Simple models vs. deep learning in detecting low ejection fraction from the electrocardiogram.
John Weston HughesSulaiman SomaniPierre A EliasJames TooleyAlbert J RogersTimothy PoteruchaChristopher M HaggertyMichael SalernoDavid OuyangEuan AshleyJames Y ZouMarco V PerezPublished in: European heart journal. Digital health (2024)
Our study demonstrates the value of simple electrocardiographic models that perform nearly as well as deep learning models, while being much easier to implement and interpret.