@inproceedings{li-etal-2023-team,
title = "Team:{PULSAR} at {P}rob{S}um 2023:{PULSAR}: Pre-training with Extracted Healthcare Terms for Summarising Patients{'} Problems and Data Augmentation with Black-box Large Language Models",
author = "Li, Hao and
Wu, Yuping and
Schlegel, Viktor and
Batista-Navarro, Riza and
Nguyen, Thanh-Tung and
Ramesh Kashyap, Abhinav and
Zeng, Xiao-Jun and
Beck, Daniel and
Winkler, Stefan and
Nenadic, Goran",
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.49",
doi = "10.18653/v1/2023.bionlp-1.49",
pages = "503--509",
abstract = "Medical progress notes play a crucial role in documenting a patient{'}s hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient{'}s problems in the form of a {``}problem list{''} can aid stakeholders in understanding a patient{'}s condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focusses on generating a list of diagnoses and problems from the provider{'}s progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients{'} problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2023-team">
<titleInfo>
<title>Team:PULSAR at ProbSum 2023:PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients’ Problems and Data Augmentation with Black-box Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuping</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viktor</namePart>
<namePart type="family">Schlegel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Tung</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Ramesh Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao-Jun</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Beck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Winkler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Nenadic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical progress notes play a crucial role in documenting a patient’s hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient’s problems in the form of a “problem list” can aid stakeholders in understanding a patient’s condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focusses on generating a list of diagnoses and problems from the provider’s progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients’ problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.</abstract>
<identifier type="citekey">li-etal-2023-team</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.49</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.49</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>503</start>
<end>509</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team:PULSAR at ProbSum 2023:PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients’ Problems and Data Augmentation with Black-box Large Language Models
%A Li, Hao
%A Wu, Yuping
%A Schlegel, Viktor
%A Batista-Navarro, Riza
%A Nguyen, Thanh-Tung
%A Ramesh Kashyap, Abhinav
%A Zeng, Xiao-Jun
%A Beck, Daniel
%A Winkler, Stefan
%A Nenadic, Goran
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F li-etal-2023-team
%X Medical progress notes play a crucial role in documenting a patient’s hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers. Automatic summarisation of a patient’s problems in the form of a “problem list” can aid stakeholders in understanding a patient’s condition, reducing workload and cognitive bias. BioNLP 2023 Shared Task 1A focusses on generating a list of diagnoses and problems from the provider’s progress notes during hospitalisation. In this paper, we introduce our proposed approach to this task, which integrates two complementary components. One component employs large language models (LLMs) for data augmentation; the other is an abstractive summarisation LLM with a novel pre-training objective for generating the patients’ problems summarised as a list. Our approach was ranked second among all submissions to the shared task. The performance of our model on the development and test datasets shows that our approach is more robust on unknown data, with an improvement of up to 3.1 points over the same size of the larger model.
%R 10.18653/v1/2023.bionlp-1.49
%U https://aclanthology.org/2023.bionlp-1.49
%U https://doi.org/10.18653/v1/2023.bionlp-1.49
%P 503-509
Markdown (Informal)
[Team:PULSAR at ProbSum 2023:PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients’ Problems and Data Augmentation with Black-box Large Language Models](https://aclanthology.org/2023.bionlp-1.49) (Li et al., BioNLP 2023)
ACL
- Hao Li, Yuping Wu, Viktor Schlegel, Riza Batista-Navarro, Thanh-Tung Nguyen, Abhinav Ramesh Kashyap, Xiao-Jun Zeng, Daniel Beck, Stefan Winkler, and Goran Nenadic. 2023. Team:PULSAR at ProbSum 2023:PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients’ Problems and Data Augmentation with Black-box Large Language Models. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 503–509, Toronto, Canada. Association for Computational Linguistics.