Skip to main content
Free-living inferential modeling of blood glucose level using only noninvasive inputs
Journal of Process Control (2010)
  • Derrick K. Rollins, Iowa State University
  • Nidhi Bhandari, Iowa State University
  • Jim Kleinedler, Iowa State University
  • Kaylee Kotz, Iowa State University
  • Amber Strohbehn, Iowa State University
  • Lindsay Boland, Iowa State University
  • Megan Murphy, Iowa State University
  • Dave Andre
  • Nisarg Vyas
  • Greg Welk, Iowa State University
  • Warren D Franke, Iowa State University
The goal of this work is to present a causation modeling methodology with the ability to accurately infer blood glucose levels using a large set of highly correlated noninvasive input variables over an extended period of time. These models can provide insight to improve glucose monitoring, and glucose regulation through advanced model-based control technologies. The efficacy of this approach is demonstrated using real data from a type 2 diabetic (T2D) subject collected under free-living conditions over a period of 25 consecutive days. The model was identified and tested using eleven variables that included three food variables as well as several activity and stress variables. The model was trained using 20 days of data and validated using 5 days of data. This gave a fitted correlation coefficient of 0.70 and an average absolute error (AAE) (i.e., the average of the absolute values for the measured glucose concentration minus modeled glucose concentration) of 13.3 mg/dL for the validation data. This AAE result was significantly better than the subject’s personal glucose meter AAE of 15.3 mg/dL for replicated measurements.
Publication Date
Publisher Statement
This article is from Journal of Process Control 20 (2010): 95-107, DOI:10.1016/j.jprocont.2009.09.008. Posted with permission.
Citation Information
Derrick K. Rollins, Nidhi Bhandari, Jim Kleinedler, Kaylee Kotz, et al.. "Free-living inferential modeling of blood glucose level using only noninvasive inputs" Journal of Process Control Vol. 20 (2010)
Available at: