@inproceedings{hsu-etal-2020-characterizing,
title = "Characterizing the Value of Information in Medical Notes",
author = "Hsu, Chao-Chun and
Karnwal, Shantanu and
Mullainathan, Sendhil and
Obermeyer, Ziad and
Tan, Chenhao",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.187",
doi = "10.18653/v1/2020.findings-emnlp.187",
pages = "2062--2072",
abstract = "Machine learning models depend on the quality of input data. As electronic health records are widely adopted, the amount of data in health care is growing, along with complaints about the quality of medical notes. We use two prediction tasks, readmission prediction and in-hospital mortality prediction, to characterize the value of information in medical notes. We show that as a whole, medical notes only provide additional predictive power over structured information in readmission prediction. We further propose a probing framework to select parts of notes that enable more accurate predictions than using all notes, despite that the selected information leads to a distribution shift from the training data ({``}all notes{''}). Finally, we demonstrate that models trained on the selected valuable information achieve even better predictive performance, with only 6.8{\%}of all the tokens for readmission prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2020-characterizing">
<titleInfo>
<title>Characterizing the Value of Information in Medical Notes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chao-Chun</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantanu</namePart>
<namePart type="family">Karnwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sendhil</namePart>
<namePart type="family">Mullainathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziad</namePart>
<namePart type="family">Obermeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine learning models depend on the quality of input data. As electronic health records are widely adopted, the amount of data in health care is growing, along with complaints about the quality of medical notes. We use two prediction tasks, readmission prediction and in-hospital mortality prediction, to characterize the value of information in medical notes. We show that as a whole, medical notes only provide additional predictive power over structured information in readmission prediction. We further propose a probing framework to select parts of notes that enable more accurate predictions than using all notes, despite that the selected information leads to a distribution shift from the training data (“all notes”). Finally, we demonstrate that models trained on the selected valuable information achieve even better predictive performance, with only 6.8%of all the tokens for readmission prediction.</abstract>
<identifier type="citekey">hsu-etal-2020-characterizing</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.187</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.187</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2062</start>
<end>2072</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Characterizing the Value of Information in Medical Notes
%A Hsu, Chao-Chun
%A Karnwal, Shantanu
%A Mullainathan, Sendhil
%A Obermeyer, Ziad
%A Tan, Chenhao
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F hsu-etal-2020-characterizing
%X Machine learning models depend on the quality of input data. As electronic health records are widely adopted, the amount of data in health care is growing, along with complaints about the quality of medical notes. We use two prediction tasks, readmission prediction and in-hospital mortality prediction, to characterize the value of information in medical notes. We show that as a whole, medical notes only provide additional predictive power over structured information in readmission prediction. We further propose a probing framework to select parts of notes that enable more accurate predictions than using all notes, despite that the selected information leads to a distribution shift from the training data (“all notes”). Finally, we demonstrate that models trained on the selected valuable information achieve even better predictive performance, with only 6.8%of all the tokens for readmission prediction.
%R 10.18653/v1/2020.findings-emnlp.187
%U https://aclanthology.org/2020.findings-emnlp.187
%U https://doi.org/10.18653/v1/2020.findings-emnlp.187
%P 2062-2072
Markdown (Informal)
[Characterizing the Value of Information in Medical Notes](https://aclanthology.org/2020.findings-emnlp.187) (Hsu et al., Findings 2020)
ACL
- Chao-Chun Hsu, Shantanu Karnwal, Sendhil Mullainathan, Ziad Obermeyer, and Chenhao Tan. 2020. Characterizing the Value of Information in Medical Notes. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2062–2072, Online. Association for Computational Linguistics.