Predicting asthma control deterioration in children

Gang Luo, Bryan L. Stone, Bernhard Fassl, Christopher G Maloney, Per H. Gesteland, Sashidhar R. Yerram, Flory L. Nkoy

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Background: Pediatric asthma affects 7.1 million American children incurring an annual total direct healthcare cost around 9.3 billion dollars. Asthma control in children is suboptimal, leading to frequent asthma exacerbations, excess costs, and decreased quality of life. Successful prediction of risk for asthma control deterioration at the individual patient level would enhance self-management and enable early interventions to reduce asthma exacerbations. We developed and tested the first set of models for predicting a child's asthma control deterioration one week prior to occurrence. Methods: We previously reported validation of the Asthma Symptom Tracker, a weekly asthma self-monitoring tool. Over a period of two years, we used this tool to collect a total of 2912 weekly assessments of asthma control on 210 children. We combined the asthma control data set with patient attributes and environmental variables to develop machine learning models to predict a child's asthma control deterioration one week ahead. Results: Our best model achieved an accuracy of 71.8 %, a sensitivity of 73.8 %, a specificity of 71.4 %, and an area under the receiver operating characteristic curve of 0.757. We also identified potential improvements to our models to stimulate future research on this topic. Conclusions: Our best model successfully predicted a child's asthma control level one week ahead. With adequate accuracy, the model could be integrated into electronic asthma self-monitoring systems to provide real-time decision support and personalized early warnings of potential asthma control deteriorations.

Original languageEnglish (US)
Article number84
JournalBMC Medical Informatics and Decision Making
Volume15
Issue number1
DOIs
StatePublished - Oct 14 2015
Externally publishedYes

Fingerprint

Asthma
Self Care
ROC Curve
Health Care Costs
Quality of Life
Pediatrics
Costs and Cost Analysis

Keywords

  • Asthma control
  • Child
  • Predict

ASJC Scopus subject areas

  • Health Policy
  • Health Informatics

Cite this

Luo, G., Stone, B. L., Fassl, B., Maloney, C. G., Gesteland, P. H., Yerram, S. R., & Nkoy, F. L. (2015). Predicting asthma control deterioration in children. BMC Medical Informatics and Decision Making, 15(1), [84]. https://doi.org/10.1186/s12911-015-0208-9

Predicting asthma control deterioration in children. / Luo, Gang; Stone, Bryan L.; Fassl, Bernhard; Maloney, Christopher G; Gesteland, Per H.; Yerram, Sashidhar R.; Nkoy, Flory L.

In: BMC Medical Informatics and Decision Making, Vol. 15, No. 1, 84, 14.10.2015.

Research output: Contribution to journalArticle

Luo, Gang ; Stone, Bryan L. ; Fassl, Bernhard ; Maloney, Christopher G ; Gesteland, Per H. ; Yerram, Sashidhar R. ; Nkoy, Flory L. / Predicting asthma control deterioration in children. In: BMC Medical Informatics and Decision Making. 2015 ; Vol. 15, No. 1.
@article{9a208b3a9e6c4dd28dfe72f9d4dbcbde,
title = "Predicting asthma control deterioration in children",
abstract = "Background: Pediatric asthma affects 7.1 million American children incurring an annual total direct healthcare cost around 9.3 billion dollars. Asthma control in children is suboptimal, leading to frequent asthma exacerbations, excess costs, and decreased quality of life. Successful prediction of risk for asthma control deterioration at the individual patient level would enhance self-management and enable early interventions to reduce asthma exacerbations. We developed and tested the first set of models for predicting a child's asthma control deterioration one week prior to occurrence. Methods: We previously reported validation of the Asthma Symptom Tracker, a weekly asthma self-monitoring tool. Over a period of two years, we used this tool to collect a total of 2912 weekly assessments of asthma control on 210 children. We combined the asthma control data set with patient attributes and environmental variables to develop machine learning models to predict a child's asthma control deterioration one week ahead. Results: Our best model achieved an accuracy of 71.8 {\%}, a sensitivity of 73.8 {\%}, a specificity of 71.4 {\%}, and an area under the receiver operating characteristic curve of 0.757. We also identified potential improvements to our models to stimulate future research on this topic. Conclusions: Our best model successfully predicted a child's asthma control level one week ahead. With adequate accuracy, the model could be integrated into electronic asthma self-monitoring systems to provide real-time decision support and personalized early warnings of potential asthma control deteriorations.",
keywords = "Asthma control, Child, Predict",
author = "Gang Luo and Stone, {Bryan L.} and Bernhard Fassl and Maloney, {Christopher G} and Gesteland, {Per H.} and Yerram, {Sashidhar R.} and Nkoy, {Flory L.}",
year = "2015",
month = "10",
day = "14",
doi = "10.1186/s12911-015-0208-9",
language = "English (US)",
volume = "15",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Predicting asthma control deterioration in children

AU - Luo, Gang

AU - Stone, Bryan L.

AU - Fassl, Bernhard

AU - Maloney, Christopher G

AU - Gesteland, Per H.

AU - Yerram, Sashidhar R.

AU - Nkoy, Flory L.

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Background: Pediatric asthma affects 7.1 million American children incurring an annual total direct healthcare cost around 9.3 billion dollars. Asthma control in children is suboptimal, leading to frequent asthma exacerbations, excess costs, and decreased quality of life. Successful prediction of risk for asthma control deterioration at the individual patient level would enhance self-management and enable early interventions to reduce asthma exacerbations. We developed and tested the first set of models for predicting a child's asthma control deterioration one week prior to occurrence. Methods: We previously reported validation of the Asthma Symptom Tracker, a weekly asthma self-monitoring tool. Over a period of two years, we used this tool to collect a total of 2912 weekly assessments of asthma control on 210 children. We combined the asthma control data set with patient attributes and environmental variables to develop machine learning models to predict a child's asthma control deterioration one week ahead. Results: Our best model achieved an accuracy of 71.8 %, a sensitivity of 73.8 %, a specificity of 71.4 %, and an area under the receiver operating characteristic curve of 0.757. We also identified potential improvements to our models to stimulate future research on this topic. Conclusions: Our best model successfully predicted a child's asthma control level one week ahead. With adequate accuracy, the model could be integrated into electronic asthma self-monitoring systems to provide real-time decision support and personalized early warnings of potential asthma control deteriorations.

AB - Background: Pediatric asthma affects 7.1 million American children incurring an annual total direct healthcare cost around 9.3 billion dollars. Asthma control in children is suboptimal, leading to frequent asthma exacerbations, excess costs, and decreased quality of life. Successful prediction of risk for asthma control deterioration at the individual patient level would enhance self-management and enable early interventions to reduce asthma exacerbations. We developed and tested the first set of models for predicting a child's asthma control deterioration one week prior to occurrence. Methods: We previously reported validation of the Asthma Symptom Tracker, a weekly asthma self-monitoring tool. Over a period of two years, we used this tool to collect a total of 2912 weekly assessments of asthma control on 210 children. We combined the asthma control data set with patient attributes and environmental variables to develop machine learning models to predict a child's asthma control deterioration one week ahead. Results: Our best model achieved an accuracy of 71.8 %, a sensitivity of 73.8 %, a specificity of 71.4 %, and an area under the receiver operating characteristic curve of 0.757. We also identified potential improvements to our models to stimulate future research on this topic. Conclusions: Our best model successfully predicted a child's asthma control level one week ahead. With adequate accuracy, the model could be integrated into electronic asthma self-monitoring systems to provide real-time decision support and personalized early warnings of potential asthma control deteriorations.

KW - Asthma control

KW - Child

KW - Predict

UR - http://www.scopus.com/inward/record.url?scp=84944245904&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944245904&partnerID=8YFLogxK

U2 - 10.1186/s12911-015-0208-9

DO - 10.1186/s12911-015-0208-9

M3 - Article

VL - 15

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

SN - 1472-6947

IS - 1

M1 - 84

ER -