Language Model Training Paradigms for Clinical Feature Embeddings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911771771535360 |
|---|---|
| author | Hu, Yurong Burger, Manuel Rätsch, Gunnar Kuznetsova, Rita |
| author_facet | Hu, Yurong Burger, Manuel Rätsch, Gunnar Kuznetsova, Rita |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_00768 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Language Model Training Paradigms for Clinical Feature Embeddings Hu, Yurong Burger, Manuel Rätsch, Gunnar Kuznetsova, Rita Machine Learning Computation and Language 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. |
| title | Language Model Training Paradigms for Clinical Feature Embeddings |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2311.00768 |