Skip to main content
. Author manuscript; available in PMC: 2022 Jul 27.
Published in final edited form as: IEEE J Biomed Health Inform. 2021 Jul 27;25(7):2398–2408. doi: 10.1109/JBHI.2021.3060997

Fig. 3:

Fig. 3:

Explaining a prediction using LIME: (1) Original ECG signal (class label S). (2) Perturbed signals with a random subset of segments removed, along with corresponding probability scores for class S obtained through the deep network. (3) Interpretable regression model. (4) Quantitative explanations.