Collaborative Learning of Common Latent Representations in Routinely Collected Multivariate ICU Physiological Signals

Hollan Haule*, Ian Piper, Patricia Jones, Tsz Yan Milly Lo, Javier Escudero

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In Intensive Care Units (ICU), the abundance of multivariate time series presents an opportunity for machine learning (ML) to enhance patient phenotyping. In contrast to previous research focused on electronic health records (EHR), here we propose an ML approach for phenotyping using routinely collected physiological time series data. Our new algorithm integrates Long Short-Term Memory (LSTM) networks with collaborative filtering concepts to identify common physiological states across patients. Tested on real-world ICU clinical data for intracranial hypertension (IH) detection in patients with brain injury, our method achieved an area under the curve (AUC) of 0.889 and average precision (AP) of 0.725. Moreover, our algorithm outperforms autoencoders in learning more structured latent representations of the physiological signals. These findings highlight the promise of our methodology for patient phenotyping, leveraging routinely collected multivariate time series to improve clinical care practices.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers
Pages393-397
Number of pages5
ISBN (Electronic)9798350374513
DOIs
Publication statusPublished - 15 Aug 2024
Event49th IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024

Conference

Conference49th IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/2419/04/24

Keywords / Materials (for Non-textual outputs)

  • Collaborative filtering
  • Latent representation
  • Machine learning
  • Phenotype
  • Time series

Fingerprint

Dive into the research topics of 'Collaborative Learning of Common Latent Representations in Routinely Collected Multivariate ICU Physiological Signals'. Together they form a unique fingerprint.

Cite this