Machine learning approaches to personalize early prediction of asthma exacerbations

Joseph Finkelstein, In cheol Jeong

Research output: Contribution to journalArticle

Abstract

Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

Original languageEnglish (US)
JournalAnnals of the New York Academy of Sciences
DOIs
StateAccepted/In press - 2016
Externally publishedYes

Fingerprint

Learning systems
Asthma
Classifiers
Bayesian networks
Learning algorithms
Support vector machines
Feature extraction
Agglomeration
Trajectories
Health
Monitoring
Self Report
Chronic Disease
Machine Learning
Prediction
Datasets
Classifier

Keywords

  • Asthma exacerbation
  • Machine learning
  • Personalized medicine
  • Prediction

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • History and Philosophy of Science

Cite this

Machine learning approaches to personalize early prediction of asthma exacerbations. / Finkelstein, Joseph; Jeong, In cheol.

In: Annals of the New York Academy of Sciences, 2016.

Research output: Contribution to journalArticle

@article{a159f92c61fa4a8992819db292038b32,
title = "Machine learning approaches to personalize early prediction of asthma exacerbations",
abstract = "Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.",
keywords = "Asthma exacerbation, Machine learning, Personalized medicine, Prediction",
author = "Joseph Finkelstein and Jeong, {In cheol}",
year = "2016",
doi = "10.1111/nyas.13218",
language = "English (US)",
journal = "Annals of the New York Academy of Sciences",
issn = "0077-8923",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Machine learning approaches to personalize early prediction of asthma exacerbations

AU - Finkelstein, Joseph

AU - Jeong, In cheol

PY - 2016

Y1 - 2016

N2 - Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

AB - Patient telemonitoring results in an aggregation of significant amounts of information about patient disease trajectory. However, the potential use of this information for early prediction of exacerbations in adult asthma patients has not been systematically evaluated. The aim of this study was to explore the utility of telemonitoring data for building machine learning algorithms that predict asthma exacerbations before they occur. The study dataset comprised daily self-monitoring reports consisting of 7001 records submitted by adult asthma patients during home telemonitoring. Predictive modeling included preparation of stratified training datasets, predictive feature selection, and evaluation of resulting classifiers. Using a 7-day window, a naive Bayesian classifier, adaptive Bayesian network, and support vector machines were able to predict asthma exacerbation occurring on day 8, with sensitivity of 0.80, 1.00, and 0.84; specificity of 0.77, 1.00, and 0.80; and accuracy of 0.77, 1.00, and 0.80, respectively. Our study demonstrated that machine learning techniques have significant potential in developing personalized decision support for chronic disease telemonitoring systems. Future studies may benefit from a comprehensive predictive framework that combines telemonitoring data with other factors affecting the likelihood of developing acute exacerbation. Approaches implemented for advanced asthma exacerbation prediction may be extended to prediction of exacerbations in patients with other chronic health conditions.

KW - Asthma exacerbation

KW - Machine learning

KW - Personalized medicine

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=84992623590&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992623590&partnerID=8YFLogxK

U2 - 10.1111/nyas.13218

DO - 10.1111/nyas.13218

M3 - Article

C2 - 27627195

AN - SCOPUS:84992623590

JO - Annals of the New York Academy of Sciences

JF - Annals of the New York Academy of Sciences

SN - 0077-8923

ER -