Key result
Deep learning echocardiography models, including EchoGo Amyloidosis, outperformed the Mayo ATTR-CM Score for detecting transthyretin cardiac amyloidosis.
Why the study?
Delays in ATTR-CM diagnosis contribute to significant morbidity, but AI and other screening algorithms for detection had not been directly compared.
Do deep learning echocardiography models improve the detection of ATTR-CM compared to clinical and claims-based scores in patients with heart failure?
Case-Control (n=3,368)
Yes
Do deep learning echocardiography models improve the detection of ATTR-CM compared to clinical and claims-based scores in patients with heart failure?
Answers are grounded in this paper and cite their sources.
Deep learning echocardiography models demonstrate superior discrimination for detecting ATTR-CM in heart failure patients compared to traditional clinical and claims-based scores, with low risk of racial bias.
Background Delays in the diagnosis of transthyretin amyloid cardiomyopathy (ATTR-CM) contribute to the significant morbidity of the condition, especially in the era of disease-modifying therapies. Screening for ATTR-CM with AI and other algorithms may improve timely diagnosis, but these algorithms have not been directly compared. Objectives The aim of this study was to compare the performance of four algorithms for ATTR-CM detection in a heart failure population and assess the risk for harms due to model bias. Methods We identified patients in an integrated health system from 2010-2022 with ATTR-CM and age- and sex-matched them to controls with heart failure to target 5% prevalence. We compared the performance of a claims-based random forest model (Huda et al. model), a regression-based score (Mayo ATTR-CM), and two deep learning echo models (EchoNet-LVH and EchoGo ® Amyloidosis). We evaluated for bias using standard fairness metrics. Results The analytical cohort included 176 confirmed cases of ATTR-CM and 3192 control patients with 79.2% self-identified as White and 9.0% as Black. The Huda et al. model performed poorly (AUC 0.49). Both deep learning echo models had a higher AUC when compared to the Mayo ATTR-CM Score (EchoNet-LVH 0.88; EchoGo Amyloidosis 0.92; Mayo ATTR-CM Score 0.79; DeLong P<0.001 for both). Bias auditing met fairness criteria for equal opportunity among patients who identified as Black. Conclusions Deep learning, echo-based models to detect ATTR-CM demonstrated best overall discrimination when compared to two other models in external validation with low risk of harms due to racial bias.
No takes yet. Share an insight, caveat, or question.
Hourmozdi et al. (2024) conducted a case-control in Transthyretin amyloid cardiomyopathy (ATTR-CM) (n=3,368). Deep learning echocardiography models (EchoGo Amyloidosis and EchoNet-LVH) vs. Mayo ATTR-CM Score and Huda et al. model was evaluated on Area under the curve (AUC) for detection of ATTR-CM (95% CI 0.89-0.95, p=<0.001). Deep learning echocardiography models, including EchoGo Amyloidosis, outperformed the Mayo ATTR-CM Score for detecting transthyretin cardiac amyloidosis.
Synapse has enriched 10 related papers. Consider them for comparative context: