@inproceedings{alzghoul-etal-2024-cld,
title = "{CLD}-{MEC} at {MEDIQA}- {CORR} 2024 Task: {GPT}-4 Multi-Stage Clinical Chain of Thought Prompting for Medical Errors Detection and Correction",
author = "Alzghoul, Renad and
Ayaabdelhaq, Ayaabdelhaq and
Tabaza, Abdulrahman and
Altamimi, Ahmad",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.52",
doi = "10.18653/v1/2024.clinicalnlp-1.52",
pages = "537--556",
abstract = "This paper demonstrates CLD-MEC team submission to the MEDIQA-CORR 2024 shared task for identifying and correcting medical errors from clinical notes. We developed a framework to track two main types of medical errors: diagnostics and medical management-related errors. The tracking framework is implied utilizing a GPT-4 multi-stage prompting-based pipeline that ends with the three downstream tasks: classification of medical error existence (Task 1), identification of error location (Task 2), and correction error (Task 3). Throughout the pipeline, we employed clinical Chain of Thought (CoT) and Chain-of-Verification (CoVe) techniques to mitigate the hallucination and enforce the clinical context learning. The model performance is acceptable, given it is based on zero-shot learning. In addition, we developed a RAG system injected with clinical practice guidelines as an external knowledge datastore. Our RAG is based on the Bio{\_}ClinicalBERT as a vector embedding model. However, our RAG system failed to get the desired results. We proposed recommendations to be investigated in future research work to overcome the limitations of our approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alzghoul-etal-2024-cld">
<titleInfo>
<title>CLD-MEC at MEDIQA- CORR 2024 Task: GPT-4 Multi-Stage Clinical Chain of Thought Prompting for Medical Errors Detection and Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renad</namePart>
<namePart type="family">Alzghoul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayaabdelhaq</namePart>
<namePart type="family">Ayaabdelhaq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Tabaza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Altamimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th 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">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper demonstrates CLD-MEC team submission to the MEDIQA-CORR 2024 shared task for identifying and correcting medical errors from clinical notes. We developed a framework to track two main types of medical errors: diagnostics and medical management-related errors. The tracking framework is implied utilizing a GPT-4 multi-stage prompting-based pipeline that ends with the three downstream tasks: classification of medical error existence (Task 1), identification of error location (Task 2), and correction error (Task 3). Throughout the pipeline, we employed clinical Chain of Thought (CoT) and Chain-of-Verification (CoVe) techniques to mitigate the hallucination and enforce the clinical context learning. The model performance is acceptable, given it is based on zero-shot learning. In addition, we developed a RAG system injected with clinical practice guidelines as an external knowledge datastore. Our RAG is based on the Bio_ClinicalBERT as a vector embedding model. However, our RAG system failed to get the desired results. We proposed recommendations to be investigated in future research work to overcome the limitations of our approach.</abstract>
<identifier type="citekey">alzghoul-etal-2024-cld</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.52</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.52</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>537</start>
<end>556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLD-MEC at MEDIQA- CORR 2024 Task: GPT-4 Multi-Stage Clinical Chain of Thought Prompting for Medical Errors Detection and Correction
%A Alzghoul, Renad
%A Ayaabdelhaq, Ayaabdelhaq
%A Tabaza, Abdulrahman
%A Altamimi, Ahmad
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F alzghoul-etal-2024-cld
%X This paper demonstrates CLD-MEC team submission to the MEDIQA-CORR 2024 shared task for identifying and correcting medical errors from clinical notes. We developed a framework to track two main types of medical errors: diagnostics and medical management-related errors. The tracking framework is implied utilizing a GPT-4 multi-stage prompting-based pipeline that ends with the three downstream tasks: classification of medical error existence (Task 1), identification of error location (Task 2), and correction error (Task 3). Throughout the pipeline, we employed clinical Chain of Thought (CoT) and Chain-of-Verification (CoVe) techniques to mitigate the hallucination and enforce the clinical context learning. The model performance is acceptable, given it is based on zero-shot learning. In addition, we developed a RAG system injected with clinical practice guidelines as an external knowledge datastore. Our RAG is based on the Bio_ClinicalBERT as a vector embedding model. However, our RAG system failed to get the desired results. We proposed recommendations to be investigated in future research work to overcome the limitations of our approach.
%R 10.18653/v1/2024.clinicalnlp-1.52
%U https://aclanthology.org/2024.clinicalnlp-1.52
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.52
%P 537-556
Markdown (Informal)
[CLD-MEC at MEDIQA- CORR 2024 Task: GPT-4 Multi-Stage Clinical Chain of Thought Prompting for Medical Errors Detection and Correction](https://aclanthology.org/2024.clinicalnlp-1.52) (Alzghoul et al., ClinicalNLP-WS 2024)
ACL