Related Experiment Video
Updated: Jan 12, 2026
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Discriminative Accuracy of CHA2DS2-VASc Score, and Development of Predictive Accuracy Model Using Machine Learning
Waqas Ullah1, Abhinav Nair2, Eric Warner3
1Department of Interventional Cardiology, University of Massachusetts, Worcester, MA, USA.
Insights
The CHA2DS2-VASc score underestimates stroke risk in cardiac amyloidosis with atrial fibrillation (CA-AF). A new E-CHADS score, incorporating ESRD, dementia, and cancer, shows improved prediction accuracy for ischemic stroke in CA-AF patients.
Area of Science:
- Cardiology
- Neurology
- Geriatrics
Background:
- Cardiac amyloidosis (CA) with atrial fibrillation (AF) poses a significant risk for ischemic stroke.
- The current CHA2DS2-VASc score is insufficient for accurately predicting stroke risk in CA-AF patients.
Purpose of the Study:
- To evaluate the predictive accuracy of the CHA2DS2-VASc score for ischemic stroke in CA-AF patients.
- To develop and validate a novel, more accurate stroke risk prediction model for CA-AF patients.
Main Methods:
- Utilized the National Readmission Database (NRD) to compare outcomes between CA-AF and non-CA-AF patients.
- Employed multivariate regression and the AutoScore machine learning framework to develop a new stroke risk model.
- Assessed model performance using receiver operating characteristic analysis and area under the curve (AUC).
Main Results:
- The CHA2DS2-VASc score demonstrated poor discriminative accuracy for 30-day stroke risk in CA-AF (AUC 49%).
- The novel E-CHADS score (ESRD, CHF, HTN, cancer, dementia, DM) achieved excellent predictive ability for 30-day ischemic stroke risk in CA-AF (AUC 80%).
- CA-AF patients exhibited significantly higher adjusted odds of mortality, stroke, and hemorrhage compared to non-CA-AF patients.
Conclusions:
- The CHA2DS2-VASc score is inadequate for predicting ischemic stroke in patients with CA and AF.
- The proposed E-CHADS score, incorporating ESRD, dementia, and cancer, offers superior discriminative accuracy for ischemic stroke risk in this population.
Background:
CHA2DS2-VASc score in cardiac amyloidosis (CA) with atrial fibrillation (AF) is believed to underestimate ischemic stroke risk, necessitating a better predictive model.
Methods:
Data were obtained from the National Readmission Database (NRD). Outcomes between CA-AF and no-CA-AF were compared using multivariate regression analysis to calculate adjusted odds ratios (aORs). AutoScore, an interpretable machine learning framework, was used to develop a stroke risk prediction model, and its predictive accuracy was evaluated with an area under the curve (AUC) using the receiver operating characteristic analysis.
Results:
A total of 11,860,804 (CA-AF 22,687 (0.19%) and no-CA-AF 11,838,117) patients were identified from 2015 to 2019. The adjusted odds of mortality (aOR: 1.41 and 1.29), stroke (aOR: 1.78 and 1.74), non-intracranial hemorrhage (aOR: 2.10 and 1.85), and intracranial hemorrhage (aOR: 14.4 and 4.26) were significantly higher in CA-AF compared with non-CA-AF at both index admission and 30 days, respectively. The CHA2DS2-VASc score had a poor discriminative accuracy for stroke at 30 days in CA-AF (AUC 49%, 95% confidence interval (CI): 47 - 51, P = 0.54). The machine learning autoscore integrative model revealed excellent predictive ability of our newly proposed E-CHADS score (end-stage renal disease (ESRD), congestive heart failure (CHF), hypertension (HTN), cancer, dementia, and diabetes mellitus (DM)) for 30-day risk of ischemic stroke in CA-AF (cutoff of 52 points random forest score) with an AUC of 80% (95% CI: 74 - 86).
Conclusions:
CA with AF carries a high risk of ischemic stroke that is not accurately predicted by the CHA2DS2-VASc score. Our proposed model (E-CHADS) identifies three new variables (ESRD, dementia, and cancer) that have higher discriminative accuracy for ischemic stroke in these patients.
