Abstract 4366855: AI-enabled Ascending Aorta and Pulmonary Trunk Volumetry in Coronary Artery Calcium Scans for Heart Failure Prediction: An AI-CVD Study within the Multi-Ethnic Study of Atherosclerosis (MESA)

Background: The AI-CVD initiative aims to extract all useful information from new or existing coronary artery calcium (CAC) scans. Previously, we have demonstrated that the automated cardiac chambers volumetry component of AI-CVD predicts incident atrial fibrillation and heart failure in the Multi-Ethnic Study of Atherosclerosis (MESA). In this report, we evaluate the AI-enabled volumetric measurements of the ascending aorta pulmonary artery component of AI-CVD for heart failure (HF) prediction. Methods: We applied AI-CVD to CAC scans of 5830 individuals (52.2% women, age 61.7±10.2 years) without known CVD that were previously obtained for CAC scoring at the baseline examination of the Multi-Ethnic Study of Atherosclerosis (MESA). The ascending aorta (AA) volume was measured using the entire AA including the aortic root. The pulmonary artery (PA) volume was measured using the entire pulmonary trunk plus right and left PA. We normalized volumes by body surface area (BSA) to account for differences in body size. We assessed the potential of these measurements using incidence for association with incident HF. The log-rank test was used to determine group differences in incidence. Results: Over 15 years follow-up, 283 HF events accrued. The mean ± SD for AA and PA volume was 104.2 ± 30.1 and 32.4 ± 16.5 cc, respectively. The top quartile of AA volume had significantly higher incidence of HF (9.6%) compared to the bottom quartile (3.1%) (p<0.0001). The top quartile of PA volume had significantly higher incidence of HF (5.9%) compared to the bottom quartile (2.5%) (p<0.0001). Notably, the 99 th percentile of PA volume had significantly higher incidence of HF (24.8%) compared to the 75 th percentile (5.9%) (p<0.0001). The age and BSA adjusted hazard ratio for AI-CVD asending aorta volume and PA volume were HF: 2.35 (95% CI: 1.0 - 5.53), and HF: 3.28 (95% CI: 1.46 - 7.36) respectively (p<0.001). Conclusion: Elevated AA and PA volumes were associated with incident HF over 15 years follow-up. These measurements can be easily measured in new or existing CAC scans for additional HF risk stratification. More studies are warranted to investigate the potential of these measurements for early detection of at-risk patients.

Authors

Institutions

Publication Details

Journal
Circulation
Published
2025-11-03
DOI
https://doi.org/10.1161/circ.152.suppl_3.4366855
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Abstract 4366855: AI-enabled Ascending Aorta and Pulmonary Trunk Volumetry in Coronary Artery Calcium Scans for Heart Failure Prediction: An AI-CVD Study within the Multi-Ethnic Study of Atherosclerosis (MESA)

Morteza Naghavi, Claudia I. Henschke, Nathan Wong, Anthony P. Reeves et al.
Circulation
Artificial Intelligence in Healthcare and Education
article

Abstract 4366855: AI-enabled Ascending Aorta and Pulmonary Trunk Volumetry in Coronary Artery Calcium Scans for Heart Failure Prediction: An AI-CVD Study within the Multi-Ethnic Study of Atherosclerosis (MESA)

Morteza Naghavi, Claudia I. Henschke, Nathan Wong, Anthony P. Reeves, Jakob Wasserthal, Thomas Atlas, K. Atlas, Chenyu Zhang, David F. Yankelevitz
article en

Abstract

Background: The AI-CVD initiative aims to extract all useful information from new or existing coronary artery calcium (CAC) scans. Previously, we have demonstrated that the automated cardiac chambers volumetry component of AI-CVD predicts incident atrial fibrillation and heart failure in the Multi-Ethnic Study of Atherosclerosis (MESA). In this report, we evaluate the AI-enabled volumetric measurements of the ascending aorta pulmonary artery component of AI-CVD for heart failure (HF) prediction. Methods: We applied AI-CVD to CAC scans of 5830 individuals (52.2% women, age 61.7±10.2 years) without known CVD that were previously obtained for CAC scoring at the baseline examination of the Multi-Ethnic Study of Atherosclerosis (MESA). The ascending aorta (AA) volume was measured using the entire AA including the aortic root. The pulmonary artery (PA) volume was measured using the entire pulmonary trunk plus right and left PA. We normalized volumes by body surface area (BSA) to account for differences in body size. We assessed the potential of these measurements using incidence for association with incident HF. The log-rank test was used to determine group differences in incidence. Results: Over 15 years follow-up, 283 HF events accrued. The mean ± SD for AA and PA volume was 104.2 ± 30.1 and 32.4 ± 16.5 cc, respectively. The top quartile of AA volume had significantly higher incidence of HF (9.6%) compared to the bottom quartile (3.1%) (p<0.0001). The top quartile of PA volume had significantly higher incidence of HF (5.9%) compared to the bottom quartile (2.5%) (p<0.0001). Notably, the 99 th percentile of PA volume had significantly higher incidence of HF (24.8%) compared to the 75 th percentile (5.9%) (p<0.0001). The age and BSA adjusted hazard ratio for AI-CVD asending aorta volume and PA volume were HF: 2.35 (95% CI: 1.0 - 5.53), and HF: 3.28 (95% CI: 1.46 - 7.36) respectively (p<0.001). Conclusion: Elevated AA and PA volumes were associated with incident HF over 15 years follow-up. These measurements can be easily measured in new or existing CAC scans for additional HF risk stratification. More studies are warranted to investigate the potential of these measurements for early detection of at-risk patients.

CirculationVol. 152(Suppl_3)
University of California, Irvine (US), Cornell University (US), Mount Sinai Hospital (US), Heart Imaging Technologies (United States) (US), Irvine University (US)
Openalex Percentile: Top 75%
Artificial Intelligence in Healthcare and Education
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.