Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.10020 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914869743190016 |
|---|---|
| author | Gopalakrishnan, Seethalakshmi Garbayo, Luciana Zadrozny, Wlodek |
| author_facet | Gopalakrishnan, Seethalakshmi Garbayo, Luciana Zadrozny, Wlodek |
| contents | This study explores the potential of natural language models, including large language models, to extract causal relations from medical texts, specifically from Clinical Practice Guidelines (CPGs). The outcomes causality extraction from Clinical Practice Guidelines for gestational diabetes are presented, marking a first in the field. We report on a set of experiments using variants of BERT (BioBERT, DistilBERT, and BERT) and using Large Language Models (LLMs), namely GPT-4 and LLAMA2. Our experiments show that BioBERT performed better than other models, including the Large Language Models, with an average F1-score of 0.72. GPT-4 and LLAMA2 results show similar performance but less consistency. We also release the code and an annotated a corpus of causal statements within the Clinical Practice Guidelines for gestational diabetes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_10020 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Causality extraction from medical text using Large Language Models (LLMs) Gopalakrishnan, Seethalakshmi Garbayo, Luciana Zadrozny, Wlodek Computation and Language Artificial Intelligence Information Retrieval This study explores the potential of natural language models, including large language models, to extract causal relations from medical texts, specifically from Clinical Practice Guidelines (CPGs). The outcomes causality extraction from Clinical Practice Guidelines for gestational diabetes are presented, marking a first in the field. We report on a set of experiments using variants of BERT (BioBERT, DistilBERT, and BERT) and using Large Language Models (LLMs), namely GPT-4 and LLAMA2. Our experiments show that BioBERT performed better than other models, including the Large Language Models, with an average F1-score of 0.72. GPT-4 and LLAMA2 results show similar performance but less consistency. We also release the code and an annotated a corpus of causal statements within the Clinical Practice Guidelines for gestational diabetes. |
| title | Causality extraction from medical text using Large Language Models (LLMs) |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2407.10020 |