@inproceedings{yang-etal-2024-clinicalmamba,
title = "{C}linical{M}amba: A Generative Clinical Language Model on Longitudinal Clinical Notes",
author = "Yang, Zhichao and
Mitra, Avijit and
Kwon, Sunjae and
Yu, Hong",
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-1.5",
doi = "10.18653/v1/2024.clinicalnlp-1.5",
pages = "54--63",
abstract = "The advancement of natural language processing (NLP) systems in healthcare hinges on language models{'} ability to interpret the intricate information contained within clinical notes. This process often requires integrating information from various time points in a patient{'}s medical history. However, most earlier clinical language models were pretrained with a context length limited to roughly one clinical document. In this study, We introduce ClinicalMamba, a specialized version of the Mamba language model, pretrained on a vast corpus of longitudinal clinical notes to address the unique linguistic characteristics and information processing needs of the medical domain. ClinicalMamba models, with 130 million and 2.8 billion parameters, demonstrate superior performance in modeling clinical language across extended text lengths compared to Mamba and other clinical models based on longformer and Llama. With few-shot learning, ClinicalMamba achieves notable benchmarks in speed and performance, outperforming existing clinical language models and large language models like GPT-4 in longitudinal clinical tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-clinicalmamba">
<titleInfo>
<title>ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhichao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avijit</namePart>
<namePart type="family">Mitra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunjae</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="family">Yu</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>The advancement of natural language processing (NLP) systems in healthcare hinges on language models’ ability to interpret the intricate information contained within clinical notes. This process often requires integrating information from various time points in a patient’s medical history. However, most earlier clinical language models were pretrained with a context length limited to roughly one clinical document. In this study, We introduce ClinicalMamba, a specialized version of the Mamba language model, pretrained on a vast corpus of longitudinal clinical notes to address the unique linguistic characteristics and information processing needs of the medical domain. ClinicalMamba models, with 130 million and 2.8 billion parameters, demonstrate superior performance in modeling clinical language across extended text lengths compared to Mamba and other clinical models based on longformer and Llama. With few-shot learning, ClinicalMamba achieves notable benchmarks in speed and performance, outperforming existing clinical language models and large language models like GPT-4 in longitudinal clinical tasks.</abstract>
<identifier type="citekey">yang-etal-2024-clinicalmamba</identifier>
<identifier type="doi">10.18653/v1/2024.clinicalnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.5</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>54</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes
%A Yang, Zhichao
%A Mitra, Avijit
%A Kwon, Sunjae
%A Yu, Hong
%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 yang-etal-2024-clinicalmamba
%X The advancement of natural language processing (NLP) systems in healthcare hinges on language models’ ability to interpret the intricate information contained within clinical notes. This process often requires integrating information from various time points in a patient’s medical history. However, most earlier clinical language models were pretrained with a context length limited to roughly one clinical document. In this study, We introduce ClinicalMamba, a specialized version of the Mamba language model, pretrained on a vast corpus of longitudinal clinical notes to address the unique linguistic characteristics and information processing needs of the medical domain. ClinicalMamba models, with 130 million and 2.8 billion parameters, demonstrate superior performance in modeling clinical language across extended text lengths compared to Mamba and other clinical models based on longformer and Llama. With few-shot learning, ClinicalMamba achieves notable benchmarks in speed and performance, outperforming existing clinical language models and large language models like GPT-4 in longitudinal clinical tasks.
%R 10.18653/v1/2024.clinicalnlp-1.5
%U https://aclanthology.org/2024.clinicalnlp-1.5
%U https://doi.org/10.18653/v1/2024.clinicalnlp-1.5
%P 54-63
Markdown (Informal)
[ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes](https://aclanthology.org/2024.clinicalnlp-1.5) (Yang et al., ClinicalNLP-WS 2024)
ACL