RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kell, Gregory, Roberts, Angus, Umansky, Serge, Khare, Yuti, Ahmed, Najma, Patel, Nikhil, Simela, Chloe, Coumbe, Jack, Rozario, Julian, Griffiths, Ryan-Rhys, Marshall, Iain J.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911991283580928
author Kell, Gregory
Roberts, Angus
Umansky, Serge
Khare, Yuti
Ahmed, Najma
Patel, Nikhil
Simela, Chloe
Coumbe, Jack
Rozario, Julian
Griffiths, Ryan-Rhys
Marshall, Iain J.
author_facet Kell, Gregory
Roberts, Angus
Umansky, Serge
Khare, Yuti
Ahmed, Najma
Patel, Nikhil
Simela, Chloe
Coumbe, Jack
Rozario, Julian
Griffiths, Ryan-Rhys
Marshall, Iain J.
contents Clinical question answering systems have the potential to provide clinicians with relevant and timely answers to their questions. Nonetheless, despite the advances that have been made, adoption of these systems in clinical settings has been slow. One issue is a lack of question-answering datasets which reflect the real-world needs of health professionals. In this work, we present RealMedQA, a dataset of realistic clinical questions generated by humans and an LLM. We describe the process for generating and verifying the QA pairs and assess several QA models on BioASQ and RealMedQA to assess the relative difficulty of matching answers to questions. We show that the LLM is more cost-efficient for generating "ideal" QA pairs. Additionally, we achieve a lower lexical similarity between questions and answers than BioASQ which provides an additional challenge to the top two QA models, as per the results. We release our code and our dataset publicly to encourage further research.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08624
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions
Kell, Gregory
Roberts, Angus
Umansky, Serge
Khare, Yuti
Ahmed, Najma
Patel, Nikhil
Simela, Chloe
Coumbe, Jack
Rozario, Julian
Griffiths, Ryan-Rhys
Marshall, Iain J.
Computation and Language
Artificial Intelligence
Clinical question answering systems have the potential to provide clinicians with relevant and timely answers to their questions. Nonetheless, despite the advances that have been made, adoption of these systems in clinical settings has been slow. One issue is a lack of question-answering datasets which reflect the real-world needs of health professionals. In this work, we present RealMedQA, a dataset of realistic clinical questions generated by humans and an LLM. We describe the process for generating and verifying the QA pairs and assess several QA models on BioASQ and RealMedQA to assess the relative difficulty of matching answers to questions. We show that the LLM is more cost-efficient for generating "ideal" QA pairs. Additionally, we achieve a lower lexical similarity between questions and answers than BioASQ which provides an additional challenge to the top two QA models, as per the results. We release our code and our dataset publicly to encourage further research.
title RealMedQA: A pilot biomedical question answering dataset containing realistic clinical questions
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2408.08624