Key result
Interpretable deep neural network diagnoses 12-lead ECG abnormalities with ~0.998 AUC and lead-specific interpretations.
Why the study?
Despite the potential of artificial intelligence in healthcare, little work focuses on extracting clinical information or knowledge discovery from clinical measurements such as electrocardiograms.
Does an interpretable deep learning model accurately diagnose cardiac abnormalities, identify gender, and screen for hypertension using 12-lead ECGs in primary care patients?
Observational (n=1,558,772)
Yes
Does an interpretable deep learning model accurately diagnose cardiac abnormalities, identify gender, and screen for hypertension using 12-lead ECGs in primary care patients?
Answers are grounded in this paper and cite their sources.
A novel interpretable deep learning model applied to 12-lead ECGs demonstrated high accuracy for cardiac abnormality diagnosis, gender identification, and hypertension screening.
Despite the potentials of artificial intelligence (AI) in healthcare, very little work focuses on the extraction of clinical information or knowledge discovery from clinical measurements. Here we propose a novel deep learning model to extract characteristics in electrocardiogram (ECG) and explore its usage in knowledge discovery. Utilising a 12-lead ECG dataset ( n ECGs = 2,322,513) collected from unique subjects ( n Subjects = 1,558,772) in primary care, we performed three independent medical tasks with the proposed model: ( i ) cardiac abnormality diagnosis, ( ii ) gender identification, and ( iii ) hypertension screening. We achieved an area under the curve (AUC) score of 0.998 (95% confidence interval (CI), 0.995-0.999), 0.964 (95% CI, 0.963-0.965), and 0.839 (95% CI, 0.837-0.841) for each task, respectively; We provide interpretation of salient morphologies and further identified key ECG leads that achieve similar performance for the three tasks: ( i ) AVR and V1 leads (AUC=0.990 (95% CI, 0.982-0.995); ( ii ) V5 lead (AUC=0.900 (95% CI, 0.899-0.902)); and ( iii ) V1 lead (AUC=0.816 (95% CI, 0.814-0.818)). Using ECGs, our model not only has demonstrated cardiologist-level accuracy in heart diagnosis with interpretability, but also shows its potentials in facilitating clinical knowledge discovery for gender and hypertension detection which are not readily available.
No takes yet. Share an insight, caveat, or question.
Lü et al. (2022) conducted an observational in Cardiac abnormalities, gender identification, and hypertension (n=1,558,772). Interpretable deep neural network (CResNet) vs. Cardiology professionals and benchmark DNN models was evaluated on Cardiac abnormality diagnosis (AUC) (AUC 0.998, 95% CI 0.995-0.999). An interpretable deep neural network achieved an AUC of 0.998 for diagnosing cardiac abnormalities from 12-lead ECGs, while providing lead-specific interpretation of salient morphologies.
Synapse has enriched 10 related papers. Consider them for comparative context: