Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2406.14500 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910495800295424 |
|---|---|
| author | Zhao, Xingmeng Wang, Tongnian Rios, Anthony |
| author_facet | Zhao, Xingmeng Wang, Tongnian Rios, Anthony |
| contents | Radiology report summarization (RRS) is crucial for patient care, requiring concise "Impressions" from detailed "Findings." This paper introduces a novel prompting strategy to enhance RRS by first generating a layperson summary. This approach normalizes key observations and simplifies complex information using non-expert communication techniques inspired by doctor-patient interactions. Combined with few-shot in-context learning, this method improves the model's ability to link general terms to specific findings. We evaluate this approach on the MIMIC-CXR, CheXpert, and MIMIC-III datasets, benchmarking it against 7B/8B parameter state-of-the-art open-source large language models (LLMs) like Meta-Llama-3-8B-Instruct. Our results demonstrate improvements in summarization accuracy and accessibility, particularly in out-of-domain tests, with improvements as high as 5% for some metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14500 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Expert Radiology Report Summarization by Prompting Large Language Models with a Layperson Summary Zhao, Xingmeng Wang, Tongnian Rios, Anthony Computation and Language Radiology report summarization (RRS) is crucial for patient care, requiring concise "Impressions" from detailed "Findings." This paper introduces a novel prompting strategy to enhance RRS by first generating a layperson summary. This approach normalizes key observations and simplifies complex information using non-expert communication techniques inspired by doctor-patient interactions. Combined with few-shot in-context learning, this method improves the model's ability to link general terms to specific findings. We evaluate this approach on the MIMIC-CXR, CheXpert, and MIMIC-III datasets, benchmarking it against 7B/8B parameter state-of-the-art open-source large language models (LLMs) like Meta-Llama-3-8B-Instruct. Our results demonstrate improvements in summarization accuracy and accessibility, particularly in out-of-domain tests, with improvements as high as 5% for some metrics. |
| title | Improving Expert Radiology Report Summarization by Prompting Large Language Models with a Layperson Summary |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.14500 |