Back to results
US 6,326,160 B1Granted
Microprocessors for use in a device for predicting physiological values
AssigneeCygnus, Inc.
InventorsTimothy C. Dunn, Yalia Jayalakshmi, Ronald T. Kurnik, Matthew J. Lesho, Jonathan James Oliver, Russell O. Potts, Janet A. Tamada, Steven Richard Waterhouse, Charles W. Wei
Life of this patent
Estimating the term…
Abstract
The invention relates generally to methods, systems, and devices for measuring the concentration of target analytes present in a biological system using a series of measurements obtained from a monitoring system and a Mixtures of Experts (MOE) algorithm. In one embodiment, the present invention describes a method for measuring blood glucose in a subject.
Claims20
One or more microprocessors for use in an analyte monitoring system, said one or more microprocessors programmed to:
- (i) control a measurement cycle comprising
- (a) operating a sampling device for extracting a series of samples at selected time intervals from a biological system, wherein each sample comprises the analyte, and
- (b) operating a sensing device for sensing the analyte in each extracted sample to obtain a raw signal from each sample that is related to the analyte amount or concentration in the biological system, thus providing a series of raw signals at selected time intervals, said sensing device comprising a sensor,
- (ii) correlate the raw signals with measurement values indicative of the amount or concentration of analyte present in the biological system, and
- (iii) predict a measurement value using a Mixtures of Experts algorithm, where the individual experts have a linear form An = ∑ i = 1 n An i w i ( 1 )
- wherein (An) is an analyte of interest, n is the number of experts, Ani is the analyte predicted by Expert i;
- and wi is a weighting value, and the individual experts Ani are further defined by the expression shown as Equation (2) An i = ∑ j = 1 m a ij P j + z i ( 2 )
- wherein, Ani is the analyte predicted by Expert i;
- Pj is one of m parameters, m is typically less than 100;
- αij are coefficients;
- and zi is a constant;
- and further where the weighting value, wi, is defined by the formula shown as Equation (3) w i = ⅇ d i [ ∑ k = 1 n ⅇ d k ] ( 3 )
- where e refers to the exponential function and the dk are a parameter set analogous to Equation 2 that is used to determine the weights wi, the dk are given by Equation 4 d k = ∑ j = 1 m α jk P j + ω k ( 4 )
- where αjk is a coefficient, Pj is one of m parameters, and where ωk is a constant.
11 more elements
One or more microprocessors for use in a glucose monitoring system, said one or more microprocessors programmed to:
- (i) control a sensing device, in operative contact with a sample comprising glucose extracted from a subject, to obtain a series of raw signals at selected time intervals, wherein each raw signal is specifically related to blood glucose in the subject,
- (ii) correlate the raw signals with measurement values indicative of an amount or concentration of blood glucose present in the subject, and
- (iii) predict a measurement value using a Mixtures of Experts algorithm, where the individual experts have a linear form
- BG=w1BG1+w2BG2+w3BG3 (5)
- wherein (BG) is blood glucose, there are three experts (n=3) and BGi is the analyte predicted by Expert i;
- wi is a weighting value, and the individual Experts BGi are further defined by the expression shown as Equations 6, 7, and 8
- BG1=p1(time)+q1(active)+r1(signal)+s1(BG/cp)+t1 (6)
- BG2=p2(time)+q2(active)+r2(signal)+s2(BG/cp)+t2 (7)
- BG3=p3(time)+q3(active)+r3(signal)+s3(BG/Cp)+t3 (8)
- wherein, BGi is the analyte predicted by Expert i;
- parameters include, time (elapsed time since the sampling system was placed in operative contact with said biological system), active (active signal), signal (calibrated signal), and BG/cp (blood glucose value at a calibration point);
- Pi, qi, ri, and si are coefficients;
- and ti is a constant;
- and further where the weighting value, wi, is defined by the formulas shown as Equations 9, 10, and 11 w 1 = ⅇ d 1 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 9 ) w 2 = ⅇ d 2 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 10 ) w 3 = ⅇ d 3 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 11 )
- where e refers to the exponential function and di is a parameter set used to determine the weights w1, given by Equations 9, 10, and 11, and
- d1=τ1(time)+β1(active)+γ1(Signal)+δ1(BG/cp)+ε1 (12)
- d2=τ2(time)+β2(active)+γ2(Signal)+δ2(BG/cp)+ε2 (13)
- d3=τ3(time)+β3(active)+γ3(Signal)+δ3(BG/cp)+ε3 (14)
- where τi, βi, γi and δi are coefficients, and where εi is a constant.
16 more elements
One or more microprocessors for use in a glucose monitoring system, said one or more microprocessors programmed to:
- (i) control a sensing device, in operative contact with a sample comprising glucose extracted from a subject, to obtain a series of raw signals at selected time intervals, wherein each raw signal is specifically related to blood glucose in the subject,
- (ii) correlate the raw signals with measurement values indicative of an amount or concentration of blood glucose present in the subject, and
- (iii) predict a measurement value using a Mixtures of Experts algorithm, where the individual experts have a linear form
- BG=w1BG1+w2BG2+w3BG3 (15)
- wherein (BG) is blood glucose, there are three experts (n=3) and BGi is the analyte predicted by Expert i;
- wi is a weighting value, and the individual Experts BGi are further defined by the expression shown as Equations 16, 17, and 18
- BG1=p1(timec)+q1(active)+r1(signal)+s1(BG/cp)+t1 (16)
- BG2=p2(timec)+q2(active)+r2(signal)+s2(BG/cp)+t2 (17)
- BG3=p3(timec)+q3(active)+r3(signal)+s3(BG/Cp)+t3 (18)
- wherein, BGi is the analyte predicted by Expert i;
- parameters include, timec (elapsed time from a calibration of said sampling system), active (active signal), signal (calibrated signal), and BG/cp (blood glucose value at a calibration point);
- pi, qi, ri, and si are coefficients;
- and ti is a constant;
- and further where the weighting value, wi, is defined by the formulas shown as Equations 19, 20, and 21 w 1 = ⅇ d 1 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 19 ) w 2 = ⅇ d 2 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 20 ) w 3 = ⅇ d 3 ⅇ d 1 + ⅇ d 2 + ⅇ d 3 ( 21 )
- where e refers to the exponential function and di is a parameter set used to determine the weights wi, given by Equations 19, 20, and 21, and
- d1=τ1(timec)+β1(active)+γ1(signal)+δ1(BG/cp)+ε1 (22)
- d2=τ2(timec)+β2(active)+γ2(signal)+δ2(BG/cp)+ε2 (23)
- d3=τ3(timec)+β3(active)+γ3(signal)+δ3(BG/cp)+ε3 (24)
- where τi, βi, γi and δi are coefficients, and where εi is a constant.
16 more elements
Dependencies are inferred from the claim text.