Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging
Authors' conclusion
The screening and diagnostic models achieved high performance (area under the curve of 0.988 ± 0.3% and 0.991 ± 0.0%, respectively) in both internal and external datasets.
Study context
- Population
- Patients undergoing CMR, 11 types of cardiovascular disease (CVD)
- Participants
- 9,719 patients
- Comparison
- AI-enabled CMR interpretation for screening and diagnosis of CVD
- Outcome
- Screening and diagnosis of CVD (internal and external datasets)
Methodological detailsinternal and external validation, proof-of-concept
- Internal and external validation
- Proof-of-concept
Performance
As reported in the abstract
| Test or model | AUC |
|---|---|
| Screening model | 0.988 ± 0.3% |
| Diagnostic model | 0.991 ± 0.0% |
AUC
Screening model0.988 ± 0.3%
Diagnostic model0.991 ± 0.0%
Further findings
Diagnosis of pulmonary arterial hypertension
- Diagnostic model outperformed cardiologists
Original publication
Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging. Nat Med. Published 13 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →