A clinical deep learning framework for continually learning from cardiac signals across diseases, time, modalities, and institutions.
Deep learning algorithms trained on instances that violate the assumption of being independent and identically distributed (i.i.d.) are known to experience destructive interference, a phenomenon characterized by a degradation in performance. Such a violation, however, is ubiquitous in clinical setti...
Main Authors: | Kiyasseh, D, Zhu, T, Clifton, D |
---|---|
Format: | Journal article |
Language: | English |
Published: |
Springer Nature
2021
|
Similar Items
-
CLOCS: contrastive learning of cardiac signals across space, time, and patients
by: Kiyasseh, D, et al.
Published: (2021) -
Deep learning with limited labelled cardiac data
by: Kiyasseh, D
Published: (2021) -
CROCS: Clustering and revival of cardiac signals based on patient disease class, sex, and age
by: Kiyasseh, D, et al.
Published: (2021) -
Combining multi-modal statistics for welfare prediction using deep learning
by: Sharma, P, et al.
Published: (2019) -
The promise of clinical decision support systems targetting low-resource settings
by: Kiyasseh, D, et al.
Published: (2020)