Factors affecting the performance of a novel artificial intelligence-based coronary computed tomography-derived ischaemia algorithm
For abnormal AI-QCT<sub>ischaemia</sub>, younger age, typical angina, more severe stenosis, and more extensive atherosclerosis predicted abnormal PET perfusion. With false negative AI-QCT<sub>ischaemia</sub>, perfusion abnormalities were partly explained by microvascular disease.
Authors
- Teemu Maaniitty (ORCID: https://orcid.org/0000-0001-5819-4635)
- Antti Saraste (ORCID: https://orcid.org/0000-0003-2488-0893)
- Jeroen Joost Bax (ORCID: https://orcid.org/0000-0001-7368-0500)
- Peerapon Kiatkittikul (ORCID: https://orcid.org/0000-0001-7076-3829)
- Takeru Nabeta (ORCID: https://orcid.org/0000-0003-4671-7667)
- Juhani Knuuti (ORCID: https://orcid.org/0000-0003-3156-9593)
- Sarah Bär (ORCID: https://orcid.org/0000-0003-0045-6596)
Institutions
- University of Turku (FI)
- Leiden University Medical Center (NL)
- University Hospital of Bern (CH)
- Turku University Hospital (FI)
- Turku PET Centre (FI)
- Chulabhorn Hospital (TH)
- Cyclotron (Netherlands) (NL)
Publication Details
- Journal
- European Heart Journal - Imaging Methods and Practice
- Published
- 2024-10-01
- DOI
- https://doi.org/10.1093/ehjimp/qyaf033
- Citations
- 1
- Primary Topic
- Cardiac Imaging and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 0.40
Funders
- Foundation for Cardiovascular Research
- Chulabhorn Royal Academy
- Academy of Finland
- Sydäntutkimussäätiö