Artificial intelligence in coronary artery calcification scoring: Current progress and future directions

Abstract

Objective: The primary purpose of this paper is to evaluate the role of artificial intelligence (AI) in enhancing coronary artery calcification (CAC) scoring for improved cardiovascular risk assessment.

Methods: A narrative review was performed using data from PubMed, Scopus, and Semantic Scholar, focusing on publications from 2020 to 2025. The study includes research utilizing AI methodologies, including deep learning and machine learning, in CAC scoring. Key measurements included CAC scores from computed tomography (CT) images, inter-observer variability, and patient outcomes. Data analysis involved qualitative synthesis of findings and examination of performance metrics.

Results: AI algorithms significantly improved CAC score accuracy, with sensitivity and specificity rates of 90%. The use of AI reduced inter-observer variability by up to 30%, enabling more consistent risk assessments. Additionally, AI-enhanced CAC scoring effectively identified high- risk patients, leading to better-targeted preventive strategies compared to traditional methods.

Conclusion: The incorporation of AI into CAC scoring holds promise for transforming cardiovascular risk assessment by enhancing accuracy and reliability. Future research should focus on validating AI tools across diverse populations, developing user-friendly clinical applications, and exploring AI's role in longitudinal cardiovascular health studies. Addressing these challenges will enhance the utility of CAC scoring and ultimately improve patient outcomes.