
Hazard Ratios ◽  
Increased Risk

Background: Genome-wide association studies have identified single nucleotide polymorphisms (SNPs) that are associated with an increased risk of stroke. We sought to determine whether a genetic risk score (GRS) could identify subjects at higher risk for ischemic stroke after accounting for traditional clinical risk factors in five trials across the spectrum of cardiometabolic disease. Methods: Subjects who had consented for genetic testing and who were of European ancestry from the ENGAGE AF-TIMI 48, SOLID-TIMI 52, SAVOR-TIMI 53, PEGASUS-TIMI 54, and FOURIER trials were included in this analysis. A set of 32 SNPs associated with ischemic stroke was used to calculate a GRS in each patient and identify tertiles of genetic risk. A Cox model was used to calculate hazard ratios for ischemic stroke across genetic risk groups, adjusted for clinical risk factors. Results: In 51,288 subjects across the five trials, a total of 960 subjects had an ischemic stroke over a median follow-up period of 2.5 years. After adjusting for clinical risk factors, increasing genetic risk was strongly and independently associated with increased risk for ischemic stroke (p-trend=0.009). When compared to individuals in the lowest third of genetic risk, individuals in the middle and top tertiles of genetic risk had adjusted hazard ratios of 1.15 (95% CI 0.98-1.36) and 1.24 (95% CI 1.05-1.45) for ischemic stroke, respectively. Stratification into subgroups revealed the performance of the GRS appeared stronger in the primary prevention cohort with an adjusted HR for the top versus lowest tertile of 1.27 (95% CI 1.04-1.53), compared with an adjusted HR of 1.06 (95% CI 0.81-1.41) in subjects with prior stroke. In an exploratory analysis of patients with atrial fibrillation and CHA 2 DS 2 -VASc of 2, high genetic risk conferred a 4-fold higher risk of stroke and an absolute risk equivalent to those with CHA 2 DS 2 -VASc of 3. Conclusions: Across a broad spectrum of subjects with cardiometabolic disease, a 32-SNP GRS was a strong, independent predictor of ischemic stroke. In patients with atrial fibrillation but lower CHA 2 DS 2 -VASc scores, the GRS identified patients with risk comparable to those with higher CHA 2 DS 2 -VASc scores.

scholarly journals Association between clinical risk scores and mortality in atrial fibrillation: Systematic review and network meta-regression of 669,000 patients

2018 ◽  
Vol 27 (6) ◽  
pp. 633-644 ◽  
Author(s):  
Marco Proietti ◽  
Alessio Farcomeni ◽  
Giulio Francesco Romiti ◽  
Arianna Di Rocco ◽  
Filippo Placentino ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Predictive Ability ◽  
Risk Scores ◽  
Clinical Risk ◽  
Increased Risk ◽  
High Negative Predictive Value ◽  
Meta Regression

Aims Many clinical scores for risk stratification in patients with atrial fibrillation have been proposed, and some have been useful in predicting all-cause mortality. We aim to analyse the relationship between clinical risk score and all-cause death occurrence in atrial fibrillation patients. Methods We performed a systematic search in PubMed and Scopus from inception to 22 July 2017. We considered the following scores: ATRIA-Stroke, ATRIA-Bleeding, CHADS2, CHA2DS2-VASc, HAS-BLED, HATCH and ORBIT. Papers reporting data about scores and all-cause death rates were considered. Results Fifty studies and 71 scores groups were included in the analysis, with 669,217 patients. Data on ATRIA-Bleeding, CHADS2, CHA2DS2-VASc and HAS-BLED were available. All the scores were significantly associated with an increased risk for all-cause death. All the scores showed modest predictive ability at five years (c-indexes (95% confidence interval) CHADS2: 0.64 (0.63–0.65), CHA2DS2-VASc: 0.62 (0.61–0.64), HAS-BLED: 0.62 (0.58–0.66)). Network meta-regression found no significant differences in predictive ability. CHA2DS2-VASc score had consistently high negative predictive value (≥94%) at one, three and five years of follow-up; conversely it showed the highest probability of being the best performing score (63% at one year, 60% at three years, 68% at five years). Conclusion In atrial fibrillation patients, contemporary clinical risk scores are associated with an increased risk of all-cause death. Use of these scores for death prediction in atrial fibrillation patients could be considered as part of holistic clinical assessment. The CHA2DS2-VASc score had consistently high negative predictive value during follow-up and the highest probability of being the best performing clinical score.

scholarly journals Comparisons of Polyexposure, Polygenic, and Clinical Risk Scores in Risk Prediction of Type 2 Diabetes

2021 ◽  
Author(s):  
Yixuan He ◽  
Chirag M Lakhani ◽  
Danielle Rasooly ◽  
Arjun K Manrai ◽  
Ioanna Tzoulaki ◽  
...  
Keyword(s):  
Risk Factors ◽  
Risk Prediction ◽  
Risk Score ◽  
Prediction Models ◽  
Disease Risk ◽  
Clinical Risk Factors ◽  
Risk Scores ◽  
Polygenic Risk Score ◽  
Polygenic Risk ◽  
Clinical Risk

OBJECTIVE: <p>Establish a polyexposure score for T2D incorporating 12 non-genetic exposure and examine whether a polyexposure and/or a polygenic risk score improves diabetes prediction beyond traditional clinical risk factors.</p> <h2><a></a>RESEARCH DESIGN AND METHODS:</h2> <p>We identified 356,621 unrelated individuals from the UK Biobank of white British ancestry with no prior diagnosis of T2D and normal HbA1c levels. Using self-reported and hospital admission information, we deployed a machine learning procedure to select the most predictive and robust factors out of 111 non-genetically ascertained exposure and lifestyle variables for the polyexposure risk score (PXS) in prospective T2D. We computed the clinical risk score (CRS) and polygenic risk score (PGS) by taking a weighted sum of eight established clinical risk factors and over six million SNPs, respectively.</p> <h2><a></a>RESULTS:</h2> <p>In the study population, 7,513 had incident T2D. The C-statistics for the PGS, PXS, and CRS models were 0.709, 0.762, and 0.839, respectively. Hazard ratios (HR) associated with risk score values in the top 10% percentile versus the remaining population is 2.00, 5.90, and 9.97 for PGS, PXS, and CRS respectively. Addition of PGS and PXS to CRS improves T2D classification accuracy with a continuous net reclassification index of 15.2% and 30.1% for cases, respectively, and 7.3% and 16.9% for controls, respectively. </p> <h2><a></a>CONCLUSIONS:</h2> <p>For T2D, the PXS provides modest incremental predictive value over established clinical risk factors. The concept of PXS merits further consideration in T2D risk stratification and is likely to be useful in other chronic disease risk prediction models.</p>

scholarly journals Improving prediction of atrial fibrillation: the impact of polygenic risk scores over conventional risk factors amongst 270,000 individuals in UK Biobank

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
A Von Ende ◽  
B Casadei ◽  
J.C Hopewell
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Risk Score ◽  
Genetic Risk ◽  
Genetic Information ◽  
Risk Scores ◽  
Funding Source ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Conventional Risk Factors

Abstract Background Previous studies have suggested only modest benefits of adding genetic information to conventional risk factors for prediction of atrial fibrillation (AF). However, these studies have been based on limited numbers of AF cases and pre-date recent AF genetic discoveries. Purpose To examine the independent relevance of common genetic risk factors over and above established non-genetic risk factors for predicting AF amongst 270,000 participants from UK Biobank, and to determine potential clinical utility. Methods UK Biobank (UKB) is a large prospective study of over 500,000 British individuals aged 40 to 69 years at recruitment. Incident AF was ascertained using hospital episode statistics and death registry data. The CHARGE-AF score, which combines the relevance of age, height, weight, blood pressure, use of antihypertensives, diabetes, heart failure, and myocardial infarction (MI) was used to estimate 5-year risk of AF at baseline. A polygenic risk score (PRS) was constructed based on 142 independent variants previously associated with AF in a genome-wide meta-analysis of 60,620 AF cases from the AFGen Consortium, weighted by their published effect sizes. A total of 270,254 individuals were analysed after exclusions for genetic QC, non-White British ancestry, and prevalent AF. Cox proportional hazard models were used to estimate associations between risk scores (based on standard deviation [SD] units) and incident AF. Standard methods were used to assess predictive value. Results During a median follow-up of 8.1 years, 12,407 incident AF cases were identified. The CHARGE-AF risk score strongly predicted incident AF in UK Biobank, and was associated with a ∼3-fold higher risk of AF per SD (Hazard ratio [HR]=2.88; 95% CI: 2.82–2.94). The PRS was associated with a 54% higher risk of AF per SD (HR=1.54; 95% CI: 1.51–1.57). The independent impact of the PRS, after adjusting for the CHARGE-AF score, was unchanged and remained strongly predictive (HR=1.57, 95% CI: 1.54–1.60), with participants in the upper tertile of the PRS having more than a 2.5-fold higher risk (HR=2.59, 95% CI: 2.47–2.71) when compared with those in the lower tertile. The addition of the PRS improved the C-statistic from 0.758 (CHARGE-AF alone) to 0.783 (Δ=0.025) and correctly reclassified 8.7% of cases and 2.6% of controls at 5 years. Both non-genetic and genetic risk scores were well-calibrated in the UK Biobank participants, and sensitivity of the results to alternative PRS selection approaches and age at risk were also examined. Conclusion In a large prospective cohort, genetic determinants of AF were independent of conventional risk factors and significantly improved prediction over a well-validated clinical risk algorithm. This illustrates the potential added benefit of genetic information to identify higher-risk individuals who may benefit from earlier monitoring and personalised risk management strategies. Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): British Heart Foundation

scholarly journals Electrocardiogram-based Deep Learning and Clinical Risk Factors to Predict Atrial Fibrillation

Circulation ◽  
2021 ◽  
Author(s):  
Shaan Khurshid ◽  
Samuel Friedman ◽  
Christopher Reeder ◽  
Paolo Di Achille ◽  
Nathaniel Diamant ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Efficient Estimation ◽  
P Wave ◽  
Clinical Risk Factors ◽  
Calibration Error ◽  
Uk Biobank ◽  
Clinical Risk ◽  
Test Sets ◽  
Linear Predictors

Background: Artificial intelligence (AI)-enabled analysis of 12-lead electrocardiograms (ECGs) may facilitate efficient estimation of incident atrial fibrillation (AF) risk. However, it remains unclear whether AI provides meaningful and generalizable improvement in predictive accuracy beyond clinical risk factors for AF. Methods: We trained a convolutional neural network ("ECG-AI") to infer 5-year incident AF risk using 12-lead ECGs in patients receiving longitudinal primary care at Massachusetts General Hospital (MGH). We then fit three Cox proportional hazards models, each composed of: a) ECG-AI 5-year AF probability, b) the Cohorts for Heart and Aging in Genomic Epidemiology AF (CHARGE-AF) clinical risk score, and c) terms for both ECG-AI and CHARGE-AF ("CH-AI"). We assessed model performance by calculating discrimination (area under the receiver operating characteristic curve, AUROC) and calibration in an internal test set and two external test sets (Brigham and Women's Hospital and UK Biobank). Models were recalibrated to estimate 2-year AF risk in the UK Biobank given limited available follow-up. We used saliency mapping to identify ECG features most influential on ECG-AI risk predictions and assessed correlation between ECG-AI and CHARGE-AF linear predictors. Results: The training set comprised 45,770 individuals (age 55±17 years, 53% women, 2,171 AF events), and the test sets comprised 83,162 individuals (age 59±13 years, 56% women, 2,424 AF events). AUROC was comparable using CHARGE-AF (MGH 0.802, 95% CI 0.767-0.836; BWH 0.752, 95% CI 0.741-0.763; UK Biobank 0.732, 95% CI 0.704-0.759) and ECG-AI (MGH 0.823, 95% CI 0.790-0.856; BWH 0.747, 95% CI 0.736-0.759; UK Biobank 0.705, 95% CI 0.673-0.737). AUROC was highest using CH-AI: MGH 0.838, 95% CI 0.807-0.869; BWH 0.777, 95% CI 0.766-0.788; UK Biobank 0.746, 95% CI 0.716-0.776). Calibration error was low using ECG-AI (MGH 0.0212; BWH 0.0129; UK Biobank 0.0035) and CH-AI (MGH 0.012; BWH 0.0108; UK Biobank 0.0001). In saliency analyses, the ECG P-wave had the greatest influence on AI model predictions. ECG-AI and CHARGE-AF linear predictors were correlated (Pearson r MGH 0.61, BWH 0.66, UK Biobank 0.41). Conclusions: AI-based analysis of 12-lead ECGs has similar predictive utility to a clinical risk factor model for incident AF and both approaches are complementary. ECG-AI may enable efficient quantification of future AF risk.

scholarly journals An integrated clinical and genetic model for predicting risk of severe COVID-19: A population-based case–control study

PLoS ONE ◽  
2021 ◽  
Vol 16 (2) ◽  
pp. e0247205 ◽  
Author(s):  
Gillian S. Dite ◽  
Nicholas M. Murphy ◽  
Richard Allman
Keyword(s):  
Risk Factors ◽  
Confidence Interval ◽  
Severe Disease ◽  
Accurate Prediction ◽  
Clinical Risk Factors ◽  
Uk Biobank ◽  
Age And Gender ◽  
Clinical Risk ◽  
Increased Risk ◽  
And Gender

Up to 30% of people who test positive to SARS-CoV-2 will develop severe COVID-19 and require hospitalisation. Age, gender, and comorbidities are known to be risk factors for severe COVID-19 but are generally considered independently without accurate knowledge of the magnitude of their effect on risk, potentially resulting in incorrect risk estimation. There is an urgent need for accurate prediction of the risk of severe COVID-19 for use in workplaces and healthcare settings, and for individual risk management. Clinical risk factors and a panel of 64 single-nucleotide polymorphisms were identified from published data. We used logistic regression to develop a model for severe COVID-19 in 1,582 UK Biobank participants aged 50 years and over who tested positive for the SARS-CoV-2 virus: 1,018 with severe disease and 564 without severe disease. Model discrimination was assessed using the area under the receiver operating characteristic curve (AUC). A model incorporating the SNP score and clinical risk factors (AUC = 0.786; 95% confidence interval = 0.763 to 0.808) had 111% better discrimination of disease severity than a model with just age and gender (AUC = 0.635; 95% confidence interval = 0.607 to 0.662). The effects of age and gender are attenuated by the other risk factors, suggesting that it is those risk factors–not age and gender–that confer risk of severe disease. In the whole UK Biobank, most are at low or only slightly elevated risk, but one-third are at two-fold or more increased risk. We have developed a model that enables accurate prediction of severe COVID-19. Continuing to rely on age and gender alone (or only clinical factors) to determine risk of severe COVID-19 will unnecessarily classify healthy older people as being at high risk and will fail to accurately quantify the increased risk for younger people with comorbidities.

scholarly journals Cholesterol reducer and Thrombolytic therapy in acute ischemic stroke

2020 ◽  
Author(s):  
Nicolas Poupore ◽  
Dan Strat ◽  
Tristan Mackey ◽  
Katherine Brown ◽  
Ashley Snell ◽  
...  
Keyword(s):  
Risk Factors ◽  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Demographic Data ◽  
Recombinant Tissue Plasminogen Activator ◽  
Clinical Risk Factors ◽  
Medication History ◽  
Factors Associated ◽  
Clinical Risk

Abstract Background Specific clinical risk factors may contribute to worsening or improving neurological functions in an acute ischemic stroke (AIS) patient pre-treated with a cholesterol reducer with a subsequent recombinant tissue plasminogen activator (rtPA) treatment. We investigated clinical risk factors associated with good or poor presenting neurological symptoms in ischemic stroke patients with prior cholesterol reducer use, specifically a statin and rtPA therapy.Methods We retrospectively analyzed baseline clinical and demographic data of 630 patients with AIS taking cholesterol reducers prior to rtPA treatment from January 2010 to June 2016 in a regional stroke center. Progressing (NIHSS ≤ 7) or worsening (NIHSS > 7) scores for neurologic improvement determined measures for treatment outcome. Multivariate logistic regression models identified demographic and clinical factors associated with worsening or progressing neurologic functions.Results Adjusted multivariate analysis showed that in an ischemic stroke population with a combined rtPA and cholesterol reducer medication history, increasing age (OR = 1.032, 95% CI, 1.015-1.048, P < 0.001) and atrial fibrillation (OR = 1.859, 95% CI, 1.098-3.149, P = 0.021) demonstrated a likely association with worsening neurologic functions, while direct admission (OR = 0.411, 95% CI, 0.246-0.686, P = 0.001) and being Caucasian (OR = 0.496, 95% CI, 0.297-0.827, P = 0.007) showed an association with improving or progressing neurologic functions.Conclusion A prior cholesterol reducer, namely a statin, plus rtPA combination may be associated with worsening neurological function for elderly AIS patients with atrial fibrillation, while Caucasians directly admitted to a neurology unit are more likely to show an association with progress or improvements in neurologic functions.

Sign in / Sign up

Export Citation Format

Share Document