Discriminative Accuracy of CHA2DS2-VASc Score, and Development of Predictive Accuracy Model Using Machine Learning for Ischemic Stroke Risk in Cardiac Amyloidosis and Atrial Fibrillation.

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.