Deep neural networks reveal novel sex-specific electrocardiographic features relevant for mortality risk.
Klaske R SiegersmaRutger R van de LeurN Charlotte Onland-MoretDavid A LeonErnest Diez BenaventeLiesbeth RozendaalMichiel L BotsRuben CoronelYolande AppelmanLeonard HofstraPim van der HarstPieter A M DoevendansRutger J HassinkHester M den RuijterRené van EsPublished in: European heart journal. Digital health (2022)
Deep neural networks accurately classify sex based on ECGs. While the proportion of ECG-based sex misclassifications is low, it is an interesting biomarker. Investigation of the causal pathway between misclassification and mortality uncovered new ECG features that might be associated with mortality. Increased emphasis on sex as a biological variable in artificial intelligence is warranted.