Projects per year
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 language | English |
---|---|
Title of host publication | 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 393-397 |
Number of pages | 5 |
ISBN (Electronic) | 9798350374513 |
DOIs | |
Publication status | Published - 15 Aug 2024 |
Event | 49th IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Seoul, Korea, Republic of Duration: 14 Apr 2024 → 19 Apr 2024 |
Conference
Conference | 49th IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 |
---|---|
Country/Territory | Korea, Republic of |
City | Seoul |
Period | 14/04/24 → 19/04/24 |
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.Projects
- 1 Finished
-
Data-driven anomaly detection in ICU signals with denoising autoencoders
2/03/20 → 31/03/22
Project: Research