Abstract
In healthcare industries, non-invasive sensor technology has played an important role in gathering biometric information without blood sampling for each patient. Existing studies have attempted to predict blood component levels based on non-invasive sensor coupled with machine learning models. However, they focused on constructing a single output model that predicts only one blood component level. In this study, we propose a multi-output predictive model that can predict the multiple blood components levels simultaneously based on non-invasive impedance sensor data. Results show that our method improves predictive performance compared to the single output models. Furthermore, we use Shapley additive explanation to identify important sensor variables that achieve efficient sensor design reducing the cost of data collection. To the best of our knowledge, this study is the first attempt to use non-invasive impedance sensor data to predict multiple blood components levels.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of the Korean Institute of Industrial Engineers
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
