Non-linear dynamic modeling of glucose in type 1 diabetes with kernel adaptive filters

Abstract

We propose a non-linear recursive solution to the problem of short-term prediction of glucose in type 1 diabetes. The Fixed Budget Quantized Kernel Least Mean Square (QKLMS-FB) algorithm is employed to construct a univariate model of subcutaneous glucose concentration, which: (i) handles nonlinearities by transforming the input space into a high-dimensional Reproducing Kernel Hilbert Space and, (ii) finds a sparse solution by retaining a representative subset of the training input vectors. The dataset comes from the continuous multi-day recordings of 15 type 1 patients in free-living conditions. QKLMS-FB produces an average root mean squared error of 18.66±3.19 mg/dl for a prediction horizon of 30 min with 82.04% of hypoglycemic readings and 93.30% of hyperglycemic ones being classified as clinically accurate or with benign errors. The effect of the prediction horizon is more evident in the hypoglycemic range.

Improving sparsity in kernel adaptive filters using a unit-norm dictionary

“…the least-mean-square (LMS) or recursive-least-square (RLS) rationales [4]. Due to the simplicity of their implementation and intuitive presentation, KAFs have been used in a number of applications from medicine [5] to telecommunications [6]; moreover, KAF is an active field of research in terms of kernel design [7], [8], [9], automatic determination of model orders [10], and learning approaches [11].…”

Development of physiological metabolic models in diabetes based on data mining techniques

“…Again, the precise merging of the same folds of each 10-fold cross-validation across all patients would be needed to ensure unbiased estimates of the prediction error. [190] and KRLS-ALD in [191]) to auto-regression of subcutaneous glucose concentration in type 1 diabetes. Herein, both univariate AR and multivariate input models are constructed and compared aiming at methodically elucidating the predictive potential of the exogenous inputs especially in critical hypoglycaemic and hyperglycaemic regions.…”