Predictive Monitoring for Improved Management of Glucose Levels

Reifman, Jaques; Rajaraman, Srinivasan; Gribok, Andrei V.; Ward, W. Kenneth

doi:10.1177/193229680700100405

Cited by 111 publications

(113 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The 5-min sampling interval is half the "optimal" sampling interval (10 min) recommended in the literature [9]. Additional information about this independent study can also be found in the work by Reifman et al [10].…”

Section: ) Isense Datasetmentioning

confidence: 88%

Universal Glucose Models for Predicting Subcutaneous Glucose Concentration in Humans

Gani

Gribok

et al. 2010

IEEE Trans. Inform. Technol. Biomed.

118

100

View full text Add to dashboard Cite

Abstract-This paper tests the hypothesis that a "universal," data-driven model can be developed based on glucose data from one diabetic subject, and subsequently applied to predict subcutaneous glucose concentrations of other subjects, even of those with different types of diabetes. We employed three separate studies, each utilizing a different continuous glucose monitoring (CGM) device, to verify the model's universality. Two out of the three studies involved subjects with type 1 diabetes and the other one with type 2 diabetes. We first filtered the subcutaneous glucose concentration data by imposing constraints on their rate of change. Then, using the filtered data, we developed data-driven autoregressive models of order 30, and used them to make short-term, 30-min-ahead glucose-concentration predictions. We used same-subject model predictions as a reference for comparisons against cross-subject and cross-study model predictions, which were evaluated using the root-mean-squared error (RMSE) and Clarke error grid analysis (EGA). We found that, for each studied subject, the average crosssubject and cross-study RMSEs of the predictions were small and indistinguishable from those obtained with the same-subject models. These observations were corroborated by EGA, where better than 99.0% of the paired sensor-predicted glucose concentrations lay in the clinically acceptable zone A. In addition, the predictive capability of the models was found not to be affected by diabetes type, subject age, CGM device, and interindividual differences. We conclude that it is feasible to develop universal glucose models that allow for clinical use of predictive algorithms and CGM devices for proactive therapy of diabetic patients.

show abstract

Section: ) Isense Datasetmentioning

confidence: 88%

Universal Glucose Models for Predicting Subcutaneous Glucose Concentration in Humans

Gani

Gribok

et al. 2010

IEEE Trans. Inform. Technol. Biomed.

118

100

View full text Add to dashboard Cite

show abstract

“…CBGM, insulin dosages, carbohydrate intakes, hypoglycemic and hyperglycemic symptoms, lifestyle activities, events and emotional state). Unfortunately the prediction accuracy cannot be compared with that reported in other works in the literature [1,10,11] because they calculated the mean percent absolute difference of the model's predictive abilities instead of the commonly used evaluation parameters. They concluded that the model tended to underestimate extreme hyperglycemic values and overestimate hypoglycemic values.…”

Section: Introductionmentioning

confidence: 91%

“…Reifman et al [11] used a 10th-order data-driven ARM. The inputs of the model were the previously observed glucose levels.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network Algorithm for Online Glucose Prediction from Continuous Glucose Monitoring

Pérez-Gandía

Facchinetti

Sparacino

et al. 2010

Diabetes Technology & Therapeutics

266

177

View full text Add to dashboard Cite

Background and Aims: Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real-time to predict future glucose levels in order to prevent hypo/hyperglycemic events. This paper proposes a new on-line method for predicting future glucose concentration levels from CGM data. Methods:The predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 minutes, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (9 subjects using the Medtronic Guardian and 6 subjects using the Abbott Navigator). Three different PH are used, i.e. 15, 30 and 45 minutes. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay. Results:The RMSE is around 10, 18 and 27 mg/dl for 15, 30 and 45 minutes of PH, respectively. The prediction delay is around 4, 9 and 14 minutes for upward trends and 5, 15 and 26 minutes for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM) [1], has been performed. The comparison shows that, the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay. Conclusions:The proposed NNM is a reliable solution for the on-line prediction of future glucose concentrations from CGM data.

show abstract

“…Despite their potential benefits, to date, only Cobelli's [8], [9] and our group [10] have proposed AR models for predicting individual-specific glucose concentrations. In [8], Sparacino et al use a first-order AR model, AR (1), in which the model's coefficient is dynamically computed at each time step through a weighted least squares.…”

mentioning

confidence: 99%

Predicting Subcutaneous Glucose Concentration in Humans: Data-Driven Glucose Modeling

Gani

Gribok

Rajaraman

et al. 2009

IEEE Trans. Biomed. Eng.

118

106

View full text Add to dashboard Cite

Abstract-The combination of predictive data-driven models with frequent glucose measurements may provide for an early warning of impending glucose excursions and proactive regulatory interventions for diabetes patients. However, from a modeling perspective, before the benefits of such a strategy can be attained, we must first be able to quantitatively characterize the behavior of the model coefficients as well as the model predictions as a function of prediction horizon. We need to determine if the model coefficients reflect viable physiologic dependencies of the individual glycemic measurements and whether the model is stable with respect to small changes in noise levels, leading to accurate near-future predictions with negligible time lag. We assessed the behavior of linear autoregressive data-driven models developed under three possible modeling scenarios, using continuous glucose measurements of nine subjects collected on a minute-by-minute basis for approximately 5 days. Simulation results indicated that stable and accurate models for near-future glycemic predictions (<60 min) with clinically acceptable time lags are attained only when the raw glucose measurements are smoothed and the model coefficients are regularized. This study provides a starting point for further needed investigations before real-time deployment can be considered.

show abstract

Predictive Monitoring for Improved Management of Glucose Levels

Cited by 111 publications

References 15 publications

Universal Glucose Models for Predicting Subcutaneous Glucose Concentration in Humans

Universal Glucose Models for Predicting Subcutaneous Glucose Concentration in Humans

Artificial Neural Network Algorithm for Online Glucose Prediction from Continuous Glucose Monitoring

Predicting Subcutaneous Glucose Concentration in Humans: Data-Driven Glucose Modeling

Contact Info

Product

Resources

About