Personalized glucose forecasting for type 2 diabetes using data assimilation

David J. Albers, Matthew Levine, Bruce Gluckman, Henry Ginsberg, George Hripcsak, Lena Mamykina

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Article numbere1005232
JournalPLoS computational biology
Volume13
Issue number4
DOIs
StatePublished - Apr 1 2017

Fingerprint

Data Assimilation
diabetes
Diabetes
Medical problems
Glucose
noninsulin-dependent diabetes mellitus
data assimilation
Type 2 Diabetes Mellitus
Forecast
Forecasting
assimilation (physiology)
glucose
Meals
mechanistic models
engines
meals (menu)
teachers
Nutrition
Premature Mortality
Physics

All Science Journal Classification (ASJC) codes

  • Ecology, Evolution, Behavior and Systematics
  • Modeling and Simulation
  • Ecology
  • Molecular Biology
  • Genetics
  • Cellular and Molecular Neuroscience
  • Computational Theory and Mathematics

Cite this

Albers, David J. ; Levine, Matthew ; Gluckman, Bruce ; Ginsberg, Henry ; Hripcsak, George ; Mamykina, Lena. / Personalized glucose forecasting for type 2 diabetes using data assimilation. In: PLoS computational biology. 2017 ; Vol. 13, No. 4.
@article{cfd9373901ef44c68f9b986b3f8b634a,
title = "Personalized glucose forecasting for type 2 diabetes using data assimilation",
abstract = "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.",
author = "Albers, {David J.} and Matthew Levine and Bruce Gluckman and Henry Ginsberg and George Hripcsak and Lena Mamykina",
year = "2017",
month = "4",
day = "1",
doi = "10.1371/journal.pcbi.1005232",
language = "English (US)",
volume = "13",
journal = "PLoS Computational Biology",
issn = "1553-734X",
publisher = "Public Library of Science",
number = "4",

}

Personalized glucose forecasting for type 2 diabetes using data assimilation. / Albers, David J.; Levine, Matthew; Gluckman, Bruce; Ginsberg, Henry; Hripcsak, George; Mamykina, Lena.

In: PLoS computational biology, Vol. 13, No. 4, e1005232, 01.04.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Personalized glucose forecasting for type 2 diabetes using data assimilation

AU - Albers, David J.

AU - Levine, Matthew

AU - Gluckman, Bruce

AU - Ginsberg, Henry

AU - Hripcsak, George

AU - Mamykina, Lena

PY - 2017/4/1

Y1 - 2017/4/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85018307645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018307645&partnerID=8YFLogxK

U2 - 10.1371/journal.pcbi.1005232

DO - 10.1371/journal.pcbi.1005232

M3 - Article

VL - 13

JO - PLoS Computational Biology

JF - PLoS Computational Biology

SN - 1553-734X

IS - 4

M1 - e1005232

ER -