Medical & Biological Engineering & Computing

, Volume 50, Issue 10, pp 1047–1057 | Cite as

Non-invasive continuous glucose monitoring: improved accuracy of point and trend estimates of the Multisensor system

  • Mattia Zanon
  • Giovanni Sparacino
  • Andrea Facchinetti
  • Michela Riz
  • Mark S. Talary
  • Roland E. Suri
  • Andreas Caduff
  • Claudio Cobelli
Original Article


Non-invasive continuous glucose monitoring (NI-CGM) sensors are still at an early stage of development, but, in the near future, they could become particularly appealing in diabetes management. Solianis Monitoring AG (Zurich, Switzerland) has proposed an approach for NI-CGM based on a multi-sensor concept, embedding primarily dielectric spectroscopy and optical sensors. This concept requires a mathematical model able to estimate glucose levels from the 150 channels directly measured through the Multisensor. A static multivariate linear regression model (with order and parameters common to the entire population of subjects) was proposed for such a scope (Caduff et al., Biosens Bioelectron 26:3794–3800, 2011). The aim of this work is to evaluate the accuracy in the estimation of glucose levels and trends that the NI-CGM Multisensor platform can achieve by exploiting different techniques for model identification, namely, ordinary least squares, subset variable selection, partial least squares and least absolute shrinkage and selection operator (LASSO). Data collected in human beings monitored for a total of 45 study days were used for model identification and model test. Several metrics of standard use in the diabetes scientific community to measure point and clinical accuracy of glucose sensors were used to assess the models. Results indicate that the LASSO technique is superior to the others shrinking many channel weights to zero thus leading to smoother glucose profiles and resulting in a more robust model to possible artifacts in the Multisensor data. Although, as expected, the performance of the NI-CGM system with the LASSO model is not yet comparable with that of enzyme-based needle glucose sensors, glucose trends are satisfactorily estimated. Considering the non-invasive nature of the multi-sensor platform, this result can have an immediate impact in the current clinical practice, e.g., to integrate sparse self-monitoring of blood glucose data with an indication of the glucose trend to aid the diabetic patient in dealing with, or even preventing in the short time scale, the threats of critical events such as hypoglycaemia.


Diabetes Glucose sensor Self-monitoring blood glucose Multivariate models Linear regression 


  1. 1.
    Abu-Rmileh A, Garcia-Gabin W, Zambrano D (2010) A robust sliding mode controller with internal model for closed-loop artificial pancreas. Med Biol Eng Comput 48:1191–1201PubMedCrossRefGoogle Scholar
  2. 2.
    Arnold MA, Small GW (2005) Noninvasive glucose sensing. Anal Chem 77:5429–5439PubMedCrossRefGoogle Scholar
  3. 3.
    Bequette BW (2005) A critical assessment of algorithms and challenges in the development of a closed-loop artificial pancreas. Diabetes Technol Ther 7:28–47PubMedCrossRefGoogle Scholar
  4. 4.
    Bode BW, Battelino T (2010) Continuous glucose monitoring. Int J Clin Pract Suppl 166:11–15PubMedCrossRefGoogle Scholar
  5. 5.
    Burattini R, Morettini M, Di Nardo F, Boemi M (2011) Dynamics of insulin action in hypertension: assessment from minimal model interpretation of intravenous glucose tolerance test data. Med Biol Eng Comput 49:831–841PubMedCrossRefGoogle Scholar
  6. 6.
    Caduff A, Dewarrat F, Talary M, Stalder G, Heinemann L, Feldman Y (2006) Non-invasive glucose monitoring in patients with diabetes: a novel system based on impedance spectroscopy. Biosens Bioelectron 22:598–604PubMedCrossRefGoogle Scholar
  7. 7.
    Caduff A, Talary MS, Mueller M, Dewarrat F, Klisic J, Donath M, Heinemann L, Stahel WA (2009) Non-invasive glucose monitoring in patients with type 1 diabetes: a multisensor system combining sensors for dielectric and optical characterisation of skin. Biosens Bioelectron 24:2778–2784PubMedCrossRefGoogle Scholar
  8. 8.
    Caduff A, Talary MS, Zakharov P (2010) Cutaneous blood perfusion as a perturbing factor for noninvasive glucose monitoring. Diabetes Technol Ther 12:1–9PubMedCrossRefGoogle Scholar
  9. 9.
    Caduff A, Mueller M, Megej A, Dewarrat F, Suri RE, Klisic J, Donath M, Zakharov P, Schaub D, Stahel WA, Talary MS (2011) Characteristics of a multisensor system for non invasive glucose monitoring with external validation and prospective evaluation. Biosens Bioelectron 26:3794–3800CrossRefGoogle Scholar
  10. 10.
    Clarke WL, Cox D, Gonder-Frederick LA, Carter W, Pohl SL (1987) Evaluating clinical accuracy of systems for self-blood glucose monitoring systems. Diabetes Care 10:622–628PubMedCrossRefGoogle Scholar
  11. 11.
    Cobelli C, Toffolo GM, Dalla Man C, Campioni M, Denti P, Caumo A, Butler P, Rizza R (2007) Assessment of beta-cell function in humans, simultaneously with insulin sensitivity and hepatic extraction, from intravenous and oral glucose tests. Am J Physiol Endocrinol Metab 293:E1–E15PubMedCrossRefGoogle Scholar
  12. 12.
    Cobelli C, Dalla Man C, Sparacino G, Magni L, De Nicolao G, Kovatchev BP (2009) Diabetes: models, signals, and control. IEEE Rev Biomed Eng 2:54–96PubMedCrossRefGoogle Scholar
  13. 13.
    Cobelli C, Renard E, Kovatchev B (2011) Artificial pancreas: past, present, future. Diabetes 60:2672–2682PubMedCrossRefGoogle Scholar
  14. 14.
    De Jong S (1993) SIMPLS: an alternative approach to partial least squares regression. Chemom Intell Lab Syst 18:251–263CrossRefGoogle Scholar
  15. 15.
    Efron B, Hastie T, Johnstone I, Tibshirani R (2004) Least angle regression. Ann Stat 32:407–451CrossRefGoogle Scholar
  16. 16.
    Fabietti PG, Canonico V, Federici MO, Benedetti MM, Sarti E (2006) Control oriented model of insulin and glucose dynamics in type 1 diabetics. Med Biol Eng Comput 44:69–78PubMedCrossRefGoogle Scholar
  17. 17.
    Galvanin F, Barolo M, Macchietto S, Bezzo F (2011) Optimal design of clinical tests for the identification of physiological models of type 1 diabetes in the presence of model mismatch. Med Biol Eng Comput 49:263–277PubMedCrossRefGoogle Scholar
  18. 18.
    Guerra S, Facchinetti A, Sparacino G, De Nicolao G, Cobelli C (2012) Enhancing the accuracy of subcutaneous glucose sensors: a real-time deconvolution-based approach. IEEE Trans Biomed Eng (Epub ahead of print)Google Scholar
  19. 19.
    Guerra S, Facchinetti A, Sparacino G, De Nicolao G, Cobelli C Method to recalibrate continuous glucose monitoring data on-line. International patent application, International Bureau of the World Intellectual Property Organization, Geneva. Official Filing number: PCT/IB2010/054947Google Scholar
  20. 20.
    Guerra S, Sparacino G, Facchinetti A, Schiavon M, Dalla Man C, Cobelli C (2011) A dynamic risk measure from continuous glucose monitoring data. Diabetes Technol Ther 13:843–852PubMedCrossRefGoogle Scholar
  21. 21.
    Hastie TJ, Tibshirani R, Friedman JH (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New York, pp 43–94, 219–257Google Scholar
  22. 22.
    Hovorka R (2008) The future of continuous glucose monitoring: closed loop. Curr Diabetes Rev 4:269–279PubMedCrossRefGoogle Scholar
  23. 23.
    Kovatchev BP, Cox DJ, Gonder-Frederick LA, Clarke W (1997) Symmetrization of the blood glucose measurement scale and its applications. Diabetes Care 20:1655–1658PubMedCrossRefGoogle Scholar
  24. 24.
    Kovatchev BP, Gonder-Frederick LA, Cox DJ, Clarke WL (2004) Evaluating the accuracy of continuous glucose-monitoring sensors. Diabetes Care 27:1922–1928PubMedCrossRefGoogle Scholar
  25. 25.
    Kovatchev B, Anderson S, Heinemann L, Clarke W (2008) Comparison of the numerical and clinical accuracy of four continuous glucose monitors. Diabetes Care 31:1160–1164PubMedCrossRefGoogle Scholar
  26. 26.
    Larin KV, Eledrisi MS, Motamedi M, Esenaliev RO (2002) Noninvasive blood glucose monitoring with optical coherence tomography: a pilot study in human subjects. Diabetes Care 25:2263–2267PubMedCrossRefGoogle Scholar
  27. 27.
    Magni L, Raimondo DM, Dalla Man C, De Nicolao G, Kovatchev B, Cobelli C (2009) Model predictive control of glucose concentration in type I diabetic patients: an in silico trial. Biomed Signal Process 4:338–346CrossRefGoogle Scholar
  28. 28.
    McGarraugh G (2009) The chemistry of commercial continuous glucose monitors. Diabetes Technol Ther 11:17–24CrossRefGoogle Scholar
  29. 29.
    Mueller M, De Feo O, Talary MS, Stahel WA, Falco L, Caduff A (2011) Data processing for non-invasive continuous glucose monitoring with a multi-Sensor device. J Diabetes Sci Technol 5:694–702PubMedGoogle Scholar
  30. 30.
    Sparacino G, Zanderigo F, Corazza S, Maran A, Facchinetti A, Cobelli C (2007) Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series. IEEE Trans Biomed Eng 54:931–937PubMedCrossRefGoogle Scholar
  31. 31.
    Sparacino G, Facchinetti A, Cobelli C (2010) “Smart” continuous glucose monitoring sensors: on-line signal processing issues. Sensors 10:6751–6772PubMedCrossRefGoogle Scholar
  32. 32.
    Tibshirani R (1994) Regression shrinkage and selection via the lasso. J R Stat Soc Ser B 58:267–288Google Scholar
  33. 33.
    Tikhonov AN, Arsenin VY (1977) Solutions of ill-posed problems. Winston/Wiley, Washington, DCGoogle Scholar
  34. 34.
    Tura A, Maran A, Pacini G (2007) Non-invasive glucose monitoring: assessment of technologies and devices according to quantitative criteria. Diabetes Res Clin Pract 77:16–40PubMedCrossRefGoogle Scholar
  35. 35.
    Updike SJ, Hicks GP (1967) The enzyme electrode. Nature 214:986–988PubMedCrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2012

Authors and Affiliations

  • Mattia Zanon
    • 1
  • Giovanni Sparacino
    • 1
  • Andrea Facchinetti
    • 1
  • Michela Riz
    • 1
  • Mark S. Talary
    • 2
  • Roland E. Suri
    • 3
  • Andreas Caduff
    • 2
  • Claudio Cobelli
    • 1
  1. 1.Department of Information EngineeringUniversity of PadovaPaduaItaly
  2. 2.Biovotion AGZurichSwitzerland
  3. 3.ZurichSwitzerland

Personalised recommendations