Back to Search Start Over

Skin‐Interfaced Microfluidic System with Machine Learning‐Enabled Image Processing of Sweat Biomarkers in Remote Settings.

Authors :
Baker, Lindsay B.
Seib, Melissa S.
Barnes, Kelly A.
Brown, Shyretha D.
King, Michelle A.
De Chavez, Peter John D.
Qu, Shankang
Archer, Julian
Wolfe, Anthony S.
Stofan, John R.
Carter, James M.
Wright, Donald E.
Wallace, Jessica
Yang, Da Som
Liu, Shanliangzi
Anderson, John
Fort, Tucker
Li, Weihua
Wright, John A.
Lee, Stephen P.
Source :
Advanced Materials Technologies; Nov2022, Vol. 7 Issue 11, p1-13, 13p
Publication Year :
2022

Abstract

Dehydration has many deleterious effects on cognitive and physical performance as well as physiological function, in the context of sports, industrial work, clinical rehabilitation, and military applications. Because sweat loss and electrolyte loss vary across individuals, conventional sweat testing strategies using absorbent patch techniques are employed in laboratory settings to characterize sweat biomarkers; however, these techniques are not suitable for remote environments. Here, an updated wearable microfluidic sweat testing system targeted for recreational athletes is presented that includes a microfluidic patch accommodating a broad range of sweating rates, and a smartphone app incorporating digital image processing algorithms to enable real‐time analysis under different lighting conditions and patch orientations. Expansive field trials (n = 148 subjects) show significant correlations between the microfluidic patch and standard absorbent patch in measuring sweating rate and sweat chloride concentration during recreational exercise. This validation study demonstrates the applicability of the microfluidic patch and software platform for field testing in recreational athletes. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
2365709X
Volume :
7
Issue :
11
Database :
Complementary Index
Journal :
Advanced Materials Technologies
Publication Type :
Academic Journal
Accession number :
160178045
Full Text :
https://doi.org/10.1002/admt.202200249