@inproceedings{13bf296a50d640a0ac4218d795ffac75,
title = "Predicting asthma exacerbations using artificial intelligence",
abstract = "Modern telemonitoring systems identify a serious patient deterioration when it already occurred. It would be much more beneficial if the upcoming clinical deterioration were identified ahead of time even before a patient actually experiences it. The goal of this study was to assess artificial intelligence approaches which potentially can be used in telemonitoring systems for advance prediction of changes in disease severity before they actually occur. The study dataset was based on daily self-reports submitted by 26 adult asthma patients during home telemonitoring consisting of 7001 records. Two classification algorithms were employed for building predictive models: na{\"i}ve Bayesian classifier and support vector machines. Using a 7-day window, a support vector machine was able to predict asthma exacerbation to occur on the day 8 with the accuracy of 0.80, sensitivity of 0.84 and specificity of 0.80. Our study showed that methods of artificial intelligence have significant potential in developing individualized decision support for chronic disease telemonitoring systems.",
keywords = "Computer-assisted instruction, health education, internet search",
author = "Joseph Finkelstein and Jeffrey Wood",
year = "2013",
doi = "10.3233/978-1-61499-276-9-56",
language = "English",
isbn = "9781614992752",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "56--58",
booktitle = "Informatics, Management and Technology in Healthcare",
address = "United States",
note = "International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2013 ; Conference date: 05-07-2013 Through 07-07-2013",
}