TY - GEN
T1 - Prediction of major adverse cardiovascular events (MACE) in Agatston low-risk patients using comprehensive AI analysis of low-cost screening CT calcium score exams
AU - Hu, Tao
AU - Hoori, Ammar
AU - Freeze, Joshua
AU - Singh, Prerna
AU - Wu, Hao
AU - Song, Yingnan
AU - Al-Kindi, Sadeer
AU - Rajagopalan, Sanjay
AU - Wilson, David L.
N1 - Publisher Copyright:
© 2025 SPIE.
PY - 2025
Y1 - 2025
N2 - Coronary artery calcification Agatston score, calculated from CT calcium score exam, is widely used in cardiovascular risk prediction, particularly for determining the necessity of statin therapies in patients with Agatston score >100, as recommended by the American Heart Association (AHA). However, as high Agatston score is indicative of MACE, patients with low or zero Agatston are more likely not been detected. There is growing recognition that CT-based assessments of epicardial adipose tissue (EAT) are associated with cardiovascular events. This study aimed to enhance cardiovascular disease prediction using pathophysiologically-driven EAT assessments obtained from CTCS images in individuals with Agatston scores below 100. We analyzed a cohort of 16,042 patients (1.7% MACE) with low Agatston score (Ag<100) from the HU-CLARIFY registry (NCT04075162). EAT was segmented using our DeepFat segmentation model from non-contrast CTCS exams, generating 216 EAT hand-crafted features (fat-omics) based on morphology, intensity, and spatial location. The cohort was divided into training/testing sets (80%/20%). We employed Cox proportional hazards regression model with elastic net regularization, incorporating EAT, Agatston score and/or clinical features to predict MACE. EAT fat-omics (c-index of train/test = 0.68/0.63) outperformed Agatston score (0.61/0.55). Our proposed model include adding Agatston score and clinical features which improve results significantly (c-index=0.77/0.74). In conclusion, advanced, pathophysiological EAT features may address a valuable risk assessment tool (that Agatston missed) for patients with low Agatston scores, enhancing early detection and management strategies.
AB - Coronary artery calcification Agatston score, calculated from CT calcium score exam, is widely used in cardiovascular risk prediction, particularly for determining the necessity of statin therapies in patients with Agatston score >100, as recommended by the American Heart Association (AHA). However, as high Agatston score is indicative of MACE, patients with low or zero Agatston are more likely not been detected. There is growing recognition that CT-based assessments of epicardial adipose tissue (EAT) are associated with cardiovascular events. This study aimed to enhance cardiovascular disease prediction using pathophysiologically-driven EAT assessments obtained from CTCS images in individuals with Agatston scores below 100. We analyzed a cohort of 16,042 patients (1.7% MACE) with low Agatston score (Ag<100) from the HU-CLARIFY registry (NCT04075162). EAT was segmented using our DeepFat segmentation model from non-contrast CTCS exams, generating 216 EAT hand-crafted features (fat-omics) based on morphology, intensity, and spatial location. The cohort was divided into training/testing sets (80%/20%). We employed Cox proportional hazards regression model with elastic net regularization, incorporating EAT, Agatston score and/or clinical features to predict MACE. EAT fat-omics (c-index of train/test = 0.68/0.63) outperformed Agatston score (0.61/0.55). Our proposed model include adding Agatston score and clinical features which improve results significantly (c-index=0.77/0.74). In conclusion, advanced, pathophysiological EAT features may address a valuable risk assessment tool (that Agatston missed) for patients with low Agatston scores, enhancing early detection and management strategies.
KW - Agatston score
KW - Artificial Intelligence
KW - Computed tomography calcium score images
KW - Epicardial adipose tissue
KW - Hand-crafted feature engineering
KW - Major adverse cardiovascular events
KW - Survival analysis
UR - http://www.scopus.com/inward/record.url?scp=105004406503&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=105004406503&partnerID=8YFLogxK
U2 - 10.1117/12.3046372
DO - 10.1117/12.3046372
M3 - Conference contribution
AN - SCOPUS:105004406503
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2025
A2 - Astley, Susan M.
A2 - Wismuller, Axel
PB - SPIE
T2 - Medical Imaging 2025: Computer-Aided Diagnosis
Y2 - 17 February 2025 through 20 February 2025
ER -