The Importance of Different Frequency Bands in Predicting Subcutaneous Glucose Concentration in Type 1 Diabetic Patients

Bioinformatics Cell, Telemedicine and Advanced Technology Research Center, U.S. Army Medical Research and Materiel Command, Fort Detrick, MD 21702, USA.
IEEE transactions on bio-medical engineering (Impact Factor: 2.35). 08/2010; 57(8):1839-46. DOI: 10.1109/TBME.2010.2047504
Source: PubMed


We investigated the relative importance and predictive power of different frequency bands of subcutaneous glucose signals for the short-term (0-50 min) forecasting of glucose concentrations in type 1 diabetic patients with data-driven autoregressive (AR) models. The study data consisted of minute-by-minute glucose signals collected from nine deidentified patients over a five-day period using continuous glucose monitoring devices. AR models were developed using single and pairwise combinations of frequency bands of the glucose signal and compared with a reference model including all bands. The results suggest that: for open-loop applications, there is no need to explicitly represent exogenous inputs, such as meals and insulin intake, in AR models; models based on a single-frequency band, with periods between 60-120 min and 150-500 min, yield good predictive power (error <3 mg/dL) for prediction horizons of up to 25 min; models based on pairs of bands produce predictions that are indistinguishable from those of the reference model as long as the 60-120 min period band is included; and AR models can be developed on signals of short length (approximately 300 min), i.e., ignoring long circadian rhythms, without any detriment in prediction accuracy. Together, these findings provide insights into efficient development of more effective and parsimonious data-driven models for short-term prediction of glucose concentrations in diabetic patients.

Download full-text


Available from: Andrei Gribok, Nov 12, 2015
  • Source
    • "The wavelet based time-scale distribution has been presented [14] for two non-diabetic 24-hour profiles with different meal regimens. An interesting parametric technique involving frequency band decomposition and short-term forecasting using an autoregressive model has been applied to the 72-hour profiles of nine type 1 diabetic patients [15]. We will consider a nonparametric approach to assess data interconnections and predictability in the time domain. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Continuous glucose monitoring is increasingly used in the management of diabetes. Subcutaneous glucose profiles are characterised by a strong non-stationarity, which limits the application of correlation-spectral analysis. We derived an index of linear predictability by calculating the autocorrelation function of time series increments and applied detrended fluctuation analysis to assess the non-stationarity of the profiles. Time series from volunteers with both type 1 and type 2 diabetes and from control subjects were analysed. The results suggest that in control subjects, blood glucose variation is relatively uncorrelated, and this variation could be modelled as a random walk with no retention of 'memory' of previous values. In diabetes, variation is both greater and smoother, with retention of inter-dependence between neighbouring values. Essential components for adequate longer term prediction were identified via a decomposition of time series into a slow trend and responses to external stimuli. Implications for diabetes management are discussed.
    Computer methods and programs in biomedicine 12/2012; 110(3). DOI:10.1016/j.cmpb.2012.11.009 · 1.90 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Measurement of blood glucose concentration is central to the diagnosis and treatment of diabetes. Although there are large numbers of historic glucose measurements in individuals with diabetes, until recently there have been very few data sets that were recorded continuously or sampled frequently enough to reveal intrinsic blood glucose dynamics, or the change in blood glucose with time. There have even fewer such recordings from individuals not having diabetes to serve as a therapeutic target. As a result, blood glucose dynamics have generally not been used in the diagnosis or treatment of the disease. Although present blood glucose monitoring is based largely on discrete measurements, future monitoring will likely focus on analysis of blood glucose excursions. New measurements are now being obtained, and there is a need for new methods of analysis to extract the maximal information from the data. Several approaches are demonstrated here for characterization of blood glucose dynamics, and a patient profiling system is proposed. An example of new insights is the observation that there are four time scales of blood glucose variations in individuals without diabetes, and these time scales are modified or lost in diabetes.
    Diabetes Technology &amp Therapeutics 05/2008; 10(2):81-94. DOI:10.1089/dia.2007.0256 · 2.11 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The availability of continuous glucose monitoring (CGM) sensors allows development of new strategies for the treatment of diabetes. In particular, from an on-line perspective, CGM sensors can become "smart" by providing them with algorithms able to generate alerts when glucose concentration is predicted to exceed the normal range thresholds. To do so, at least four important aspects have to be considered and dealt with on-line. First, the CGM data must be accurately calibrated. Then, CGM data need to be filtered in order to enhance their signal-to-noise ratio (SNR). Thirdly, predictions of future glucose concentration should be generated with suitable modeling methodologies. Finally, generation of alerts should be done by minimizing the risk of detecting false and missing true events. For these four challenges, several techniques, with various degrees of sophistication, have been proposed in the literature and are critically reviewed in this paper.
    Sensors 07/2010; 10(7):6751-72. DOI:10.3390/s100706751 · 2.25 Impact Factor
Show more