1. Language Model Training Paradigms for Clinical Feature Embeddings
- Author
-
Hu, Yurong, Burger, Manuel, Rätsch, Gunnar, and Kuznetsova, Rita
- Subjects
Computer Science - Machine Learning ,Computer Science - Computation and Language - Abstract
In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and blood pressure. We use self-supervised training paradigms for language models to learn high-quality clinical feature embeddings, achieving a finer granularity than existing time-step and patient-level representation learning. We visualize the learnt embeddings via unsupervised dimension reduction techniques and observe a high degree of consistency with prior clinical knowledge. We also evaluate the model performance on the MIMIC-III benchmark and demonstrate the effectiveness of using clinical feature embeddings. We publish our code online for replication., Comment: Poster at "NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice"
- Published
- 2023