Prediction of 30-day readmission for COPD patients using accelerometer-based activity monitoring

Wen Yen Lin*, Vijay Kumar Verma, Ming Yih Lee, Horng Chyuan Lin, Chao Sung Lai

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

8 Scopus citations

Abstract

Chronic obstructive pulmonary disease (COPD) claimed 3.0 million lives in 2016 and ranked 3rd among the top 10 global causes of death. Moreover, once diagnosed and discharged from the hospital, the 30-day readmission risk in COPD patients is found to be the highest among all chronic diseases. The existing diagnosis methods, such as Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2019, Body-mass index, airflow Obstruction, Dyspnea, and Exercise (BODE) index, modified Medical Research Council (mMRC), COPD assessment test (CAT), 6-minute walking distance, which are adopted currently by physicians cannot predict the potential readmission of COPD patients, especially within the 30 days after discharge from the hospital. In this paper, a statistical model was proposed to predict the readmission risk of COPD patients within 30-days by monitoring their physical activity (PA) in daily living with accelerometer-based wrist-worn wearable devices. This proposed model was based on our previously reported PA models for activity index (AI) and regularity index (RI) and it introduced a new parameter, quality of activity (QoA), which incorporates previously proposed parameters, such as AI and RI, with other activity-based indices to predict the readmission risk. Data were collected from continuous PA monitoring of 16 COPD patients after hospital discharge as test subjects and readmission prediction criteria were proposed, with a 63% sensitivity and a 37.78% positive prediction rate. Compared to other clinical assessment, diagnosis, and prevention methods, the proposed model showed significant improvement in predicting the 30-day readmission risk.

Original languageEnglish
Article number217
JournalSensors
Volume20
Issue number1
DOIs
StatePublished - 01 01 2020

Bibliographical note

Publisher Copyright:
© 2019 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

  • Accelerometers
  • Actigraphy
  • Activity monitoring
  • COPD
  • Prediction
  • Readmission risk
  • Wearable devices

Fingerprint

Dive into the research topics of 'Prediction of 30-day readmission for COPD patients using accelerometer-based activity monitoring'. Together they form a unique fingerprint.

Cite this