@inproceedings{dandala-etal-2016-scoring,
title = "Scoring Disease-Medication Associations using Advanced {NLP}, Machine Learning, and Multiple Content Sources",
author = "Dandala, Bharath and
Devarakonda, Murthy and
Bornea, Mihaela and
Nielson, Christopher",
editor = "Ananiadou, Sophia and
Batista-Navarro, Riza and
Cohen, Kevin Bretonnel and
Demner-Fushman, Dina and
Thompson, Paul",
booktitle = "Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining ({B}io{T}xt{M}2016)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-5114/",
pages = "125--133",
abstract = "Effective knowledge resources are critical for developing successful clinical decision support systems that alleviate the cognitive load on physicians in patient care. In this paper, we describe two new methods for building a knowledge resource of disease to medication associations. These methods use fundamentally different content and are based on advanced natural language processing and machine learning techniques. One method uses distributional semantics on large medical text, and the other uses data mining on a large number of patient records. The methods are evaluated using 25,379 unique disease-medication pairs extracted from 100 de-identified longitudinal patient records of a large multi-provider hospital system. We measured recall (R), precision (P), and F scores for positive and negative association prediction, along with coverage and accuracy. While individual methods performed well, a combined stacked classifier achieved the best performance, indicating the limitations and unique value of each resource and method. In predicting positive associations, the stacked combination significantly outperformed the baseline (a distant semi-supervised method on large medical text), achieving F scores of 0.75 versus 0.55 on the pairs seen in the patient records, and F scores of 0.69 and 0.35 on unique pairs."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dandala-etal-2016-scoring">
<titleInfo>
<title>Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharath</namePart>
<namePart type="family">Dandala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Murthy</namePart>
<namePart type="family">Devarakonda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihaela</namePart>
<namePart type="family">Bornea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Nielson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Effective knowledge resources are critical for developing successful clinical decision support systems that alleviate the cognitive load on physicians in patient care. In this paper, we describe two new methods for building a knowledge resource of disease to medication associations. These methods use fundamentally different content and are based on advanced natural language processing and machine learning techniques. One method uses distributional semantics on large medical text, and the other uses data mining on a large number of patient records. The methods are evaluated using 25,379 unique disease-medication pairs extracted from 100 de-identified longitudinal patient records of a large multi-provider hospital system. We measured recall (R), precision (P), and F scores for positive and negative association prediction, along with coverage and accuracy. While individual methods performed well, a combined stacked classifier achieved the best performance, indicating the limitations and unique value of each resource and method. In predicting positive associations, the stacked combination significantly outperformed the baseline (a distant semi-supervised method on large medical text), achieving F scores of 0.75 versus 0.55 on the pairs seen in the patient records, and F scores of 0.69 and 0.35 on unique pairs.</abstract>
<identifier type="citekey">dandala-etal-2016-scoring</identifier>
<location>
<url>https://aclanthology.org/W16-5114/</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>125</start>
<end>133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources
%A Dandala, Bharath
%A Devarakonda, Murthy
%A Bornea, Mihaela
%A Nielson, Christopher
%Y Ananiadou, Sophia
%Y Batista-Navarro, Riza
%Y Cohen, Kevin Bretonnel
%Y Demner-Fushman, Dina
%Y Thompson, Paul
%S Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F dandala-etal-2016-scoring
%X Effective knowledge resources are critical for developing successful clinical decision support systems that alleviate the cognitive load on physicians in patient care. In this paper, we describe two new methods for building a knowledge resource of disease to medication associations. These methods use fundamentally different content and are based on advanced natural language processing and machine learning techniques. One method uses distributional semantics on large medical text, and the other uses data mining on a large number of patient records. The methods are evaluated using 25,379 unique disease-medication pairs extracted from 100 de-identified longitudinal patient records of a large multi-provider hospital system. We measured recall (R), precision (P), and F scores for positive and negative association prediction, along with coverage and accuracy. While individual methods performed well, a combined stacked classifier achieved the best performance, indicating the limitations and unique value of each resource and method. In predicting positive associations, the stacked combination significantly outperformed the baseline (a distant semi-supervised method on large medical text), achieving F scores of 0.75 versus 0.55 on the pairs seen in the patient records, and F scores of 0.69 and 0.35 on unique pairs.
%U https://aclanthology.org/W16-5114/
%P 125-133
Markdown (Informal)
[Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources](https://aclanthology.org/W16-5114/) (Dandala et al., 2016)
ACL