An artificial intelligence (AI)-augmented clinical programme may significantly improve the detection of transthyretin amyloid cardiomyopathy (ATTR-CM), a condition that is frequently underdiagnosed, according to the results of a new nonrandomized clinical trial.¹ The study evaluated an AI model, ATTRACTnet, in a real-world setting to identify patients missed by usual care.

The ATTRACTnet model was developed using electrocardiogram (ECG) waveforms, echocardiographic measurements, demographics, and diagnosis codes for orthopedic manifestations of amyloidosis. The model was then evaluated prospectively in the single-arm, open-label Cardiac Amyloidosis Discovery Trial (NCT06469372).

The trial included patients aged 50 years or older with a left ventricular (LV) wall thickness of 12 mm or more and an ATTRACTnet score of 0.5 or higher. Patients with prior ATTR-CM testing or a diagnosis of hypertrophic cardiomyopathy were excluded. Eligible patients, upon agreement from their treating physician, were offered nuclear scintigraphy and monoclonal protein testing. The primary outcome was a diagnosis of ATTR-CM based on consensus criteria.

During the study period, the AI model identified 1471 patients with a positive score, of whom 256 were eligible for the trial. Following physician and patient approval, 50 patients underwent diagnostic testing.

Of the 50 patients tested, 24 (48%) were diagnosed with ATTR-CM. This positivity rate was more than 2.8 times higher than that of historical controls (15.3%; 95% CI, 13.1%–17.9%; p<0.001) and contemporary controls (17.0%; 95% CI, 14.6%–19.6%; p<0.001). The algorithm could have identified these patients a median of 345 days earlier than their study enrolment. Following diagnosis, 21 of the 24 patients (88%) initiated treatment for ATTR-CM within three months.

The study authors concluded that “AI-augmented screening may improve ATTR-CM detection and identify patients who are missed by usual care.”¹ The findings suggest that integrating such AI tools into clinical workflows could help to close diagnostic gaps and reduce delays in initiating treatment for ATTR-CM.

The authors noted that prospective randomized trials are needed to determine if this AI-augmented screening approach improves patient outcomes.

This study was funded by Pfizer and Eidos/BridgeBio.

References

1. Jain SS, Sun T, Pierson E, et al. Detecting Transthyretin Cardiac Amyloidosis With Artificial Intelligence: A Nonrandomized Clinical Trial. JAMA Cardiol. Published online November 10, 2025. https://doi.org/10.1001/jamacardio.2025.4591

Disclaimer: The information presented in this article is for educational purposes only. Any quotes included reflect the opinions of the individual quoted, and do not necessarily reflect the views of the publisher. The publisher does not guarantee the accuracy or completeness of the content and accepts no responsibility for any errors, or any consequences arising from its use.