A clinical deep learning framework for continually learning from cardiac signals across diseases, time, modalities, and institutions

Dani Kiyasseh (), Tingting Zhu and David Clifton
Additional contact information
Dani Kiyasseh: University of Oxford
Tingting Zhu: University of Oxford
David Clifton: University of Oxford

Nature Communications, 2021, vol. 12, issue 1, 1-11

Abstract: Abstract 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 settings where data are streamed temporally from different clinical sites and from a multitude of physiological sensors. To mitigate this interference, we propose a continual learning strategy, entitled CLOPS, that employs a replay buffer. To guide the storage of instances into the buffer, we propose end-to-end trainable parameters, termed task-instance parameters, that quantify the difficulty with which data points are classified by a deep-learning system. We validate the interpretation of these parameters via clinical domain knowledge. To replay instances from the buffer, we exploit uncertainty-based acquisition functions. In three of the four continual learning scenarios, reflecting transitions across diseases, time, data modalities, and healthcare institutions, we show that CLOPS outperforms the state-of-the-art methods, GEM1 and MIR2. We also conduct extensive ablation studies to demonstrate the necessity of the various components of our proposed strategy. Our framework has the potential to pave the way for diagnostic systems that remain robust over time.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-021-24483-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-24483-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-24483-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().