@inproceedings{grundmann-etal-2024-data-drift,
title = "Data Drift in Clinical Outcome Prediction from Admission Notes",
author = "Grundmann, Paul and
Papaioannou, Jens-Michalis and
Oberhauser, Tom and
Steffek, Thomas and
Siu, Amy and
Nejdl, Wolfgang and
Loeser, Alexander",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.391",
pages = "4381--4391",
abstract = "Clinical NLP research faces a scarcity of publicly available datasets due to privacy concerns. MIMIC-III marked a significant milestone, enabling substantial progress, and now, with MIMIC-IV, the dataset has expanded significantly, offering a broader scope. In this paper, we focus on the task of predicting clinical outcomes from clinical text. This is crucial in modern healthcare, aiding in preventive care, differential diagnosis, and capacity planning. We introduce a novel clinical outcome prediction dataset derived from MIMIC-IV. Furthermore, we provide initial insights into the performance of models trained on MIMIC-III when applied to our new dataset, with specific attention to potential data drift. We investigate challenges tied to evolving documentation standards and changing codes in the International Classification of Diseases (ICD) taxonomy, such as the transition from ICD-9 to ICD-10. We also explore variations in clinical text across different hospital wards. Our study aims to probe the robustness and generalization of clinical outcome prediction models, contributing to the ongoing advancement of clinical NLP in healthcare.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grundmann-etal-2024-data-drift">
<titleInfo>
<title>Data Drift in Clinical Outcome Prediction from Admission Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Grundmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jens-Michalis</namePart>
<namePart type="family">Papaioannou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Oberhauser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Steffek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Siu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Nejdl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Loeser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Clinical NLP research faces a scarcity of publicly available datasets due to privacy concerns. MIMIC-III marked a significant milestone, enabling substantial progress, and now, with MIMIC-IV, the dataset has expanded significantly, offering a broader scope. In this paper, we focus on the task of predicting clinical outcomes from clinical text. This is crucial in modern healthcare, aiding in preventive care, differential diagnosis, and capacity planning. We introduce a novel clinical outcome prediction dataset derived from MIMIC-IV. Furthermore, we provide initial insights into the performance of models trained on MIMIC-III when applied to our new dataset, with specific attention to potential data drift. We investigate challenges tied to evolving documentation standards and changing codes in the International Classification of Diseases (ICD) taxonomy, such as the transition from ICD-9 to ICD-10. We also explore variations in clinical text across different hospital wards. Our study aims to probe the robustness and generalization of clinical outcome prediction models, contributing to the ongoing advancement of clinical NLP in healthcare.</abstract>
<identifier type="citekey">grundmann-etal-2024-data-drift</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.391</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4381</start>
<end>4391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Drift in Clinical Outcome Prediction from Admission Notes
%A Grundmann, Paul
%A Papaioannou, Jens-Michalis
%A Oberhauser, Tom
%A Steffek, Thomas
%A Siu, Amy
%A Nejdl, Wolfgang
%A Loeser, Alexander
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F grundmann-etal-2024-data-drift
%X Clinical NLP research faces a scarcity of publicly available datasets due to privacy concerns. MIMIC-III marked a significant milestone, enabling substantial progress, and now, with MIMIC-IV, the dataset has expanded significantly, offering a broader scope. In this paper, we focus on the task of predicting clinical outcomes from clinical text. This is crucial in modern healthcare, aiding in preventive care, differential diagnosis, and capacity planning. We introduce a novel clinical outcome prediction dataset derived from MIMIC-IV. Furthermore, we provide initial insights into the performance of models trained on MIMIC-III when applied to our new dataset, with specific attention to potential data drift. We investigate challenges tied to evolving documentation standards and changing codes in the International Classification of Diseases (ICD) taxonomy, such as the transition from ICD-9 to ICD-10. We also explore variations in clinical text across different hospital wards. Our study aims to probe the robustness and generalization of clinical outcome prediction models, contributing to the ongoing advancement of clinical NLP in healthcare.
%U https://aclanthology.org/2024.lrec-main.391
%P 4381-4391
Markdown (Informal)
[Data Drift in Clinical Outcome Prediction from Admission Notes](https://aclanthology.org/2024.lrec-main.391) (Grundmann et al., LREC-COLING 2024)
ACL
- Paul Grundmann, Jens-Michalis Papaioannou, Tom Oberhauser, Thomas Steffek, Amy Siu, Wolfgang Nejdl, and Alexander Loeser. 2024. Data Drift in Clinical Outcome Prediction from Admission Notes. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4381–4391, Torino, Italia. ELRA and ICCL.