@inproceedings{he-etal-2019-extracting,
title = "Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research",
author = "He, Kai and
Wu, Jialun and
Ma, Xiaoyong and
Zhang, Chong and
Huang, Ming and
Li, Chen and
Yao, Lixia",
editor = "Weissenbacher, Davy and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the Fourth Social Media Mining for Health Applications (\#SMM4H) Workshop \& Shared Task",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3201/",
doi = "10.18653/v1/W19-3201",
pages = "1--10",
abstract = "Claims database and electronic health records database do not usually capture kinship or family relationship information, which is imperative for genetic research. We identify online obituaries as a new data source and propose a special named entity recognition and relation extraction solution to extract names and kinships from online obituaries. Built on 1,809 annotated obituaries and a novel tagging scheme, our joint neural model achieved macro-averaged precision, recall and F measure of 72.69\%, 78.54\% and 74.93\%, and micro-averaged precision, recall and F measure of 95.74\%, 98.25\% and 96.98\% using 57 kinships with 10 or more examples in a 10-fold cross-validation experiment. The model performance improved dramatically when trained with 34 kinships with 50 or more examples. Leveraging additional information such as age, death date, birth date and residence mentioned by obituaries, we foresee a promising future of supplementing EHR databases with comprehensive and accurate kinship information for genetic research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2019-extracting">
<titleInfo>
<title>Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jialun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lixia</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Claims database and electronic health records database do not usually capture kinship or family relationship information, which is imperative for genetic research. We identify online obituaries as a new data source and propose a special named entity recognition and relation extraction solution to extract names and kinships from online obituaries. Built on 1,809 annotated obituaries and a novel tagging scheme, our joint neural model achieved macro-averaged precision, recall and F measure of 72.69%, 78.54% and 74.93%, and micro-averaged precision, recall and F measure of 95.74%, 98.25% and 96.98% using 57 kinships with 10 or more examples in a 10-fold cross-validation experiment. The model performance improved dramatically when trained with 34 kinships with 50 or more examples. Leveraging additional information such as age, death date, birth date and residence mentioned by obituaries, we foresee a promising future of supplementing EHR databases with comprehensive and accurate kinship information for genetic research.</abstract>
<identifier type="citekey">he-etal-2019-extracting</identifier>
<identifier type="doi">10.18653/v1/W19-3201</identifier>
<location>
<url>https://aclanthology.org/W19-3201/</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research
%A He, Kai
%A Wu, Jialun
%A Ma, Xiaoyong
%A Zhang, Chong
%A Huang, Ming
%A Li, Chen
%A Yao, Lixia
%Y Weissenbacher, Davy
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F he-etal-2019-extracting
%X Claims database and electronic health records database do not usually capture kinship or family relationship information, which is imperative for genetic research. We identify online obituaries as a new data source and propose a special named entity recognition and relation extraction solution to extract names and kinships from online obituaries. Built on 1,809 annotated obituaries and a novel tagging scheme, our joint neural model achieved macro-averaged precision, recall and F measure of 72.69%, 78.54% and 74.93%, and micro-averaged precision, recall and F measure of 95.74%, 98.25% and 96.98% using 57 kinships with 10 or more examples in a 10-fold cross-validation experiment. The model performance improved dramatically when trained with 34 kinships with 50 or more examples. Leveraging additional information such as age, death date, birth date and residence mentioned by obituaries, we foresee a promising future of supplementing EHR databases with comprehensive and accurate kinship information for genetic research.
%R 10.18653/v1/W19-3201
%U https://aclanthology.org/W19-3201/
%U https://doi.org/10.18653/v1/W19-3201
%P 1-10
Markdown (Informal)
[Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research](https://aclanthology.org/W19-3201/) (He et al., ACL 2019)
ACL