Affordable Access

deepdyve-link
Publisher Website

Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing.

Authors
  • Roy, Subhrajit1
  • Mincu, Diana1
  • Loreaux, Eric1
  • Mottram, Anne1
  • Protsyuk, Ivan1
  • Harris, Natalie1
  • Xue, Yuan2
  • Schrouff, Jessica1
  • Montgomery, Hugh3
  • Connell, Alistair1
  • Tomasev, Nenad4
  • Karthikesalingam, Alan1
  • Seneviratne, Martin1
  • 1 Google Health, London, United Kingdom. , (United Kingdom)
  • 2 Google Health, Mountain View, California, USA.
  • 3 Centre for Human Health and Performance, University College London, London, United Kingdom. , (United Kingdom)
  • 4 DeepMind, London, United Kingdom. , (United Kingdom)
Type
Published Article
Journal
Journal of the American Medical Informatics Association
Publisher
Oxford University Press
Publication Date
Aug 13, 2021
Volume
28
Issue
9
Pages
1936–1946
Identifiers
DOI: 10.1093/jamia/ocab101
PMID: 34151965
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

Multitask learning (MTL) using electronic health records allows concurrent prediction of multiple endpoints. MTL has shown promise in improving model performance and training efficiency; however, it often suffers from negative transfer - impaired learning if tasks are not appropriately selected. We introduce a sequential subnetwork routing (SeqSNR) architecture that uses soft parameter sharing to find related tasks and encourage cross-learning between them. Using the MIMIC-III (Medical Information Mart for Intensive Care-III) dataset, we train deep neural network models to predict the onset of 6 endpoints including specific organ dysfunctions and general clinical outcomes: acute kidney injury, continuous renal replacement therapy, mechanical ventilation, vasoactive medications, mortality, and length of stay. We compare single-task (ST) models with naive multitask and SeqSNR in terms of discriminative performance and label efficiency. SeqSNR showed a modest yet statistically significant performance boost across 4 of 6 tasks compared with ST and naive multitasking. When the size of the training dataset was reduced for a given task (label efficiency), SeqSNR outperformed ST for all cases showing an average area under the precision-recall curve boost of 2.1%, 2.9%, and 2.1% for tasks using 1%, 5%, and 10% of labels, respectively. The SeqSNR architecture shows superior label efficiency compared with ST and naive multitasking, suggesting utility in scenarios in which endpoint labels are difficult to ascertain. © The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Report this publication

Statistics

Seen <100 times