Evaluation of an artificial intelligence model for opportunistic Agatston scoring on non-gated chest computed tomography.
Authors
Affiliations (6)
Affiliations (6)
- Mass General Brigham AI, 399 Revolution Dr, Boston, MA, 02145, USA. [email protected].
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA. [email protected].
- Mass General Brigham AI, 399 Revolution Dr, Boston, MA, 02145, USA.
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
- Harvard Medical School, Boston, MA, USA.
- Department of Neurology, Massachusetts General Hospital, Boston, MA, USA.
Abstract
The Agatston score is a measure of cardiovascular disease traditionally calculated on cardiac gated computed tomography (CT) of the chest. Cardiac gated CT is resource-intensive, can be hard to access, and involves extra radiation exposure. Artificial intelligence (AI) can be used to opportunistically calculate Agatston scores on non-gated CTs performed for other indications. This retrospective standalone performance assessment compared the accuracy of an AI model (Riverain Technologies ClearRead CT CAC) at calculating Agatston scores on non-gated CTs to both consensus radiologist interpretations on the same CTs and Agatston scores from the original radiology reports of paired cardiac gated CTs. It involved 491 non-contrast CT chest cases acquired at five hospitals in the United States between January 2022 and December 2023; approximately two-thirds had a paired cardiac gated CT. It compared the agreement of Agatston categories (0, 1-99, 100-399 and ≥ 400) using the quadratic weighted Kappa coefficient and the correlation of Agatston scores using the Spearman coefficient. The agreement of Agatston categories between the AI model and ground truth radiologists was 0.959 (95% CI: 0.943 to 0.975); this result was broadly consistent across sex, age group, race, ethnicity and CT scanner manufacturer subgroups. The agreement between the AI model and paired cardiac gated CT was 0.906 (95% CI: 0.882 to 0.927). The correlations of Agatston scores for these two comparisons were 0.975 (95% CI: 0.962 to 0.987) and 0.942 (95% CI: 0.920 to 0.957) respectively. The assessed AI model accurately calculated Agatston scores on non-gated CTs and produced similar scores to paired cardiac gated CTs. Its use could broaden screening for atherosclerotic cardiovascular disease, enabling opportunistic screening on CTs captured for other indications.