The skin’s interstitial fluid (ISF) represents a versatile platform for non-invasive in vivo biosensing of systemic biomarkers such as glucose. Biomedical applications of THz spectroscopy mostly leverage the strong interaction between THz light and water by mapping frequency-dependent changes in the sample’s dielectric response. We propose a novel THz spectroscopy-based approach for non-invasive detection of glucose in the skin’s ISF in conjunction with machine learning (ML). In this study, we explore advantages and limitations an ex vivo experiment on fresh porcine skin as a proof of concept of our approach. We investigate multiple sources of variation in such a dataset to understand how well our samples represent their in vivo counterpart. We characterize inter-sample and intra-sample variations to rule out undesired bias in our data that may complicate classification or regression tasks for glucose detection. Our results indicate that occlusion during THz contact measurements affects fresh ex vivo porcine skin similarly to what has previously been reported for in vivo human skin. Data processing strategies for ex vivo experiments for THz spectroscopy or imaging should therefore find ways to account for these effects.
The skin's interstitial fluid is rich in composition and easily accessible for the monitoring of systemic biomarkers, however, THz-based molecular detection in biological media is challenging. Machine learning can provide solutions, but strict data engineering is required to avoid confounding trends and ensure large training datasets. We propose an experimental framework to mimic interstitial fluid diffusion in ex vivo pig skin to detect analytes via THz-ATR spectroscopy. We evaluate the applicability of the protocol for controlled studies of THz-ATR spectroscopy-based biomolecular detection in skin. Our findings can significantly contribute to the field of ML-reinforced biosensing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.