Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 6;9(5):e22591.
doi: 10.2196/22591.

Acute Exacerbation of a Chronic Obstructive Pulmonary Disease Prediction System Using Wearable Device Data, Machine Learning, and Deep Learning: Development and Cohort Study

Chia-Tung Wu #  1 , Guo-Hung Li #  2 , Chun-Ta Huang  3 , Yu-Chieh Cheng  2 , Chi-Hsien Chen  4 , Jung-Yien Chien  3 , Ping-Hung Kuo  3 , Lu-Cheng Kuo  3 , Feipei Lai  1
Affiliations

Acute Exacerbation of a Chronic Obstructive Pulmonary Disease Prediction System Using Wearable Device Data, Machine Learning, and Deep Learning: Development and Cohort Study

Chia-Tung Wu et al. JMIR Mhealth Uhealth. .

Abstract

Background: The World Health Organization has projected that by 2030, chronic obstructive pulmonary disease (COPD) will be the third-leading cause of mortality and the seventh-leading cause of morbidity worldwide. Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) are associated with an accelerated decline in lung function, diminished quality of life, and higher mortality. Accurate early detection of acute exacerbations will enable early management and reduce mortality.

Objective: The aim of this study was to develop a prediction system using lifestyle data, environmental factors, and patient symptoms for the early detection of AECOPD in the upcoming 7 days.

Methods: This prospective study was performed at National Taiwan University Hospital. Patients with COPD that did not have a pacemaker and were not pregnant were invited for enrollment. Data on lifestyle, temperature, humidity, and fine particulate matter were collected using wearable devices (Fitbit Versa), a home air quality-sensing device (EDIMAX Airbox), and a smartphone app. AECOPD episodes were evaluated via standardized questionnaires. With these input features, we evaluated the prediction performance of machine learning models, including random forest, decision trees, k-nearest neighbor, linear discriminant analysis, and adaptive boosting, and a deep neural network model.

Results: The continuous real-time monitoring of lifestyle and indoor environment factors was implemented by integrating home air quality-sensing devices, a smartphone app, and wearable devices. All data from 67 COPD patients were collected prospectively during a mean 4-month follow-up period, resulting in the detection of 25 AECOPD episodes. For 7-day AECOPD prediction, the proposed AECOPD predictive model achieved an accuracy of 92.1%, sensitivity of 94%, and specificity of 90.4%. Receiver operating characteristic curve analysis showed that the area under the curve of the model in predicting AECOPD was greater than 0.9. The most important variables in the model were daily steps walked, stairs climbed, and daily distance moved.

Conclusions: Using wearable devices, home air quality-sensing devices, a smartphone app, and supervised prediction algorithms, we achieved excellent power to predict whether a patient would experience AECOPD within the upcoming 7 days. The AECOPD prediction system provided an effective way to collect lifestyle and environmental data, and yielded reliable predictions of future AECOPD events. Compared with previous studies, we have comprehensively improved the performance of the AECOPD prediction model by adding objective lifestyle and environmental data. This model could yield more accurate prediction results for COPD patients than using only questionnaire data.

Keywords: chronic obstructive pulmonary disease; clinical decision support systems; health risk assessment; wearable device.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
System architecture of the acute exacerbation of chronic obstructive pulmonary disease (AECOPD) prediction system. API: application programming interface; COPD: chronic obstructive pulmonary disease; mMRC: modified Medical Research Council dyspnea scale.
Figure 2
Figure 2
Data visualization from the lifestyle observation platform. Pm2.5: fine particulate matter.
Figure 3
Figure 3
Daily prediction of acute exacerbation of chronic obstructive pulmonary disease.
Figure 4
Figure 4
Data hierarchy workflow. PI: principal investigator.
Figure 5
Figure 5
Screenshots of NTU-med-good health advice app.
Figure 6
Figure 6
Forward padding for questionnaire data. AE: acute exacerbation.
Figure 7
Figure 7
Decision rules for data selection. COPD: chronic obstructive pulmonary disease; AE: acute exacerbation.
Figure 8
Figure 8
Correlation matrix of physiological and environmental data.
Figure 9
Figure 9
Deep neural network model architecture. PReLU: parametric rectified linear unit.
Figure 10
Figure 10
Workflow of 3-fold cross-validation.
Figure 11
Figure 11
Acute exacerbation of chronic obstructive pulmonary disorder probability trends versus normalized distributions of physiological and environmental factors. HR: heart rate; AE: acute exacerbation: PM2.5: fine particulate matter.
Figure 12
Figure 12
Receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve of all models. AE: acute exacerbation; KNN: k-nearest neighbor; LDA: linear discriminant analysis.
Figure 13
Figure 13
Acute exacerbation of chronic obstructive pulmonary disease prediction system.
Figure 14
Figure 14
Feature importance scores as evaluated by random forest.
See this image and copyright information in PMC

References

    1. Qureshi H, Sharafkhaneh A, Hanania NA. Chronic obstructive pulmonary disease exacerbations: latest evidence and clinical implications. Ther Adv Chronic Dis. 2014 Sep 14;5(5):212–227. doi: 10.1177/2040622314532862. https://journals.sagepub.com/doi/10.1177/2040622314532862?url_ver=Z39.88... - DOI - DOI - PMC - PubMed
    1. Yan R, Wang Y, Bo J, Li W. Healthy lifestyle behaviors among individuals with chronic obstructive pulmonary disease in urban and rural communities in China: a large community-based epidemiological study. Int J Chron Obstruct Pulmon Dis. 2017;12:3311–3321. doi: 10.2147/COPD.S144978. - DOI - PMC - PubMed
    1. Global Initiative for Chronic Obstructive Lung Disease. [2021-03-23]. https://goldcopd.org/
    1. Ambrosino N, Bertella E. Lifestyle interventions in prevention and comprehensive management of COPD. Breathe (Sheff) 2018 Sep 31;14(3):186–194. doi: 10.1183/20734735.018618. http://europepmc.org/abstract/MED/30186516 - DOI - PMC - PubMed
    1. Adibi A, Sin DD, Safari A, Johnson KM, Aaron SD, FitzGerald JM, Sadatsafavi M. The Acute COPD Exacerbation Prediction Tool (ACCEPT): a modelling study. Lancet Respir Med. 2020 Oct;8(10):1013–1021. doi: 10.1016/S2213-2600(19)30397-2. - DOI - PubMed

Publication types