Answers are grounded in this paper and cite their sources.
Summary Sweat contains physiological information for non-invasive health monitoring. However, the complexity of sweat components makes signal decoupling challenging; this traditionally relies on selective sensors to detect specific biomarkers and manual analysis for decoupling, which are susceptible to interference and signal drift. In this study, we present an intrinsic ion dynamics-dependent sweat identification strategy by combining an inkjet-printed customized organic electrochemical transistor (OECT) array with artificial intelligence (AI) algorithms. The OECT array comprises two types of channel films, featuring 3D-interconnected porous (3D-IP) structures with facilitated ion transport and tabular porous (TP) structures with enhanced electron transport. The designed OECT array achieves a differentiated dynamic electrochemical response for specific sweat components, thereby constructing ion dynamics-based fingerprint information for sweat identification. Integrated with flexible peripheral circuitry and a convolutional neural network, the OECT array can distinguish six samples of artificial sweat and four samples of real sweat with accuracies of 95.0% and 98.0%, respectively.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: