Uncertainty estimation for deep learning-based automated analysis of 12-lead electrocardiograms.
Jeroen F VrankenRutger R van de LeurDeepak K GuptaLuis E Juarez OrozcoRutger J HassinkPim van der HarstPieter A DoevendansSadaf GulshadRené van EsPublished in: European heart journal. Digital health (2021)
Uncertainty estimation is warranted in automated DNN-based ECG classification and its accurate estimation enables intermediate quality control in the clinical implementation of deep learning. This is an important step towards the clinical applicability of automated ECG diagnosis using DNNs.