Premium
Correlated gamma‐based hidden Markov model for the smart asthma management based on rescue inhaler usage
Author(s) -
Son Junbo,
Brennan Patricia Flatley,
Zhou Shiyu
Publication year - 2017
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.7214
Subject(s) - inhaler , asthma , medicine , asthma exacerbations , hidden markov model , computer science , markov chain , markov model , medical emergency , artificial intelligence , machine learning
Asthma is a very common chronic disease that affects a large portion of population in many nations. Driven by the fast development in sensor and mobile communication technology, a smart asthma management system has become available to continuously monitor the key health indicators of asthma patients. Such data provides opportunities for healthcare practitioners to examine patients not only in the clinic (on‐site) but also outside of the clinic (off‐site) in their daily life. In this paper, taking advantage from this data availability, we propose a correlated gamma‐based hidden Markov model framework, which can reveal and highlight useful information from the rescue inhaler‐usage profiles of individual patients for practitioners. The proposed method can provide diagnostic information about the asthma control status of individual patients and can help practitioners to make more informed therapeutic decisions accordingly. The proposed method is validated through both numerical study and case study based on real world data. Copyright © 2017 John Wiley & Sons, Ltd.