Literature DB >> 32718193

Detecting asthma exacerbations using daily home monitoring and machine learning.

Olivier Zhang1, Leandro L Minku2, Sherif Gonem3,4.   

Abstract

OBJECTIVE: Acute exacerbations contribute significantly to the morbidity of asthma. Recent studies have shown that early detection and treatment of asthma exacerbations leads to improved outcomes. We aimed to develop a machine learning algorithm to detect severe asthma exacerbations using easily available daily monitoring data.
METHODS: We analyzed daily peak expiratory flow and symptom scores recorded by participants in the SAKURA study (NCT00839800), an international multicentre randomized controlled trial comparing budesonide/formoterol as maintenance and reliever therapy versus budesonide/formoterol maintenance plus terbutaline as reliever, in adults with persistent asthma. The dataset consisted of 728,535 records of daily monitoring data in 2010 patients, with 576 severe exacerbation events. Data post-processing techniques included normalization, standardization, calculation of differences or slopes over time and the use of smoothing filters. Principal components analysis was used to reduce the large number of derived variables to a smaller number of linearly independent components. Logistic regression, decision tree, naïve Bayes, and perceptron algorithms were evaluated. Model accuracy was assessed using stratified cross-validation. The primary outcome was the detection of exacerbations on the same day or up to three days in the future.
RESULTS: The best model used logistic regression with input variables derived from post-processed data using principal components analysis. This had an area under the receiver operating characteristic curve of 0.85, with a sensitivity of 90% and specificity of 83% for severe asthma exacerbations.
CONCLUSION: Asthma exacerbations may be detected using machine learning algorithms applied to daily self-monitoring of peak expiratory flow and asthma symptoms.

Entities:  

Keywords:  Asthma; exacerbation; home monitoring; machine learning; peak expiratory flow

Mesh:

Substances:

Year:  2020        PMID: 32718193     DOI: 10.1080/02770903.2020.1802746

Source DB:  PubMed          Journal:  J Asthma        ISSN: 0277-0903            Impact factor:   2.515


  5 in total

1.  Factors Predicting Treatment of World Trade Center-Related Lung Injury: A Longitudinal Cohort Study.

Authors:  Barbara Putman; Lies Lahousse; David G Goldfarb; Rachel Zeig-Owens; Theresa Schwartz; Ankura Singh; Brandon Vaeth; Charles B Hall; Elizabeth A Lancet; Mayris P Webber; Hillel W Cohen; David J Prezant; Michael D Weiden
Journal:  Int J Environ Res Public Health       Date:  2020-12-04       Impact factor: 3.390

Review 2.  Application of Machine Learning Algorithms for Asthma Management with mHealth: A Clinical Review.

Authors:  Kevin C H Tsang; Hilary Pinnock; Andrew M Wilson; Syed Ahmar Shah
Journal:  J Asthma Allergy       Date:  2022-06-29

3.  Predicting asthma attacks using connected mobile devices and machine learning: the AAMOS-00 observational study protocol.

Authors:  Kevin Cheuk Him Tsang; Hilary Pinnock; Andrew M Wilson; Dario Salvi; Syed Ahmar Shah
Journal:  BMJ Open       Date:  2022-10-03       Impact factor: 3.006

Review 4.  Artificial Intelligence Techniques to Predict the Airway Disorders Illness: A Systematic Review.

Authors:  Apeksha Koul; Rajesh K Bawa; Yogesh Kumar
Journal:  Arch Comput Methods Eng       Date:  2022-09-28       Impact factor: 8.171

Review 5.  Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary Disease.

Authors:  Yinhe Feng; Yubin Wang; Chunfang Zeng; Hui Mao
Journal:  Int J Med Sci       Date:  2021-06-01       Impact factor: 3.738

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.