.png){kind=icon}
.png){kind=icon}
Return
Low-Effort Respiratory Function Estimation with a Soft Wearable Digital Spirometry Patch
.png){kind=icon}
OA
AI
DOI：10.3390/bios16050272.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spirometry is widely regarded as the clinical gold standard for quantifying lung function. It plays a central role in the diagnosis and management of cardiopulmonary disorders, including asthma and chronic obstructive pulmonary disease (COPD). However, the procedure relies on a forceful and often stressful expiratory maneuver that may cause patient discomfort and require substantial effort, frequently necessitating active coaching and trained personnel to ensure reproducible measurements. In this paper, we present the Digital Spirometry Patch (DSP), a soft, flexible, wearable patch capable of estimating lung function parameters by utilizing low-effort breathing maneuvers. Eighteen participants performed low-effort and forceful breathing maneuvers while wearing the DSP to collect tracheal sound and chest movement signals for spirometric parameter estimation using elastic net and simple linear regression. Using leave-one-subject-out cross-validation, the elastic net models achieved RMSEs of 0.668 L, 0.224 L, and 0.428 L/s for FVC, FEV1, and PEF, respectively, using low-effort breathing maneuvers, and 0.499 L, 0.304 L, and 0.891 L/s using forceful exhalation maneuvers. These results demonstrate the potential of the DSP as a wearable, low-effort alternative for estimating lung function outside of conventional spirometry settings.
Keywords:
wearable biosensor
spirometry
FVC
FEV<sub>1</sub>
PEF
linear regression
elastic net
feature extraction
cross-validation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.6
Papers:
1.2K
Citations:
1.9W
Organization
View more organizations