Key result
An AI-ECG model identified transthyretin amyloid cardiomyopathy from routine ECG images with an AUROC of 0.84 (95% CI, 0.79-0.89) in internal validation.
Why the study?
ATTR-CM is a treatable cause of heart failure, but diagnosis is often delayed, creating a need for accessible tools to prioritize confirmatory evaluation when cardiac imaging is limited.
Does an AI-enabled ECG system accurately identify patients with transthyretin amyloid cardiomyopathy (ATTR-CM)?
Observational (n=44,123)
Yes
Does an AI-enabled ECG system accurately identify patients with transthyretin amyloid cardiomyopathy (ATTR-CM)?
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“In Transthyretin Cardiac Amyloidosis, risk prediction is shifting from static staging at diagnosis toward models that incorporate treatment status and better reflect prognosis in contemporary treated populations. This editorial indicates that machine learning-based prediction improved discrimination compared with National Amyloidosis Centre and Mayo staging systems and may support more granular baseline risk assessment.”
An AI-enabled ECG system demonstrated good discrimination for detecting transthyretin amyloid cardiomyopathy across multiple retrospective and screening cohorts, offering a potential accessible tool to prioritize patients for confirmatory imaging.
Importance: Transthyretin amyloid cardiomyopathy (ATTR-CM) is a treatable cause of heart failure, but diagnosis is often delayed. Accessible tools to prioritize confirmatory evaluation could reduce missed diagnoses when cardiac imaging is limited. Objective: To develop and validate a locally deployable artificial intelligence (AI)-enabled system that identifies patients for further ATTR-CM evaluation from routine electrocardiography (ECG) images. Design, Setting, and Participants: This diagnostic test study used an AI-ECG model developed within Yale New Haven Health (using ECGs from August 2015-June 2023) and temporally validated (July 2023-July 2025). External validation included 5 multinational cohorts and 3 screening cohorts (older Black and Hispanic adults with heart failure; adults with prior carpal tunnel surgery; 99-3902 individuals per cohort). Exposure: Use of AI-ECG for detecting ATTR-CM from routine ECG images or raw 12-lead signals. Main Outcomes and Measures: Area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and positive and negative predictive values for ATTR-CM confirmed by cardiac amyloid radionuclide imaging (CARI) or biopsy. An exploratory analysis evaluated sequential screening with AI-ECG followed by AI-enabled echocardiography. Results: Development used 28 174 ECGs from 11 291 patients (293 with ATTR-CM). In internal validation (44 123 patients; mean age, 68.5 years; 49.7% female), AUROC was 0.84 (95% CI, 0.79-0.89), with sensitivity of 0.72 and specificity of 0.86 at the prespecified threshold, and was maintained in a specificity stress test among patients with features that mimic ATTR-CM (left ventricular hypertrophy or severe aortic stenosis without amyloid; AUROC, 0.81 [95% CI, 0.75-0.86]) and those referred for CARI (AUROC, 0.78 [95% CI, 0.73-0.84]). Across 5 external cohorts, AUROCs ranged from 0.78 to 0.89. In 3 screening cohorts, AUROCs were 0.76 (95% CI, 0.68-0.83) in the SCAN-MP study (n = 645) and 0.79 (95% CI, 0.65-0.93) and 0.91 (95% CI, 0.82-0.97) in 2 CACTUS study cohorts (n = 251, n = 121). Sequential AI-ECG and AI-enabled echocardiography increased the positive predictive value from 0.24 to 0.66 and reduced sensitivity from 0.84 to 0.68. Conclusions and Relevance: Locally deployable AI applied to ECG images discriminated ATTR-CM across multinational retrospective and screening cohorts. This approach may provide an accessible first step to prioritize selected patients for echocardiography and confirmatory imaging, although intended use and calibration require prospective evaluation.
No takes yet. Share an insight, caveat, or question.
Croon et al. (2026) conducted an observational in Transthyretin amyloid cardiomyopathy (ATTR-CM) (n=44,123). AI-ECG vs. Cardiac amyloid radionuclide imaging (CARI) or biopsy was evaluated on Area under the receiver operating characteristic curve (AUROC) for ATTR-CM confirmed by CARI or biopsy (AUROC 0.84, 95% CI 0.79-0.89). An AI-ECG model identified transthyretin amyloid cardiomyopathy from routine ECG images with an AUROC of 0.84 (95% CI, 0.79-0.89) in internal validation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: