Scientific Sessions 2024  /  AI at Heart: Revolutionizing Cardiovascular Imaging  /  Incorporating AI-enabled Left Atrial Volume Measurement from Coronary Artery Calcium Scans (AI-CAC) to CHA2DS2s-VASc Risk Score Improves Stroke Prediction in the Asymptomatic Population: The Multi-Ethnic Study of Atherosclerosis
Logo

American Heart Association

  131
  0

Final ID: Su3048

Incorporating AI-enabled Left Atrial Volume Measurement from Coronary Artery Calcium Scans (AI-CAC) to CHA2DS2s-VASc Risk Score Improves Stroke Prediction in the Asymptomatic Population: The Multi-Ethnic Study of Atherosclerosis

Abstract Body (Do not enter title and authors here):
Background: The CHA2DS2-VASc risk score is a clinical tool for stroke prediction. It is mainly used in patients with atrial fibrillation (AF) but is also applied to the non-AF population. We previously reported that artificial intelligence (AI)-enabled left atrial (LA) volumetry from coronary artery calcium (CAC) scans (AI-CAC) predicts AF as early as one year and outperformed CHARGE-AF and NT-proBNP. In this report, we compare AI-CAC LA volumetry to the CHA2DS2-VASc risk score and evaluate the incremental value of incorporating AI-CAC LA volume to CHA2DS2-VASc for incident stroke prediction in the non-AF population.
Methods: We applied the AutoChamberTM LA volumetry component of AI-CAC to CAC scans of 5830 people without AF (52.2% women, age 61.7±10.2 years) enrolled in the Multi-Ethnic Study of Atherosclerosis (MESA) baseline (2000-2002). We used the 15-year outcomes data for incident stroke (ischemic and hemorrhagic) and assessed discrimination using the time-dependent area under the curve (AUC) between AI-CAC LA volume vs. CHA2DS2-VASc risk score. Notably, the CHA2DS2-VASc score in this non-AF population ranges from 0 to 5, whereas in the AF population it typically ranges from 0 to 9 points.
Results: 252 cases of stroke accrued over 15 years. The median and mean ± SD of CHA2DS2-VASc score at baseline were 1.0 and 1.58 ± 1.15, respectively. The cumulative incidence of stroke for the 95th percentile of AI-CAC LA volume (n=291) vs. CHA2DS2-VASc 4 or 5 points (n=364) was 13.0% and 13.7%, respectively. AI-CAC LA volume significantly improved the AUC of CHA2DS2-VASc for stroke prediction at 2-year follow-up (0.76 for CHA2DS2-VASc vs. 0.81 for CHA2DS2-VASc plus LA volume, p=0.03), 5-year follow-up (0.73 vs. 0.77, p=0.01), 10-year follow-up (0.70 vs. 0.75, p<0.0001) and 15- year follow-up (0.70 vs. 0.74, p<0.0001).
Conclusion: In this multi-ethnic longitudinal cohort of people without AF, addition of LA volume significantly improved performance of the CHA2DS2-VASc risk score for stroke prediction from 2 to 15 years follow-up. Further studies are needed to evaluate the clinical utility of adding LA volume to CHA2DS2-VASc risk score in people with and without AF.
  • Naghavi, Morteza  ( HeartLung.AI , Houston , Texas , United States )
  • Reeves, Anthony  ( Cornell University , Ithaca , New York , United States )
  • Atlas, Kyle  ( HeartLung.AI , Houston , Texas , United States )
  • Zhang, Chenyu  ( HeartLung.AI , Houston , Texas , United States )
  • Atlas, Thomas  ( Tustin Teleradiology , Tustin , California , United States )
  • Henschke, Claudia  ( Mount Sinai Hospital , New York , New York , United States )
  • Yankelevitz, David  ( Mount Sinai Hospital , New York , New York , United States )
  • Budoff, Matthew  ( LUNDQUIST INSTITUTE , Torrance , California , United States )
  • Fan, Wenjun  ( University of California Irvine , Irvine , California , United States )
  • Yu, Ruilin  ( UCLA , Los Angeles , California , United States )
  • Branch, Andrea  ( Mount Sinai Hospital , New York , New York , United States )
  • Ma, Ning  ( Mount Sinai Hospital , New York , New York , United States )
  • Roy, Sion  ( UCLA Harbor , Santa Monica , California , United States )
  • Nasir, Khurram  ( Houston Methodist , Houston , Texas , United States )
  • Molloi, Sabee  ( University of California, Irvine , Irvine , California , United States )
  • Fayad, Zahi  ( MOUNT SINAI MEDICAL CENTER , New York , New York , United States )
  • Mcconnell, Michael  ( Stanford University School of Medicine , Stanford , California , United States )
  • Kakadiaris, Ioannis  ( University of Houston , Houston , Texas , United States )
  • Zulueta, Javier  ( Mount Sinai Hospital , New York , New York , United States )
  • Maron, David  ( Stanford University School of Medicine , Stanford , California , United States )
  • Shah, Prediman  ( Cedars-Sinai Medical Center , Los Angeles , California , United States )
  • Williams, Kim  ( University of Louisville Medicine , Louisville , Kentucky , United States )
  • Abela, George  ( Michigan State University , East Lansing , Michigan , United States )
  • Levy, Daniel  ( National Heart, Lung, and Blood Institute , Bethesda , Maryland , United States )
  • Wong, Nathan  ( University of California Irvine , Irvine , California , United States )
    • Author Disclosures:
    Morteza Naghavi: DO have relevant financial relationships ; Ownership Interest:HeartLung.AI:Active (exists now) | Ruilin Yu: DO NOT have relevant financial relationships | Andrea Branch: DO NOT have relevant financial relationships | Ning Ma: No Answer | Sion Roy: DO NOT have relevant financial relationships | Khurram Nasir: No Answer | Sabee Molloi: DO NOT have relevant financial relationships | Zahi Fayad: No Answer | Michael McConnell: DO have relevant financial relationships ; Employee:Toku Inc.:Active (exists now) ; Advisor:Porter Health:Active (exists now) ; Employee:Identifeye Health:Past (completed) | Ioannis Kakadiaris: No Answer | Javier Zulueta: DO have relevant financial relationships ; Advisor:Heart Lung Technologies:Active (exists now) ; Advisor:Disit Biotech:Active (exists now) ; Advisor:OncoSwab:Active (exists now) ; Advisor:Median Technologies:Active (exists now) | Anthony Reeves: No Answer | David Maron: No Answer | Prediman Shah: No Answer | Kim Williams: DO NOT have relevant financial relationships | george Abela: No Answer | Daniel Levy: No Answer | Nathan Wong: No Answer | Kyle Atlas: DO have relevant financial relationships ; Independent Contractor:HeartLung.AI:Active (exists now) | Chenyu Zhang: DO have relevant financial relationships ; Employee:HeartLung Corporation:Active (exists now) ; Individual Stocks/Stock Options:HeartLung Corporation:Active (exists now) | Thomas Atlas: DO NOT have relevant financial relationships | Claudia Henschke: No Answer | David Yankelevitz: DO have relevant financial relationships ; Individual Stocks/Stock Options:HeartLung:Active (exists now) ; Advisor:Lunglife AI:Active (exists now) ; Advisor:Carestream:Active (exists now) ; Advisor:Median Technology:Active (exists now) ; Advisor:HeartLung:Active (exists now) ; Individual Stocks/Stock Options:Accumetra:Active (exists now) ; Royalties/Patent Beneficiary:General Electric:Active (exists now) | Matthew Budoff: DO have relevant financial relationships ; Researcher:General Electric:Active (exists now) | WENJUN FAN: DO NOT have relevant financial relationships
Meeting Info:

Scientific Sessions 2024

2024

Chicago, Illinois

Session Info:

AI at Heart: Revolutionizing Cardiovascular Imaging

Sunday, 11/17/2024 , 11:30AM - 12:30PM

Abstract Poster Session

More abstracts on this topic:
A Contactless and Automated Approach to the Acute Stroke Assessment

Saadat Moh, Titus Ryan, Verkuilen Haley, Fleming Phil, Sur Sanjib, Sen Souvik

A distinct clot transcriptomic signature is associated with atrial fibrillation-derived ischemic stroke in the INSIGHT Registry

Seah Carina, Rivet Dennis, Fraser Justin, Kellner Christopher, Devarajan Alex, Vicari James, Dabney Alan, Baltan Selva, Sohrabji Farida, Pennypacker Keith, Nanda Ashish, Woodward Britton

More abstracts from these authors:
AI-enabled Cardiac Chambers Volumetry in Coronary Artery Calcium Scans (AI-CAC) vs. ASCVD Pooled Cohorts Equation and PREVENT Risk Scores: The Multi-Ethnic Study of Atherosclerosis

Naghavi Morteza, Yu Ruilin, Branch Andrea, Ma Ning, Roy Sion, Nasir Khurram, Molloi Sabee, Fayad Zahi, Mcconnell Michael, Kakadiaris Ioannis, Zulueta Javier, Reeves Anthony, Maron David, Narula Jagat, Shah Prediman, Williams Kim, Abela George, Levy Daniel, Wong Nathan, Atlas Kyle, Zhang Chenyu, Atlas Thomas, Henschke Claudia, Yankelevitz David, Budoff Matthew, Fan Wenjun

AI-CVD: Artificial Intelligence-Enabled Opportunistic Screening of Coronary Artery Calcium Computed Tomography Scans for Predicting CVD Events and All-Cause Mortality: The Multi-Ethnic Study of Atherosclerosis (MESA)

Naghavi Morteza, Yu Ruilin, Branch Andrea, Ma Ning, Roy Sion, Nasir Khurram, Molloi Sabee, Fayad Zahi, Mcconnell Michael, Kakadiaris Ioannis, Zulueta Javier, Reeves Anthony, Maron David, Shah Prediman, Williams Kim, Abela George, Levy Daniel, Wong Nathan, Atlas Kyle, Zhang Chenyu, Atlas Thomas, Henschke Claudia, Yankelevitz David, Budoff Matthew, Fan Wenjun

4144108_File000000.jpg
4144108_File000000.jpg
4144108_File000001.jpg
4144108_File000001.jpg
You have to be authorized to contact abstract author. Please, Login
Not Available