External Measurement of Swallowed Volume During Exercise Enabled by Stretchable Derivatives of PEDOT:PSS, Graphene, Metallic Nanoparticles, and Machine Learning

• Published in: Advanced Sensor Research Vol. 2; no. 4
• Main Authors: Polat, Beril, Rafeedi, Tarek, Becerra, Laura, Chen, Alexander X., Chiang, Kuanjung, Kaipu, Vineel, Blau, Rachel, Mercier, Patrick P., Cheng, Chung‐Kuan, Lipomi, Darren J.
• Format: Journal Article
• Language: English
• Published: Stanford John Wiley & Sons, Inc 01.04.2023; Wiley-VCH
• Subjects: Circuit boards; Conducting polymers; Cycles; Electrodes; Electromyography; Esophagus; exercise study; Graphene; Hydration; Machine learning; nanostructures on graphene; Nanowires; Nutrition; PEDOT:PSS; Perspiration; Physiology; Polyethylene glycol monomethyl ether acrylate; Polymers; Printed circuits; Remote monitoring; Remote sensors; Sensors; Silver; Strain gauges; Stretchability; surface‐electromyography; Swallowing; Wearable computers; wireless epidermal sensors
• ISSN: 2751-1219; 2751-1219
• DOI: 10.1002/adsr.202200060

Epidermal sensors for remote healthcare and performance monitoring require the ability to operate under the effects of bodily motion, heat, and perspiration. Here, the use of purpose‐synthesized polymer‐based dry electrodes and graphene‐based strain gauges to obtain measurements of swallowed volume under typical conditions of exercise is evaluated. The electrodes, composed of the common conductive polymer poly(3,4 ethylenedioxythiophene) (PEDOT) electrostatically bound to poly(styrenesulfonate)‐b‐poly(poly(ethylene glycol) methyl ether acrylate) (PSS‐b‐PPEGMEA), collect surface electromyography (sEMG) signals on the submental muscle group, under the chin. Simultaneously, the deformation of the surface of the skin is measured using strain gauges comprising single‐layer graphene supporting subcontinuous coverage of gold and a highly plasticized composite containing PEDOT:PSS. Together, these materials permit high stretchability, high resolution, and resistance to sweat. A custom printed circuit board (PCB) allows this multicomponent system to acquire strain and sEMG data wirelessly. This sensor platform is tested on the swallowing activity of a cohort of 10 subjects while walking or cycling on a stationary bike. Using a machine learning (ML) model, it is possible to predict swallowed volume with absolute errors of 36% for walking and 43% for cycling. A wearable sensor platform for detecting swallow volume during exercise is studied. Participants wear a stretchable organic sensor set and perform exercises during which they swallow various volumes of water. The data are collected, transmitted to a cellphone,  and used to train a machine learning algorithm. The sensors show promising durability and sensitivity, while the algorithm has reasonable accuracy, especially at higher swallow volumes.