Key result
An automated artificial intelligence pipeline using electrocardiograms and echocardiograms accurately detected cardiac amyloidosis, achieving C-statistics of 0.85-0.92 for the ECG model and 0.91-1.00 for the echocardiography model.
Why the study?
Cardiac amyloidosis is often mistaken for common forms of heart failure and diagnosed late, limiting the use of emerging therapies, while AI detection models must address low disease prevalence.
Does an artificial intelligence-enabled automated pipeline using ECG and echocardiograms accurately detect cardiac amyloidosis?
Observational
Yes
Does an artificial intelligence-enabled automated pipeline using ECG and echocardiograms accurately detect cardiac amyloidosis?
An automated multi-modality AI pipeline using ECG and echocardiography can accurately detect cardiac amyloidosis, outperforming expert interpretation and offering a scalable strategy for screening rare cardiac diseases.
Answers are grounded in this paper and cite their sources.
May aid scalable cardiac amyloidosis screening; hypothesis-generating and requires prospective validation before practice change.
Although individually uncommon, rare diseases collectively affect over 350 million patients worldwide and are increasingly the target of therapeutic development efforts 1 . Unfortunately, the pursuit and use of such therapies have been hindered by a common challenge: patients with specific rare diseases are difficult to identify, especially if the conditions resemble more prevalent disorders. Cardiac amyloidosis is one such rare disease, which is characterized by deposition of misfolded proteins within the heart muscle resulting in heart failure and death 2–4 . In recent years, specific therapies have emerged for cardiac amyloidosis 5,6 and several more are under investigation 7–9 , but because cardiac amyloidosis is mistaken for common forms of heart failure, it is typically diagnosed late in its course. As a possible solution, artificial intelligence methods could enable automated detection of rare diseases, but model performance must address low disease prevalence. Here we present an automated multi-modality pipeline for cardiac amyloidosis detection using two neural-network models; one using electrocardiograms (ECG) and the second using echocardiographic videos as input. These models were trained and validated on 3 and 5 academic medical centers (AMC), respectively, in the United States and Japan. Both models had excellent accuracy for detecting cardiac amyloidosis with C-statistics of 0.85-0.92 and 0.91-1.00 for the ECG and echocardiography models, respectively, with the latter outperforming expert diagnosis. Simulating deployment on 13,906 and 7,775 patients with ECG-echocardiography paired data for AMC2 and AMC3 indicated a positive predictive value (PPV) for the ECG model of 4% and 3% at 61% and 54% recall, respectively. Pre-screening with ECG enhanced the echocardiography model performance from PPV 23% and 20% to PPV 58% and 53% at 64% recall, respectively for AMC2 and AMC3. In conclusion, we have developed a robust pipeline to augment detection of cardiac amyloidosis, which should serve as a generalizable strategy for other rare and intermediate frequency cardiac diseases with established or emerging therapies.
No takes yet. Share an insight, caveat, or question.
Goto et al. (2020) conducted an observational in Cardiac amyloidosis. Artificial intelligence-enabled automated detection models (ECG and echocardiography) vs. Expert cardiologist interpretation and gold standard clinical diagnosis was evaluated on Predictive accuracy of the echocardiography model for detecting cardiac amyloidosis on the BWH test dataset (ROC-AUC 0.97, 95% CI 0.96-0.98). An automated artificial intelligence pipeline using electrocardiograms and echocardiograms accurately detected cardiac amyloidosis, achieving C-statistics of 0.85-0.92 for the ECG model and 0.91-1.00 for the echocardiography model.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: