Large Language Model Agentic Workflows for Automated Opportunistic Screening of Incidental Coronary Artery Calcium on Chest CT Reports
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
One study estimated a cost of US$0.006 per screened patient using automated notification workflows (≈US$6485 per million patients).
“one estimating a cost of US$0.006 per screened patient using automated notification workflows (≈US$6485 per million patients)40”
From Prognostication and clinical opportunities with AI for coronary artery calcium: a scoping review (2026) · cites this paper as [40]
Agentic workflows can be used at the panel-management level to identify patients in the electronic health record with elevated CAC without statin prescription.
“Agentic workflows can be used at the panel-management level to identify patients in the electronic health record with elevated CAC without statin prescription.”
From Prognostication and clinical opportunities with AI for coronary artery calcium: a scoping review (2026) · cites this paper as [40]
Notification of patients and clinicians based on AI-CAC results increases cardiovascular preventive discussions, statin prescription rates and statin persistence.
“Notification of patients and clinicians based on these results has been shown to increase cardiovascular preventive discussions, statin prescription rates and statin persistence.40–43”
From Prognostication and clinical opportunities with AI for coronary artery calcium: a scoping review (2026) · cites this paper as [40]
Large language models accurately identified patients for preventive interventions from review of patient charts and CT reports (F1 0.99, positive predictive value 98%-100%).
“In real-world applications, large language models accurately identified patients for preventive interventions from review of patient charts and CT reports (F1 0.99, positive predictive value 98%–100%).40”
From Prognostication and clinical opportunities with AI for coronary artery calcium: a scoping review (2026) · cites this paper as [40]
Cites
Pearson, G. J., Thanassoulis, G., Anderson, T. J., Barry, A. R., Couture, P., Dayan, N., Francis, G. A., Genest, J. J., Grégoire, J. C., Grover, S. A., et al. (2021) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2021.03.016 · Cited by 870 · see citing works
Sandhu, A. T., Rodriguez, F., Ngo, S., Patel, B. N., Mastrodicasa, D., Eng, D., Khandwala, N., Balla, S., Sousa, D., & Maron, D. J. (2023) · Circulation · doi:10.1161/circulationaha.122.062746 · Cited by 174 · see citing works
Fresno, C. M. U., Tijmes, F. S., Thavendiranathan, P., Akhtari, S., Karur, G. R., Torres, F. S., Halankar, J., Nguyen, E. T., & Hanneman, K. A. (2022) · American Journal of Roentgenology · doi:10.2214/ajr.22.27664 · Cited by 37 · see citing works
Self-citationUse of GPT-4 With Single-Shot Learning to Identify Incidental Findings in Radiology Reports
Bhayana, R., Elias, G. J. B., Datta, D., Bhambra, N., Deng, Y., & Krishna, S. (2024) · American Journal of Roentgenology · doi:10.2214/ajr.23.30651 · Cited by 22 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Canadian radiology: 2026 update
Kamran, R., Buckley, B., Costa, A. F., Forster, B. B., Mafeld, S. C., Shankar, J., Sheikh, A., Souza, C., & Patlas, M. N. (2026) · Diagnostic and Interventional Imaging · doi:10.1016/j.diii.2026.05.001 · Cited by 3 · see citing works
Prognostication and clinical opportunities with AI for coronary artery calcium: a scoping review
McDonald, V. J. F., Parsa, S., Mastrodicasa, D., Rodriguez, F., Langlotz, C., Maron, D. J., Sandhu, A. T., Dudum, R., & Jain, S. S. (2026) · BMJ Digital Health & AI · doi:10.1136/bmjdh-2026-000053
- Authors
- Ladak, A. M., Halankar, J., Nguyen, E. T., Hanneman, K., Deng, Y., Krishna, S., & Bhayana, R.
- Affiliations
- University of Toronto (CA)
- University Health Network (CA)
- Corresponding author
- Bhayana, Rajesh
- ORCID
- Venue
- Canadian Association of Radiologists Journal
- Publisher
- SAGE Publications
- Published
- 2025-08-02
- Volume
- 77
- Issue
- 1
- Pages
- 246-249
- ISSN
- 0846-5371 (ISSN-L)
- 1488-2361
- OpenAlex
- W4412853731
- Cited by
- 2
- References
- 4
- Citations by year
- 2026: 2
- FWCI
- 0.49
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Canadian Association of Radiologists Journal (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Cardiac Imaging and Diagnostics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- large language models, LLM agents, coronary artery calcium, incidental finding, automated screening, radiology report analysis, opportunistic screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
