Heart failure & cardiomyopathies
Detecting Transthyretin Cardiac Amyloidosis With Artificial Intelligence: A Nonrandomized Clinical Trial
Main finding · ATTR-CM diagnosis among tested patientsResult — go to the resultPositivity rate more than 2.8 times higher 95% CI 13.1%–17.9%Authors' conclusion
AI-augmented screening may improve ATTR-CM detection and identify patients who are missed by usual care.
Study context
- Population
- Patients with left ventricular (LV) wall thickness ≥12 mm and ATTRACTnet score ≥0.550 underwent testing
- Participants
- 256 patients
- Comparison
- Artificial intelligence (AI)-augmented ATTR-CM screening vs historical controls
- ATTRACTnetn = 50
- Outcome
- Diagnosis of ATTR-CM by consensus criteria
Methodological detailssingle-arm, open-label, single-system, multisite, 1471 patients had AI score ≥0.5 during study period
- Single-arm
- Open-label
- Single-system
- Multisite
- 1471 patients had AI score ≥0.5 during study period
Main finding
ATTR-CM diagnosis among tested patients
Positivity rate
more than 2.8 times higher
95% CI 13.1%–17.9%
P < 0.001
As reported in the abstract
- Diagnosed with ATTR-CM, of 50 tested
- 24 (48%)
- Relative increase in new diagnoses vs the prior year
- 18%
Further findings
ATTRACTnet discrimination for ATTR-CM (AUC)
- AUC, internal test set (n = 799; 5-fold cross-validation, 0.77-0.85)
- 0.85
- AUC, external test set
- 0.82 (n = 422; 95% CI, .81-0.83)
- Similar performance in Hispanic, non-Hispanic Black, and non-Hispanic White patients
Treatment initiation among diagnosed · within 3 months
- Initiated treatment
- 21 (88%)
Original publication
Detecting Transthyretin Cardiac Amyloidosis With Artificial Intelligence: A Nonrandomized Clinical Trial. JAMA Cardiol. Published 1 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →