Incremental prognostic value of downstream positron emission tomography perfusion imaging after coronary computed tomography angiography: a study using machine learning
Authors' conclusion
PET MPI variables improve the prediction of adverse events beyond CCTA imaging alone for the first 4 years of follow-up.
Study context
- Population
- Patients with clinically suspected coronary artery disease (CAD) undergoing coronary computed tomography angiography (CCTA), 891 referred to downstream positron emission tomography (PET) myocardial perfusion imaging (MPI)2,284 analysed
- Participants
- 2,411 patients
- Comparison
- Machine learning (ML) model with clinical, CCTA and PET MPI variables vs ML model with clinical and CCTA variables only
- Outcome
- Adverse events (MI, unstable angina pectoris, death); incremental prognostic value assessed by AUC
- Follow-up
- 8-year follow-up
Methodological detailsmachine learning (XGBoost)
- Machine learning (XGBoost)
Performance
As reported in the abstract
Incremental prognostic value of PET MPI over CCTA (AUC, adverse events)
Highest AUC at observation time of Year 1
0.82, 95% CI 0.804-0.827
Original publication
Incremental prognostic value of downstream positron emission tomography perfusion imaging after coronary computed tomography angiography: a study using machine learning. Eur Heart J Cardiovasc Imaging. Published 29 September 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →