Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit

Arvind Ramanathan; Laura L. Pullum; Tanner C. Hobson; Christopher G. Stahl; Chad A. Steed; Shannon P. Quinn; Chakra S. Chennubhotla; Silvia Valkova

doi:10.3389/fpubh.2015.00182

Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit

Arvind Ramanathan, Laura L. Pullum, Tanner C. Hobson, Christopher G. Stahl, Chad A. Steed, Shannon P. Quinn, Chakra S. Chennubhotla, Silvia Valkova

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

We describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flu incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.

Original language	English
Article number	182
Journal	Frontiers in Public Health
Volume	3
DOIs	https://doi.org/10.3389/fpubh.2015.00182
State	Published - Aug 3 2015

Funding

Funding: Preparation of this paper was funded by ORNL internal SEED project number 7280, “Demonstrating a Novel BioDefense Capability using Public Health Data Informatics.” This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, Funding : Preparation of this paper was funded by ORNL internal SEED project number 7280, “Demonstrating a Novel Bio-Defense Capability using Public Health Data Informatics.” This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

Keywords

asthma
disease co-occurrence
electronic healthcare reimbursement claims
flu
non-negative matrix factorization
public health surveillance

Access to Document

10.3389/fpubh.2015.00182

Cite this

@article{9f26923a0cd74b84bebdd1b9219fce6b,

title = "Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit",

abstract = "We describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flu incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.",

keywords = "asthma, disease co-occurrence, electronic healthcare reimbursement claims, flu, non-negative matrix factorization, public health surveillance",

author = "Arvind Ramanathan and Pullum, {Laura L.} and Hobson, {Tanner C.} and Stahl, {Christopher G.} and Steed, {Chad A.} and Quinn, {Shannon P.} and Chennubhotla, {Chakra S.} and Silvia Valkova",

note = "Publisher Copyright: {\textcopyright} Copyright {\textcopyright} 2015 Ramanathan, Pullum, Hobson, Stahl, Steed, Quinn, Chennubhotla and Valkova.",

year = "2015",

month = aug,

day = "3",

doi = "10.3389/fpubh.2015.00182",

language = "English",

volume = "3",

journal = "Frontiers in Public Health",

issn = "2296-2565",

publisher = "Frontiers Media",

}

TY - JOUR

T1 - Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit

AU - Ramanathan, Arvind

AU - Pullum, Laura L.

AU - Hobson, Tanner C.

AU - Stahl, Christopher G.

AU - Steed, Chad A.

AU - Quinn, Shannon P.

AU - Chennubhotla, Chakra S.

AU - Valkova, Silvia

PY - 2015/8/3

Y1 - 2015/8/3

N2 - We describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flu incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.

AB - We describe a data-driven unsupervised machine learning approach to extract geo-temporal co-occurrence patterns of asthma and the flu from large-scale electronic healthcare reimbursement claims (eHRC) datasets. Specifically, we examine the eHRC data from 2009 to 2010 pandemic H1N1 influenza season and analyze whether different geographic regions within the United States (US) showed an increase in co-occurrence patterns of the flu and asthma. Our analyses reveal that the temporal patterns extracted from the eHRC data show a distinct lag time between the peak incidence of the asthma and the flu. While the increased occurrence of asthma contributed to increased flu incidence during the pandemic, this co-occurrence is predominant for female patients. The geo-temporal patterns reveal that the co-occurrence of the flu and asthma are typically concentrated within the south-east US. Further, in agreement with previous studies, large urban areas (such as New York, Miami, and Los Angeles) exhibit co-occurrence patterns that suggest a peak incidence of asthma and flu significantly early in the spring and winter seasons. Together, our data-analytic approach, integrated within the Oak Ridge Bio-surveillance Toolkit platform, demonstrates how eHRC data can provide novel insights into co-occurring disease patterns.

KW - asthma

KW - disease co-occurrence

KW - electronic healthcare reimbursement claims

KW - flu

KW - non-negative matrix factorization

KW - public health surveillance

UR - http://www.scopus.com/inward/record.url?scp=84981525931&partnerID=8YFLogxK

U2 - 10.3389/fpubh.2015.00182

DO - 10.3389/fpubh.2015.00182

M3 - Article

AN - SCOPUS:84981525931

SN - 2296-2565

VL - 3

JO - Frontiers in Public Health

JF - Frontiers in Public Health

M1 - 182

ER -

Discovering Multi-Scale Co-Occurrence Patterns of Asthma and Influenza with Oak Ridge Bio-Surveillance Toolkit

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this