<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nair-etal-2023-generating">
    <titleInfo>
        <title>Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Varun</namePart>
        <namePart type="family">Nair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Elliot</namePart>
        <namePart type="family">Schumacher</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anitha</namePart>
        <namePart type="family">Kannan</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>Proceedings of the 5th Clinical Natural Language Processing Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Tristan</namePart>
            <namePart type="family">Naumann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asma</namePart>
            <namePart type="family">Ben Abacha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kirk</namePart>
            <namePart type="family">Roberts</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rumshisky</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>A medical provider’s summary of a patient visit serves several critical purposes, including clinical decision-making, facilitating hand-offs between providers, and as a reference for the patient. An effective summary is required to be coherent and accurately capture all the medically relevant information in the dialogue, despite the complexity of patient-generated language. Even minor inaccuracies in visit summaries (for example, summarizing “patient does not have a fever” when a fever is present) can be detrimental to the outcome of care for the patient. This paper tackles the problem of medical conversation summarization by discretizing the task into several smaller dialogue-understanding tasks that are sequentially built upon. First, we identify medical entities and their affirmations within the conversation to serve as building blocks. We study dynamically constructing few-shot prompts for tasks by conditioning on relevant patient information and use GPT-3 as the backbone for our experiments. We also develop GPT-derived summarization metrics to measure performance against reference summaries quantitatively. Both our human evaluation study and metrics for medical correctness show that summaries generated using this approach are clinically accurate and outperform the baseline approach of summarizing the dialog in a zero-shot, single-prompt setting.</abstract>
    <identifier type="citekey">nair-etal-2023-generating</identifier>
    <identifier type="doi">10.18653/v1/2023.clinicalnlp-1.26</identifier>
    <location>
        <url>https://aclanthology.org/2023.clinicalnlp-1.26</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>200</start>
            <end>217</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models
%A Nair, Varun
%A Schumacher, Elliot
%A Kannan, Anitha
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 5th Clinical Natural Language Processing Workshop
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F nair-etal-2023-generating
%X A medical provider’s summary of a patient visit serves several critical purposes, including clinical decision-making, facilitating hand-offs between providers, and as a reference for the patient. An effective summary is required to be coherent and accurately capture all the medically relevant information in the dialogue, despite the complexity of patient-generated language. Even minor inaccuracies in visit summaries (for example, summarizing “patient does not have a fever” when a fever is present) can be detrimental to the outcome of care for the patient. This paper tackles the problem of medical conversation summarization by discretizing the task into several smaller dialogue-understanding tasks that are sequentially built upon. First, we identify medical entities and their affirmations within the conversation to serve as building blocks. We study dynamically constructing few-shot prompts for tasks by conditioning on relevant patient information and use GPT-3 as the backbone for our experiments. We also develop GPT-derived summarization metrics to measure performance against reference summaries quantitatively. Both our human evaluation study and metrics for medical correctness show that summaries generated using this approach are clinically accurate and outperform the baseline approach of summarizing the dialog in a zero-shot, single-prompt setting.
%R 10.18653/v1/2023.clinicalnlp-1.26
%U https://aclanthology.org/2023.clinicalnlp-1.26
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.26
%P 200-217

Markdown (Informal)

[Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models](https://aclanthology.org/2023.clinicalnlp-1.26) (Nair et al., ClinicalNLP 2023)

• Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models (Nair et al., ClinicalNLP 2023)

ACL

• Varun Nair, Elliot Schumacher, and Anitha Kannan. 2023. Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 200–217, Toronto, Canada. Association for Computational Linguistics.