Roy, S;
Mincu, D;
Loreaux, E;
Mottram, A;
Protsyuk, I;
Harris, N;
Xue, Y;
... Seneviratne, M; + view all
(2021)
Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing.
Journal of the American Medical Informatics Association
10.1093/jamia/ocab101.
(In press).
Preview |
Text
Montgomery_ocab101.pdf - Published Version Download (496kB) | Preview |
Abstract
OBJECTIVE: 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. MATERIALS AND METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
| Type: | Article |
|---|---|
| Title: | Multitask prediction of organ dysfunction in the intensive care unit using sequential subnetwork routing. |
| Location: | England |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1093/jamia/ocab101 |
| Publisher version: | https://doi.org/10.1093/jamia/ocab101 |
| Language: | English |
| Additional information: | © The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association. This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com |
| Keywords: | Deep Learning, Electronic Health Records, Intensive Care, Machine Learning, Multitask Learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Medicine UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Medicine > Experimental and Translational Medicine |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10130273 |
Archive Staff Only
 |
View Item |
