Related Experiment Video
Updated: Apr 9, 2026
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
AI-Derived LA Volume Index, LA/RA and LA/LV Volume Ratios From Coronary Artery Calcium Scans Predict Long-Term Atrial
Amir Azimi1, Kyle Atlas1, Anthony P Reeves2
1HeartLung.AI, Houston, TX (A.A., K.A., C.Z., S.R.M., M.M., A.H., M.N.).
Insights
Artificial intelligence (AI) analysis of coronary artery calcium (CAC) scans can predict atrial fibrillation (AF) and stroke risk using cardiac chamber metrics. These AI-derived measurements offer valuable insights beyond traditional scores for long-term patient outcomes.
Area of Science:
- Cardiovascular Imaging and AI
- Predictive Analytics in Cardiology
- Public Health and Stroke Prevention
Background:
- Coronary artery calcium (CAC) scans traditionally provide a CAC score.
- AI-CVD initiative explores extracting deeper insights from CAC scans.
- AI-derived cardiac chamber volumes predict atrial fibrillation (AF) and stroke, but prognostic value of chamber ratios is less understood.
Purpose of the Study:
- To evaluate the predictive value of AI-derived left atrial volume index and chamber ratios (LA/RA, LA/LV) from routine CAC scans for incident AF and stroke.
- To assess the incremental predictive value of these AI-derived metrics beyond established risk scores.
Main Methods:
- Pooled data from MESA (n=5670) and FHS (n=1142) prospective cohorts.
- AI-enabled volumetry (AutoChamber, AI-CVD platform) quantified cardiac chamber metrics from noncontrast CAC scans.
- Cox proportional hazards models, net reclassification improvement, and calibration metrics were used for analysis.
Main Results:
- Over 17 years, higher percentiles of AI-derived chamber metrics were associated with significantly increased risk of AF and stroke.
- AI-derived metrics improved risk reclassification beyond standard scores (CHA, Framingham Stroke Risk Profile), particularly for AF (left atrial volume index) and stroke (LA/RA ratio).
- Left atrial volume index and LA/RA ratio were identified as the strongest predictors for AF and stroke, respectively.
Conclusions:
- AI-enabled volumetric and ratio-based left atrial metrics from CAC scans offer incremental predictive value for AF and stroke.
- These opportunistic AI-derived metrics enhance risk prediction beyond traditional methods.
Background:
The AI-CVD initiative aims to extract actionable insights from coronary artery calcium (CAC) scans beyond the traditional CAC score. Although AI-derived cardiac chamber volumes predict atrial fibrillation (AF) and stroke, the long-term prognostic value of chamber ratios is less established. We evaluated the predictive value of AI-derived left atrial volume index and related chamber ratios (left atrial [LA]/right atrial [RA], LA/left ventricular) from routine CAC scans for incident AF and stroke, and their incremental value beyond established risk scores.
Methods:
Pooled participant-level data from 2 prospective cohorts, the MESA (Multi-Ethnic Study of Atherosclerosis, 2000-2002, n=5670) and the FHS (Framingham Heart Study Offspring cohort, 1998-2001, n=1142), were analyzed. Primary outcomes were incident AF and incident stroke. AI-enabled volumetry (AutoChamber, AI-CVD platform) quantified cardiac chamber metrics from noncontrast CAC scans. Cox proportional hazards models, net reclassification improvement, time-dependent area under the curve, calibration metrics, and least absolute shrinkage and selection operator regression were applied to evaluate predictive performance.
Results:
Over a median 17-year follow-up, 1302 participants developed AF, and 365 experienced stroke events. Individuals in the ≥95th percentile of chamber metrics had a significantly increased risk. Adjusted hazard ratios for AF were 2.66 (95% CI, 2.23-3.17) for left atrial volume index, 2.04 (95% CI, 1.71-2.45) for LA/left ventricular (LV) ratio, and 1.87 (95% CI, 1.55-2.26) for LA/RA ratio. For stroke, corresponding hazard ratios were 1.96 (95% CI, 1.38-2.77), 1.64 (95% CI, 1.15-2.33), and 1.83 (95% CI, 1.29-2.59), respectively. AI-derived metrics improved reclassification beyond Cohorts for Heart and Aging Research in Genomic Epidemiology Atrial Fibrillation risk score and Framingham Stroke Risk Profile, with greatest improvements for AF from left atrial volume index (net reclassification improvement, 0.48) and stroke from LA/RA ratio (net reclassification improvement, 0.39), driven mainly by nonevent classification. Although discrimination improvements (area under the curve ) were modest, chamber measurements substantially improved Framingham Stroke Risk Profile calibration (slope, 0.448 to 0.834-0.902). Among all chamber metrics (including volumes and ratios), the least absolute shrinkage and selection operator identified left atrial volume index as the strongest predictor for AF, and LA/RA ratio as the strongest for stroke.
Conclusions:
AI-enabled left atrial volumetric and ratio-based metrics derived opportunistically from CAC scans provide incremental predictive value for AF and stroke prediction.
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:22Aortic Regurgitation II: Clinical Features and Diagnostic Tests
01:30Acute Coronary Syndrome III: Diagnostic Studies