Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909347735404544 |
|---|---|
| author | Pohyer, Valentin Fabre, Elizabeth Oudard, Stéphane Fournier, Laure Rance, Bastien |
| author_facet | Pohyer, Valentin Fabre, Elizabeth Oudard, Stéphane Fournier, Laure Rance, Bastien |
| contents | At the hospital, the dispersion of information regarding anti-cancer treatment makes it difficult to extract. We proposed a solution capable of identifying dates, drugs and their temporal relationship within free-text oncology reports with very few manual annotations. We used pattern recognition for dates, dictionaries for drugs and transformer language models for the relationship, combined with a data augmentation strategy. Our models achieved good prediction F1-scores, reaching 0.872. The performance of models with data augmentation outperforms those of models without. By inferring such models, we can now identify and structure thousands of previously unavailable treatment events to better apprehend solutions and patient response. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10271 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment Pohyer, Valentin Fabre, Elizabeth Oudard, Stéphane Fournier, Laure Rance, Bastien Quantitative Methods At the hospital, the dispersion of information regarding anti-cancer treatment makes it difficult to extract. We proposed a solution capable of identifying dates, drugs and their temporal relationship within free-text oncology reports with very few manual annotations. We used pattern recognition for dates, dictionaries for drugs and transformer language models for the relationship, combined with a data augmentation strategy. Our models achieved good prediction F1-scores, reaching 0.872. The performance of models with data augmentation outperforms those of models without. By inferring such models, we can now identify and structure thousands of previously unavailable treatment events to better apprehend solutions and patient response. |
| title | Fake it till you predict it: data augmentation strategies to detect initiation and termination of oncology treatment |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2410.10271 |