Personalized glucose forecasting for type 2 diabetes using data assimilation.

PLoS Comput Biol 2017 04 27;13(4):e1005232. Epub 2017 Apr 27.

Department of Biomedical Informatics, Columbia University, New York, New York, United States of America.

Type 2 diabetes leads to premature death and reduced quality of life for 8% of Americans. Nutrition management is critical to maintaining glycemic control, yet it is difficult to achieve due to the high individual differences in glycemic response to nutrition. Anticipating glycemic impact of different meals can be challenging not only for individuals with diabetes, but also for expert diabetes educators. Personalized computational models that can accurately forecast an impact of a given meal on an individual's blood glucose levels can serve as the engine for a new generation of decision support tools for individuals with diabetes. However, to be useful in practice, these computational engines need to generate accurate forecasts based on limited datasets consistent with typical self-monitoring practices of individuals with type 2 diabetes. This paper uses three forecasting machines: (i) data assimilation, a technique borrowed from atmospheric physics and engineering that uses Bayesian modeling to infuse data with human knowledge represented in a mechanistic model, to generate real-time, personalized, adaptable glucose forecasts; (ii) model averaging of data assimilation output; and (iii) dynamical Gaussian process model regression. The proposed data assimilation machine, the primary focus of the paper, uses a modified dual unscented Kalman filter to estimate states and parameters, personalizing the mechanistic models. Model selection is used to make a personalized model selection for the individual and their measurement characteristics. The data assimilation forecasts are empirically evaluated against actual postprandial glucose measurements captured by individuals with type 2 diabetes, and against predictions generated by experienced diabetes educators after reviewing a set of historical nutritional records and glucose measurements for the same individual. The evaluation suggests that the data assimilation forecasts compare well with specific glucose measurements and match or exceed in accuracy expert forecasts. We conclude by examining ways to present predictions as forecast-derived range quantities and evaluate the comparative advantages of these ranges.

Download full-text PDF

Source
http://dx.doi.org/10.1371/journal.pcbi.1005232DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5409456PMC
April 2017
3 Reads

Publication Analysis

Top Keywords

data assimilation
24
type diabetes
16
glucose measurements
12
model selection
8
diabetes
8
individuals type
8
assimilation forecasts
8
diabetes educators
8
individuals diabetes
8
data
7
assimilation
6
model
5
glucose
5
forecasts
5
engineering bayesian
4
reviewing set
4
bayesian modeling
4
personalized
4
physics engineering
4
set historical
4

References

(Supplied by CrossRef)
Data assimilation
K Law et al.
2015
Stochastic processes and Filtering Theory
A Jazwinski et al.
1998
Analysis methods for numerical weather prediction
A Lorenc et al.
Q J R Meterol Soc 1988
Atmospheric data analysis
R Daley et al.
1991
Beyond the Kalman filter: particle filters for tracking and applications
B Ristic et al.
2004
Baysian estimation and tracking
A Haug et al.
2012
Closed-loop control of blood glucose
F Chee et al.
2007
Cardiac Arrhythmias and Device Therapy: Results and Perspectives for the New Century
L Glass et al.
2000

Similar Publications