Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.

<h4>Background</h4>New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span t...

Full description

Saved in:
Bibliographic Details
Main Authors: Son Q Duong, Le Zheng, Minjie Xia, Bo Jin, Modi Liu, Zhen Li, Shiying Hao, Shaun T Alfreds, Karl G Sylvester, Eric Widen, Jeffery J Teuteberg, Doff B McElhinney, Xuefeng B Ling
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2021-01-01
Series:PLoS ONE
Online Access:https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0260885&type=printable
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705650361204736
author Son Q Duong
Le Zheng
Minjie Xia
Bo Jin
Modi Liu
Zhen Li
Shiying Hao
Shaun T Alfreds
Karl G Sylvester
Eric Widen
Jeffery J Teuteberg
Doff B McElhinney
Xuefeng B Ling
author_facet Son Q Duong
Le Zheng
Minjie Xia
Bo Jin
Modi Liu
Zhen Li
Shiying Hao
Shaun T Alfreds
Karl G Sylvester
Eric Widen
Jeffery J Teuteberg
Doff B McElhinney
Xuefeng B Ling
author_sort Son Q Duong
collection DOAJ
description <h4>Background</h4>New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span the entire spectrum of clinical care, but there are no HIE-based clinical decision support tools for diagnosis of incident-HF. We applied machine-learning methods to model the one-year risk of incident-HF from the Maine statewide-HIE.<h4>Methods and results</h4>We included subjects aged ≥ 40 years without prior HF ICD9/10 codes during a three-year period from 2015 to 2018, and incident-HF defined as assignment of two outpatient or one inpatient code in a year. A tree-boosting algorithm was used to model the probability of incident-HF in year two from data collected in year one, and then validated in year three. 5,668 of 521,347 patients (1.09%) developed incident-HF in the validation cohort. In the validation cohort, the model c-statistic was 0.824 and at a clinically predetermined risk threshold, 10% of patients identified by the model developed incident-HF and 29% of all incident-HF cases in the state of Maine were identified.<h4>Conclusions</h4>Utilizing machine learning modeling techniques on passively collected clinical HIE data, we developed and validated an incident-HF prediction tool that performs on par with other models that require proactively collected clinical data. Our algorithm could be integrated into other HIEs to leverage the EMR resources to provide individuals, systems, and payors with a risk stratification tool to allow for targeted resource allocation to reduce incident-HF disease burden on individuals and health care systems.
format Article
id doaj-art-ef645ee2cc074b578313005a4e2b0f43
institution DOAJ
issn 1932-6203
language English
publishDate 2021-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-ef645ee2cc074b578313005a4e2b0f432025-08-20T03:16:25ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-011612e026088510.1371/journal.pone.0260885Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.Son Q DuongLe ZhengMinjie XiaBo JinModi LiuZhen LiShiying HaoShaun T AlfredsKarl G SylvesterEric WidenJeffery J TeutebergDoff B McElhinneyXuefeng B Ling<h4>Background</h4>New-onset heart failure (HF) is associated with poor prognosis and high healthcare utilization. Early identification of patients at increased risk incident-HF may allow for focused allocation of preventative care resources. Health information exchange (HIE) data span the entire spectrum of clinical care, but there are no HIE-based clinical decision support tools for diagnosis of incident-HF. We applied machine-learning methods to model the one-year risk of incident-HF from the Maine statewide-HIE.<h4>Methods and results</h4>We included subjects aged ≥ 40 years without prior HF ICD9/10 codes during a three-year period from 2015 to 2018, and incident-HF defined as assignment of two outpatient or one inpatient code in a year. A tree-boosting algorithm was used to model the probability of incident-HF in year two from data collected in year one, and then validated in year three. 5,668 of 521,347 patients (1.09%) developed incident-HF in the validation cohort. In the validation cohort, the model c-statistic was 0.824 and at a clinically predetermined risk threshold, 10% of patients identified by the model developed incident-HF and 29% of all incident-HF cases in the state of Maine were identified.<h4>Conclusions</h4>Utilizing machine learning modeling techniques on passively collected clinical HIE data, we developed and validated an incident-HF prediction tool that performs on par with other models that require proactively collected clinical data. Our algorithm could be integrated into other HIEs to leverage the EMR resources to provide individuals, systems, and payors with a risk stratification tool to allow for targeted resource allocation to reduce incident-HF disease burden on individuals and health care systems.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0260885&type=printable
spellingShingle Son Q Duong
Le Zheng
Minjie Xia
Bo Jin
Modi Liu
Zhen Li
Shiying Hao
Shaun T Alfreds
Karl G Sylvester
Eric Widen
Jeffery J Teuteberg
Doff B McElhinney
Xuefeng B Ling
Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
PLoS ONE
title Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
title_full Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
title_fullStr Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
title_full_unstemmed Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
title_short Identification of patients at risk of new onset heart failure: Utilizing a large statewide health information exchange to train and validate a risk prediction model.
title_sort identification of patients at risk of new onset heart failure utilizing a large statewide health information exchange to train and validate a risk prediction model
url https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0260885&type=printable
work_keys_str_mv AT sonqduong identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT lezheng identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT minjiexia identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT bojin identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT modiliu identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT zhenli identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT shiyinghao identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT shauntalfreds identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT karlgsylvester identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT ericwiden identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT jefferyjteuteberg identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT doffbmcelhinney identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel
AT xuefengbling identificationofpatientsatriskofnewonsetheartfailureutilizingalargestatewidehealthinformationexchangetotrainandvalidateariskpredictionmodel