Multicenter evaluation of interpretable AI for coronary artery disease diagnosis from PET biomarkers - Summary - MDSpire

Multicenter evaluation of interpretable AI for coronary artery disease diagnosis from PET biomarkers

  • By

  • Wenhao Zhang

  • Jacek Kwiecinski

  • Aakash Shanbhag

  • Robert J. H. Miller

  • Shiva Mostafavi

  • Giselle Ramirez

  • Jirong Yi

  • Donghee Han

  • Damini Dey

  • Dominika Grodecka

  • Kajetan Grodecki

  • Mark Lemley

  • Paul Kavanagh

  • Joanna X. Liang

  • Jianhang Zhou

  • Valerie Builoff

  • Jon Hainer

  • Sylvain Carre

  • Leanne Barrett

  • Andrew J. Einstein

  • Stacey Knight

  • Steve Mason

  • Viet T. Le

  • Wanda Acampa

  • Samuel Wopperer

  • Panithaya Chareonthaitawee

  • Daniel S. Berman

  • Marcelo F. Di Carli

  • Piotr J. Slomka

  • January 14, 2026

  • 0 min

Share

Objective:

To develop and validate an AI model that integrates PET MPI parameters for improved diagnosis of coronary artery disease (CAD), enhancing clinical decision-making.

Key Findings:
  • The AI model achieved an AUC of 0.83, outperforming clinical scores and individual PET parameters, indicating its potential for clinical adoption.
  • Patients with CAD showed significantly higher ischemic TPD and lower stress MBF and MFR, highlighting the model's ability to detect critical differences.
  • The model identified more high-risk patients compared to traditional quantitative measurements, suggesting improved risk stratification.
Interpretation:

The AI model provides a more accurate and comprehensive assessment of CAD by integrating multiple PET imaging parameters, enhancing diagnostic capabilities and potentially improving patient outcomes.

Limitations:
  • The study may have selection bias due to the specific patient cohorts used, which could limit the applicability of the findings.
  • External validation was limited to three centers, which may affect generalizability to broader populations.
Conclusion:

The AI-driven approach represents a significant advancement in CAD diagnosis, leveraging multiple imaging biomarkers for improved risk stratification and paving the way for future research in AI applications in cardiology.

Original Source(s)

Multicenter evaluation of interpretable AI for coronary artery disease diagnosis from PET biomarkers

  • by Wenhao Zhang, Jacek Kwiecinski, Aakash Shanbhag, Robert J. H. Miller, Shiva Mostafavi, Giselle Ramirez, Jirong Yi, Donghee Han, Damini Dey, Dominika Grodecka, Kajetan Grodecki, Mark Lemley, Paul Kavanagh, Joanna X. Liang, Jianhang Zhou, Valerie Builoff, Jon Hainer, Sylvain Carre, Leanne Barrett, Andrew J. Einstein, Stacey Knight, Steve Mason, Viet T. Le, Wanda Acampa, Samuel Wopperer, Panithaya Chareonthaitawee, Daniel S. Berman, Marcelo F. Di Carli, Piotr J. Slomka

  • January 14, 2026

Related Content

Application and prospect of artificial intelligence in diagnostic imaging of prostate cancer

Quality of Life in Cardiac Arrest Recovery

Post–cardiac arrest care is increasingly structured around survivorship, with standardized patient-reported assessments supporting multidisciplinary follow-up.

AD Not Linked to Early CV Risk Markers

Repeated assessments from childhood to early adulthood did not identify consistent cardiometabolic risk patterns by disease activity or severity.