Learning Unsupervised Representations for ICU Timeseries

Addison Weatherhead, Robert Greer, Michael-Alice Moga, Mjaye Mazwi, Danny Eytan, Anna Goldenberg, Sana Tonekaboni
Proceedings of the Conference on Health, Inference, and Learning, PMLR 174:152-168, 2022.

Abstract

Medical time series like physiological signals provide a rich source of information about patients’ underlying clinical states. Learning such states is a challenging problem for ML but has great utility for clinical applications. It allows us to identify patients with similar underlying conditions, track disease progression over time, and much more. The challenge with medical time series however, is the lack of well-defined labels for a given patient’s state for extended periods of time. Collecting such labels is expensive and often requires substantial effort. In this work, we propose an unsupervised representation learning method, called TRACE, that allows us to learn meaningful patient representations from time series collected in the Intensive Care Unit (ICU). We show the utility and generalizability of these representations in identifying different downstream clinical conditions and also show how the trajectory of representations over time exhibits progression toward critical conditions such as cardiopulmonary arrest or circulatory failure.

Cite this Paper

BibTeX
@InProceedings{pmlr-v174-weatherhead22a, title = {Learning Unsupervised Representations for ICU Timeseries}, author = {Weatherhead, Addison and Greer, Robert and Moga, Michael-Alice and Mazwi, Mjaye and Eytan, Danny and Goldenberg, Anna and Tonekaboni, Sana}, booktitle = {Proceedings of the Conference on Health, Inference, and Learning}, pages = {152--168}, year = {2022}, editor = {Flores, Gerardo and Chen, George H and Pollard, Tom and Ho, Joyce C and Naumann, Tristan}, volume = {174}, series = {Proceedings of Machine Learning Research}, month = {07--08 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v174/weatherhead22a/weatherhead22a.pdf}, url = {https://proceedings.mlr.press/v174/weatherhead22a.html}, abstract = {Medical time series like physiological signals provide a rich source of information about patients’ underlying clinical states. Learning such states is a challenging problem for ML but has great utility for clinical applications. It allows us to identify patients with similar underlying conditions, track disease progression over time, and much more. The challenge with medical time series however, is the lack of well-defined labels for a given patient’s state for extended periods of time. Collecting such labels is expensive and often requires substantial effort. In this work, we propose an unsupervised representation learning method, called TRACE, that allows us to learn meaningful patient representations from time series collected in the Intensive Care Unit (ICU). We show the utility and generalizability of these representations in identifying different downstream clinical conditions and also show how the trajectory of representations over time exhibits progression toward critical conditions such as cardiopulmonary arrest or circulatory failure.} }
Endnote
%0 Conference Paper %T Learning Unsupervised Representations for ICU Timeseries %A Addison Weatherhead %A Robert Greer %A Michael-Alice Moga %A Mjaye Mazwi %A Danny Eytan %A Anna Goldenberg %A Sana Tonekaboni %B Proceedings of the Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2022 %E Gerardo Flores %E George H Chen %E Tom Pollard %E Joyce C Ho %E Tristan Naumann %F pmlr-v174-weatherhead22a %I PMLR %P 152--168 %U https://proceedings.mlr.press/v174/weatherhead22a.html %V 174 %X Medical time series like physiological signals provide a rich source of information about patients’ underlying clinical states. Learning such states is a challenging problem for ML but has great utility for clinical applications. It allows us to identify patients with similar underlying conditions, track disease progression over time, and much more. The challenge with medical time series however, is the lack of well-defined labels for a given patient’s state for extended periods of time. Collecting such labels is expensive and often requires substantial effort. In this work, we propose an unsupervised representation learning method, called TRACE, that allows us to learn meaningful patient representations from time series collected in the Intensive Care Unit (ICU). We show the utility and generalizability of these representations in identifying different downstream clinical conditions and also show how the trajectory of representations over time exhibits progression toward critical conditions such as cardiopulmonary arrest or circulatory failure.
APA
Weatherhead, A., Greer, R., Moga, M., Mazwi, M., Eytan, D., Goldenberg, A. & Tonekaboni, S.. (2022). Learning Unsupervised Representations for ICU Timeseries. Proceedings of the Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 174:152-168 Available from https://proceedings.mlr.press/v174/weatherhead22a.html.

Related Material